Behind the Headset: Predictive Accuracy of Patient-Reported Outcome Measures for Voice Symptoms in Call Centers

Objective: This study examines factors predicting self-reported voice symptoms in call center workers. Methods: Multivariate analysis and predictive modeling assess personal, work-related, acoustic, and behavioral factors. Generalized Linear Models (GLMs) and Receiver Operating Characteristic (ROC) curves are employed. Results: Age and sleep patterns impacted voice quality and effort, while workplace factors influenced symptom perception. Unhealthy vocal behaviors related to tense voice and increased effort, while hydration was protective. Voice acoustics showed diagnostic potential, supported by ROC data. These findings emphasize voice symptom complexity in call center professionals, necessitating comprehensive assessment. Limitations: This study recognizes its limitations, including a moderate-sized convenience sample and reliance on PROM metrics. Future research should incorporate more objective measures in addition to self-reports and acoustic analysis. Value: This research provides novel insights into the interplay of personal, occupational, and voice-related factors in developing voice symptoms among call center workers. Predictive modeling enhances risk assessment and understanding of individual susceptibility to voice disorders. Conclusion: Results show associations between various factors and self-reported voice symptoms. Protective factors include sleeping more than six hours and consistent hydration, whereas risk factors include working conditions, such as location and behaviors like smoking. Diagnostic models indicate good accuracy for some voice symptom PROMs, emphasizing the need for comprehensive models considering work factors, vocal behaviors, and acoustic parameters to understand voice issues complexity.

Objetivo: Este estudio examina los factores que predicen los síntomas de voz en los trabajadores de call centers. Métodos: Se utilizan análisis multivariados y modelos predictivos para evaluar factores personales, laborales, acústicos y de comportamiento. Se emplean Modelos Lineales Generalizados (GLM) y curvas ROC. Resultados: La edad y los patrones de sueño afectaron la calidad vocal y el esfuerzo, mientras que los factores laborales influyeron en la percepción de síntomas. Los comportamientos vocales no saludables se relacionaron con voz tensa y mayor esfuerzo, mientras que la hidratación fue protectora. Los parámetros acústicos de voz mostraron potencial diagnóstico respaldado por datos de ROC. Los hallazgos subrayan complejidad de síntomas vocales en profesionales de centros de llamadas, requiriendo una evaluación integral. Limitaciones: Este estudio reconoce sus limitaciones, que incluyen una muestra de conveniencia de tamaño moderado y la dependencia de medidas PROMs. Futuras investigaciones deberían incorporar medidas objetivas, además de los autorreportes y análisis acústico. Importancia: Esta investigación aporta nuevos conocimientos sobre factores personales, laborales y síntomas de voz en trabajadores de call centers. El modelado predictivo mejora la evaluación de riesgos y la comprensión de la susceptibilidad individual a trastornos de la voz. Conclusión: Los resultados muestran asociaciones entre diversos factores y los síntomas vocales reportados. Los factores de protección incluyen dormir más de seis horas y una hidratación constante; los factores de riesgo incluyen las condiciones de trabajo, como la ubicación y comportamientos como fumar. Los modelos de diagnóstico indican una buena precisión para algunas PROMs de síntomas de la voz, lo que subraya la necesidad de modelos integrales que tengan en cuenta los factores laborales, los comportamientos vocales y los parámetros acústicos para comprender la complejidad de los problemas de la voz.

Nomgram model for individual prediction of coronary heart disease with pulmonary hypertension / 公共卫生与预防医学

Objective To establish an individual Nomgram model for predicting the risk of coronary heart disease complicated with pulmonary hypertension. Methods From January 2017 to December 2021 , 352 patients with coronary heart disease (CHD) complicated with pulmonary hypertension in our hospital were selected, and 352 patients with coronary heart disease but without pulmonary hypertension were selected as the control group. The clinical baseline data of the two groups were analyzed first, and then logistics multivariate analysis was performed. To explore the risk factors of coronary heart disease complicated with pulmonary hypertension, the Nomgram model was established to predict the risk, and the predictive value of the model was tested by receiver characteristic curve (ROC). Results Logistics multivariate analysis showed that alcoholism, smoking, stroke history, hypertension course, CHD course, PASP, HCT, PaCO2, D-dimer, NIHSS score and low PaO2 were all independent risk factors for CHD complicated with pulmonary hypertension. Nomgram model prediction results for patients with coronary heart disease showed that Alcohol abuse, smoking, stroke history, duration of hypertension (5.66 years), duration of coronary heart disease (2.12 years), NIHSS (12.33 points), PASP (75.22mmHg), HCT (33.22%), PaCO2 (56.11mmHg), D-dimer (255.12μg/L), PaO2 (56.22mmHg) is a risk factor for coronary heart disease complicated with pulmonary hypertension. ROC curve showed that the area under the prediction curve of Nomgram model for coronary heart disease complicated with pulmonary hypertension was 0.675. Conclusion Nomgram model can predict pulmonary hypertension in patients with coronary heart disease to a certain extent.

UDC- COVID 19: herramienta digital para predecir el retiro de la ventilación mecánica invasiva de pacientes con COVID-19

En diciembre de 2019 las Autoridades de la República Popular China, comunicaron a la OMS varios casos de neumonía de etiología desconocida en Wuhan, una ciudad situada en la provincia china de Hubei. Una semana más tarde confirmaron que se trataba de un nuevo coronavirus que fue denominado SARS-CoV-2, este virus causa diversas manifestaciones clínicas englobadas bajo el término COVID-19. El presente trabajo presenta un prototipo de aplicación con el nombre UDC-COVID19 que propone una herramienta digital sobre la base de una revisión actualizada de la evaluación ultrasonográfica del diafragma como elemento predictivo para retirar la ventilación mecánica invasiva en pacientes con COVID-19, proporcionando una excelente herramienta digital para la evaluación de la estructura y función dinámica diafragmática, es precisa, reproducible, sin radiación ionizante, fácil de realizar a la cabecera del paciente y costo efectiva en pacientes críticamente enfermos.

In December 2019, the Authorities of the People's Republic of China reported to the WHO several cases of pneumonia of unknown etiology in Wuhan, a city located in the Chinese province of Hubei. A week later, they confirmed that it was a new coronavirus called SARS-CoV-2, which causes various clinical manifestations encompassed under the term COVID-19. The present work presents an application prototype with the name UDC-COVID19 that proposes a digital tool based on an updated review of the ultrasonographic evaluation of the diaphragm as a predictive element to withdraw invasive mechanical ventilation in patients with COVID-19, providing an excellent digital tool for the evaluation of the diaphragmatic structure and dynamic function since it is precise, reproducible, without ionizing radiation, easy to perform at the patient's bedside and cost effective in critically ill patients; mechanical ventilation.

Alergia a la leche de vaca: ¿se pueden evitar las pruebas de provocación oral? Un análisis probabilístico basado en datos clínicos / Cow's milk allergy: Can oral food challenges be avoided? A probabilistic analysis based on clinical data

Introducción. La prueba de provocación oral (PPO) para el diagnóstico de alergia a las proteínas de la leche de la vaca (APLV) presenta riesgos y requiere de recursos. Nuestro objetivo fue evaluar condiciones y pruebas complementarias para identificar una alta probabilidad de APLV. Población y métodos. Análisis secundario sobre estudio de pacientes atendidos en una unidad de alergia entre 2015 y 2018. Se determinaron las probabilidades prepruebas asociadas a los síntomas y sus combinaciones, y las probabilidades pospruebas luego de realizadas pruebas cutáneas y determinación de inmunoglobulina E (IgE) sérica. Resultados. Se evaluó la información de 239 pacientes. Se observaron probabilidades mayores al 95 % en pacientes con angioedema y combinación de urticaria y vómitos. Usando puntos de corte propuestos por Calvani et al., la combinación de vómitos con rinitis, sin angioedema, también superó el 95 %. Conclusión. Se ofrece una metodología para identificar pacientes en los que puede diagnosticarse APLV sin realización de PPO.

Introduction. The oral food challenge (OFC) for the diagnosis of cow's milk protein allergy (CMPA) poses risks and requires resources. Our objective was to assess conditions and complementary tests used to identify a high probability of CMPA. Population and methods. Secondary analysis of a study of patients seen at a unit of allergy between 2015 and 2018. Pre-testing probabilities associated with symptoms and their combinations and post-testing probabilities after skin prick testing and serum immunoglobulin E (IgE) levels were determined. Results. The data from 239 patients were assessed. A probability greater than 95% was observed for angioedema and a combination of urticaria and vomiting. Based on the cut-off points proposed by Calvani et al., the combination of vomiting with rhinitis, without angioedema, also exceeded 95%. Conclusion. A methodology is provided to identify patients in whom CMPA may be diagnosed without an OFC.

Instrumentos para la evaluación del riesgo de lesiones por presión en adultos en estado crítico: scoping review / Risk assessment instruments for pressure ulcer in adults in critical situation: a scoping review / Instrumentos para a avaliação do risco de lesões por pressão para adultos em situação crítica: scoping review*

Objetivo: mapear los instrumentos para la evaluación del riesgo de lesiones por presión en adultos en situación crítica en una unidad de terapia intensiva; identificar los indicadores de desempeño de los instrumentos y la apreciación de los usuarios con respecto al uso/limitaciones de los instrumentos. Método: scoping review. Para redactar el estudio se utilizó la extensión Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews. La investigación se realizó mediante la herramienta de búsqueda EBSCOhost en 8 bases de datos, resultando 1846 estudios, de los cuales 22 conforman la muestra. Resultados: se identificaron dos grandes grupos de instrumentos: los generalistas [Braden, Braden (ALB), Emina, Norton-MI, RAPS y Waterlow]; y los específicos (CALCULATE, Cubbin & Jackson, EVARUCI, RAPS-ICU, Song & Choi, Suriaidi y Sanada y el índice COMHON). En cuanto al valor predictivo, EVARUCI y CALCULATE mostraron los mejores resultados de indicadores de desempeño. En cuanto a las apreciaciones/limitaciones señaladas por los usuarios, destaca la escala CALCULATE, seguida de la EVARUCI y la RAPS-ICU, aunque aún necesitan ajustes futuros. Conclusión: el mapeo mostró que las evidencias son suficientes para indicar uno o más instrumentos para la evaluación del riesgo de lesiones por presión en adultos críticos en una unidad de cuidados intensivos.

Objective: to map the instruments for risk assessment of pressure ulcers in adults in critical situation in intensive care units; identify performance indicators of the instrument, and the appreciation of users regarding the instruments' use/limitations. Method: a scoping review. We used the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews in the writing of the study. We carried out the searches in the EBSCOhost search tool for 8 databases, resulting in 1846 studies, of which 22 studies compose the sample. Results: we identified two big instrument groups: generalist [Braden, Braden (ALB), Emina, Norton-MI, RAPS, and Waterlow]; and specific (CALCULATE, Cubbin & Jackson, EVARUCI, RAPS-ICU, Song & Choi, Suriaidi and Sanada, and COMHON index). Regarding the predictive value, EVARUCI and CALCULATE presented better results for performance indicators. Concerning appreciation/limitations indicated by users, we highlight the CALCULATE scale, followed by EVARUCI and RAPS-ICU, although they still need future adjustments. Conclusion: the mapping of the literature showed that the evidence is sufficient to indicate one or more instruments for the risk assessment of pressure ulcers for adults in critical situation in intensive care units.

Objetivo: mapear os instrumentos para avaliação do risco de lesões por pressão nos adultos em situação crítica em unidade de cuidados intensivos; identificar os indicadores de desempenho dos instrumentos e a apreciação dos utilizadores quanto ao uso/às limitações dos instrumentos. Método: scoping review. O Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews foi utilizado para a redação do estudo. A pesquisa foi realizada na ferramenta de busca EBSCOhost em oito bases de dados, resultando em 1846 estudos, dos quais 22 compõem a amostra. Resultados: identificaram-se dois grandes grupos de instrumentos: os genéricos [Braden, Braden (ALB), Emina, Norton-MI, RAPS e Waterlow]; e os específicos (CALCULATE, Cubbin & Jackson, EVARUCI, RAPS-ICU, Song & Choi, Suriaidi e Sanada e o índice de COMHON). Quanto ao valor preditivo, a EVARUCI e a CALCULATE apresentaram os melhores resultados de indicadores de desempenho. Em relação à apreciação/às limitações apontadas pelos utilizadores, destacam-se a escala CALCULATE, seguindo-se da EVARUCI e da RAPS-ICU, embora ainda necessitem de ajustes futuros. Conclusão: o mapeamento mostrou que as evidências são suficientes para indicar um ou mais instrumentos para avaliação do risco de lesões por pressão nos adultos em situação crítica em unidade de cuidados intensivos.

Are we ready to stratify BI-RADS 4 lesions observed on magnetic resonance imaging? A real-world noninferiority/equivalence analysis / Estamos prontos para estratificar lesões BI-RADS 4 na ressonância magnética? Uma análise de não inferioridade/equivalência do mundo real

Abstract Objective: To demonstrate that positive predictive values (PPVs) for suspicious (category 4) magnetic resonance imaging (MRI) findings that have been stratified are equivalent to those stipulated in the American College of Radiology Breast Imaging Reporting and Data System (BI-RADS) for mammography and ultrasound. Materials and Methods: This retrospective analysis of electronic medical records generated between January 4, 2016 and December 29, 2021 provided 365 patients in which 419 suspicious (BI-RADS category 4) findings were subcategorized as BI-RADS 4A, 4B or 4C. Malignant and nonmalignant outcomes were determined by pathologic analyses, follow-up, or both. For each subcategory, the level 2 PPV (PPV2) was calculated and tested for equivalence/noninferiority against the established benchmarks. Results: Of the 419 findings evaluated, 168 (40.1%) were categorized as malignant and 251 (59.9%) were categorized as nonmalignant. The PPV2 for subcategory 4A was 14.2% (95% CI: 9.3-20.4%), whereas it was 41.2% (95% CI: 32.8-49.9%) for subcategory 4B and 77.2% (95% CI: 68.4-84.5%) for subcategory 4C. Multivariate analysis showed a significantly different cancer yield for each subcategory (p < 0.001). Conclusion: We found that stratification of suspicious findings by MRI criteria is feasible, and malignancy probabilities for sub-categories 4B and 4C are equivalent to the values established for the other imaging methods in the BI-RADS. Nevertheless, low suspicion (4A) findings might show slightly higher malignancy rates.

Resumo Objetivo: Demonstrar que os valores preditivos positivos (VPPs) para lesões suspeitas (categoria 4) identificadas por ressonância magnética (RM) são equivalentes aos estipulados no ACR BI-RADS para mamografia e ultrassonografia. Materiais e Métodos: Análise retrospectiva de dados em prontuário eletrônico, entre 4 de janeiro de 2016 e 29 de dezembro de 2021, resultou em 365 pacientes elegíveis, com 419 lesões classificadas como BI-RADS 4A, 4B ou 4C. Desfechos malignos e não malignos foram determinados por estudo patológico e/ou acompanhamento. Realizamos o cálculo do VPP nível 2 (VPP2) para cada subcategoria e testamos para não inferioridade/equivalência em relação aos valores de referência. Resultados: Dos 419 achados, 168 (40,1%) foram malignos e 251 (59,9%), não malignos. O VPP2 para subcategoria 4A foi 14,2% (IC 95%: 9,3-20,4%), para 4B foi 41,2% (IC 95%:, 32,8-49,9%) e para 4C foi 77,2% (IC 95%: 68,4-84,5%). Análise multivariada demonstrou diferenças estatisticamente significantes entre as subcategorias (p < 0,001). Conclusão: A estratificação de achados suspeitos por RM é factível, sendo que a probabilidade de malignidade das subcategorias 4B e 4C é equivalente à estabelecida para outros métodos de imagem pelo BI-RADS. Contudo, lesões de baixa suspeição (4A) podem apresentar taxas mais altas de malignidade.

Factores pronósticos de metástasis ósea en pacientes con cáncer de próstata / Predictive factors for bone metastasis in patients with prostate cancer i: en

El adenocarcinoma de próstata es considerado una de las neoplasias más frecuentes en hombres mayores de 60 años, y su metástasis ósea constituye una de las complicaciones de peor pronóstico. Objetivo: Estimar los factores pronósticos de metástasis ósea en pacientes con cáncer de próstata. Métodos: Se realizó un estudio analítico de 73 pacientes con cáncer de próstata, asistidos en el Hospital Oncológico Conrado Benítez de Santiago de Cuba en el período 2018-2022. Entre las variables analizadas figuraron: edad, color de la piel, manifestaciones clínicas, tiempo de aparición de la metástasis ósea, grado de diferenciación celular, nivel de antígeno prostático específico y diagnóstico imagenológico. Resultados: En la serie predominó el grupo etario de 60-69 años (50,7 %) y el promedio de edad fue de 67 años; asimismo, prevalecieron los pacientes de piel negra, el dolor óseo como síntoma más frecuente y el diagnóstico imagenológico de metástasis ósea por tomografía axial computarizada (48,0 %). Se observó un aumento proporcional de los valores del antígeno prostático específico y de la puntuación de Gleason en relación con la aparición de metástasis. Conclusiones: Los factores pronósticos que permiten estimar la presencia de metástasis ósea en pacientes con cáncer de próstata son la edad avanzada, el color negro de la piel y los valores de antígeno prostático específico por encima de 20 ng/mL.

Prostate adenocarcinoma is considered one of the most frequent neoplasms in men over 60 years, and bone metastasis constitutes one of the complications with the worst prognosis. Objective: Estimate the predictive factors for bone metastasis in patients with prostate cancer. Methods: An analytic study of 73 patients with prostate cancer was carried out. They were assisted at Conrado Benítez Cancer Hospital in Santiago de Cuba during 2018-2022. The variables analyzed included: age, skin color, clinical manifestations, onset time of bone metastasis, degree of cellular differentiation, prostate-specific antigen level and imaging diagnosis. Results: In the series there was a prevalence of the 60-69 age group (50.7%) and the average age was 67 years; also, dark skinned patients, bone pain as more frequent symptom and imaging diagnosis of bone metastasis by computerized axial tomography prevailed (48.0%). A proportional increase of prostate-specific antigen values and Gleason punctuation was observed in relation to the metastasis onset. Conclusions: The predictive factors for estimating the presence of bone metastasis in patients with prostate cancer are the advanced age, black skin color and prostate-specific antigen values above 20 ng/mL.

Modelo predictivo de enfermedad cardiovascular basado en inteligencia artificial en la atención primaria de salud / A Predictive Model for Cardiovascular Disease based on Artificial Intelligence in Primary Health Care

Introducción: En Cuba y en el resto del mundo, las enfermedades cardiovasculares son reconocidas como un problema de salud pública mayúsculo y creciente, que provoca una alta mortalidad. Objetivo: Diseñar un modelo predictivo para estimar el riesgo de enfermedad cardiovascular basado en técnicas de inteligencia artificial. Métodos: La fuente de datos fue una cohorte prospectiva que incluyó 1633 pacientes, seguidos durante 10 años, fue utilizada la herramienta de minería de datos Weka, se emplearon técnicas de selección de atributos para obtener un subconjunto más reducido de variables significativas, para generar los modelos fueron aplicados: el algoritmo de reglas JRip y el meta algoritmo Attribute Selected Classifier, usando como clasificadores el J48 y el Multilayer Perceptron. Se compararon los modelos obtenidos y se aplicaron las métricas más usadas para clases desbalanceadas. Resultados: El atributo más significativo fue el antecedente de hipertensión arterial, seguido por el colesterol de lipoproteínas de alta densidad y de baja densidad, la proteína c reactiva de alta sensibilidad y la tensión arterial sistólica, de estos atributos se derivaron todas las reglas de predicción, los algoritmos fueron efectivos para generar el modelo, el mejor desempeño fue con el Multilayer Perceptron, con una tasa de verdaderos positivos del 95,2 por ciento un área bajo la curva ROC de 0,987 en la validación cruzada. Conclusiones: Fue diseñado un modelo predictivo mediante técnicas de inteligencia artificial, lo que constituye un valioso recurso orientado a la prevención de las enfermedades cardiovasculares en la atención primaria de salud(AU)

Introduction: In Cuba and in the rest of the world, cardiovascular diseases are recognized as a major and growing public health problem, which causes high mortality. Objective: To design a predictive model to estimate the risk of cardiovascular disease based on artificial intelligence techniques. Methods: The data source was a prospective cohort including 1633 patients, followed for 10 years. The data mining tool Weka was used and attribute selection techniques were employed to obtain a smaller subset of significant variables. To generate the models, the rule algorithm JRip and the meta-algorithm Attribute Selected Classifier were applied, using J48 and Multilayer Perceptron as classifiers. The obtained models were compared and the most used metrics for unbalanced classes were applied. Results: The most significant attribute was history of arterial hypertension, followed by high and low density lipoprotein cholesterol, high sensitivity c-reactive protein and systolic blood pressure; all the prediction rules were derived from these attributes. The algorithms were effective to generate the model. The best performance was obtained using the Multilayer Perceptron, with a true positive rate of 95.2percent and an area under the ROC curve of 0.987 in the cross validation. Conclusions: A predictive model was designed using artificial intelligence techniques; it is a valuable resource oriented to the prevention of cardiovascular diseases in primary health care(AU)

Prognostic predictive model for PONV in cesarean delivery

Introduction: Apfel simplified risk score for postoperative nausea and vomiting (PONV) has shown to be useful in anesthesia; however, since it has not been calibrated in regional anesthesia or in pregnant patients, its use in cesarean section is limited. Objective: To develop a prognostic predictive model for postoperative nausea and vomiting in pregnant patients undergoing cesarean section under spinal anesthesia. Methods: In a cohort of 703 term pregnant patients scheduled of cesarean section, 15 variables were prospectively assessed, to design a prognostic predictive model for the development of postoperative nausea and vomiting. A logistic regression analysis was used to construct the model and its calibration and discrimination were based on the Hosmer-Lemeshow test, the calibration curves, and C statistic. Additionally, the internal calibration was performed with the Bootstrap resampling method. Results: Postoperative nausea and vomiting were experienced by 27% of the patients during the first six hours after surgery. The model included as prognostic variables the development of intraoperative nausea and vomiting, age under 28 years, a history of PONV, the mother's BMI and the weight of the newborn baby. The model showed an adequate calibration (x2: 4.65 p: 0.5888), though a low discrimination (Statistic C = 0.68). Conclusions: A prognostic predictive model was created for the development of PONV in cesarean section. This model was used to build a prognostic scale for the classification of patients into risk groups.

Introducción: La escala de riesgo simplificada de Apfel para náuseas y vómito posoperatorio (NVPO) ha mostrado utilidad en anestesia; sin embargo, al no haber sido calibrada en anestesia regional o en pacientes embarazadas, su utilidad en cesárea es limitado. Objetivo: Desarrollar un modelo de predicción pronóstica para náuseas y vómito posoperatorios en pacientes embarazadas, llevadas a cesárea bajo anestesia espinal. Métodos: En una cohorte de 703 pacientes con embarazo a término programadas para cesárea, se evaluaron 15 variables de forma prospectiva para construir un modelo de predicción pronóstica para el desarrollo de náuseas y vómito posoperatorio. Se utilizó el análisis de regresión logística para la construcción del modelo y se calculó su calibración y discriminación con la prueba de Hosmer-Lemeshow, las curvas de calibración y el estadístico C. Además, se realizó la calibración interna con el método de remuestreo Bootstrap. Resultados: Las náuseas y vómito posoperatorio se presentaron en el 27% de las pacientes durante las primeras seis horas después de la cirugía. El modelo incluyó como variables pro-nósticas el desarrollo de náuseas y vómito en el intraoperatorio, edad menor de 28 años, antecedentes de NVPO, índice de masa corporal (IMC) de la madre y el peso del recién nacido. El modelo mostró una adecuada calibración (x2: 4,65 p: 0,5888), aunque una baja discriminación (Estadístico C = 0,68). Conclusiones: Se construyó un modelo de predicción pronóstica para el desarrollo de NVPO en cirugía cesárea, y con este se construyó una escala pronóstica que permite clasificar a las pacientes por grupos de riesgo.

Aprendizaje automático aplicado a la predicción de diabetes mellitus, utilizando información socioeconómica y ambiental de usuarios del sistema de salud

Objetivo: Se propuso aplicar modelos basados en técnicas de aprendizaje automático como apoyo para el diagnóstico temprano de la diabetes mellitus, utilizando variables de datos ambientales, sociales, económicos y sanitarios, sin la dependencia de la toma de muestras clínicas. Metodología: Se utilizaron datos de 10 889 usuarios afiliados al régimen subsidiado de salud de la zona suroccidental en Colombia, diagnosticados con hipertensión y agrupados en usuarios sin (74,3 %) y con (25,7 %) diabetes mellitus. Se entrenaron modelos supervisados utilizando k vecinos más cercanos, árboles de decisión y bosques aleatorios, así como modelos basados en ensambles, aplicados a la base de datos antes y después de balancear el número de casos en cada grupo de diagnóstico. Se evalúo el rendimiento de los algoritmos mediante la división de la base de datos en datos de entreno y de prueba (70/30, respectivamente), y se utilizaron métricas de exactitud, sensibilidad, especificidad y área bajo la curva. Resultados: Los valores de sensibilidad aumentaron considerablemente al utilizar datos balanceados, pasando de valores máximos del 17,1 % (datos sin balancear) a valores de hasta 57,4 % (datos balanceados). El valor más alto de área bajo la curva (0,61) fue obtenido con los modelos de ensambles, al aplicar un balance en el número de datos por cada grupo y al codificar las variables categóricas. Las variables de mayor peso estuvieron asociadas con aspectos hereditarios (24,65 %) y con el grupo étnico (5.59 %), además de la dificultad visual, el bajo consumo de agua, una dieta baja en frutas y verduras, y el consumo de sal y azúcar. Conclusiones: Aunque los modelos predictivos, utilizando información socioeconómica y ambiental de las personas, surgen como una herramienta para el diagnóstico temprano de la diabetes mellitus, estos aún deben ser mejorados en su capacidad predictiva.

Objective: The objective was to apply models based on machine learning techniques to support the early diagnosis of diabetes mellitus, using environmental, social, economic and health data variables, without dependence on clinical sample collection. Methodology: Data from 10,889 users affiliated with the subsidized health system in the southwestern area of Colombia, diagnosed with hypertension and grouped into users without (74.3%) and with (25.7%) diabetes mellitus, were used. Supervised models were trained using k-nearest neighbors, decision trees, and random forests, as well as ensemble-based models, applied to the database before and after balancing the number of cases in each diagnostic group. The performance of the algorithms was evaluated by dividing the database into training and test data (70/30, respectively), and metrics of accuracy, sensitivity, specificity, and area under the curve were used. Results: Sensitivity values increased significantly when using balanced data, going from maximum values of 17.1% (unbalanced data) to values as high as 57.4% (balanced data). The highest value of area under the curve (0.61) was obtained with the ensemble models, by applying a balance in the amount of data for each group and by coding the categorical variables. The variables with the greatest weight were associated with hereditary aspects (24.65%) and with the ethnic group (5.59%), in addition to visual difficulty, low water consumption, a diet low in fruits and vegetables, and the consumption of salt and sugar. Conclusions: Although predictive models, using people's socioeconomic and environmental information, emerge as a tool for the early diagnosis of diabetes mellitus, their predictive capacity still needs to be improved.

Objetivo: Propôs-se aplicar modelos baseados em técnicas de aprendizagem automática como apoio para o diagnóstico precoce da diabetes mellitus, utilizando variáveis de dados ambientais, sociais, econômicos e sanitários, sem a dependência da coleta de amostras clínicas. Metodologia: Usaram-se dados de 10.889 usuários filiados ao regime subsidiado de saúde da zona sudoeste da Colômbia, diagnosticados com hipertensão e agrupados em usuários sem (74,3%) e com (25,7%) diabetes mellitus. Foram treinados modelos supervisionados utilizando k vizinhos mais próximos, árvores de decisão e florestas aleatórias, assim como modelos baseados em montagens, aplicados à base de dados antes de depois de equilibrar o número de casos em cada grupo de diagnóstico. Avaliou-se o desempenho dos algoritmos por meio da divisão da base de dados de treino e teste (70/30, respectivamente), e utilizaram-se métricas de exatidão, sensibilidade, especificidade e área sob a curva. Resultados: Os valores de sensibilidade aumentaram de maneira significativa ao utilizar dados equilibrados, passando de valores máximos de 17,1% (dados sem equilibrar) a valores de até 57,4% (dados equilibrados). O valor mais elevado de área sob a curva (0,61) foi obtido com os modelos de montagens, ao aplicar um balanço no número de dados por cada grupo e codificar as variáveis categóricas. As variáveis de maior peso estiveram associadas com fatores hereditários (24,65%) e com o grupo étnico (5,59%), além da dificuldade visual, o baixo consumo de água, um regime baixo em frutas e vegetais e o consumo de sal e açúcar. Conclusões: Embora os modelos preditivos, utilizando informação socioeconômica e ambiental das pessoas, surgem como uma ferramenta para o diagnóstico precoce da diabetes mellitus, ainda devem ser melhorados em sua capacidade preditiva.

Generación de un test predictivo para el diagnóstico de laetiología de la hemorragia digestiva alta variceal

Nuestro objetivo fue desarrollar un test diagnóstico para predecir la etiología de la Hemorragia Digestiva Alta Variceal (HDAV). Realizamos un estudio de cohorte retrospectivo. Se revisaron historias clínicas de pacientes mayores de 18 años con Hemorragia Digestiva Alta (HDA) que acudieron al servicio de emergencia del Hospital Cayetano Heredia (HCH) de Lima-Perú entre el 2019 a 2022, se recolectaron datos demográficos, de laboratorio y clínicos; posteriormente, se identificaron variables predictivas de HDAV mediante una regresión logística múltiple. A cada variable con capacidad predictiva se les asignó un puntaje con un punto de corte y sirvió para construir una escala predictiva de HDAV. Se incluyeron 197 historias clínicas de pacientes con HDA, de los cuales 127 (64%) tuvieron sangrado de causa no variceal, y, 70 (36%), variceal. Se identificaron 4 factores predictivos independientes: hematemesis (vómito rojo) (OR: 4,192, IC 95%: 1,586-11,082), recuento de plaquetas (OR: 3,786, IC 95%: 1,324-10,826), antecedente de HDA (OR: 2,634, IC 95%: 1,017-6,820), signos de enfermedad hepática crónica (OR: 11,244, IC 95%: 3,067-35,047), con los que se construyó una escala predictiva, con un punto de corte >7 y ≤7; que mostró una sensibilidad, especificidad, valor predictivo positivo, valor predictivo negativo, cociente de probabilidad positivo, y, negativo de 58,6%, 90,6%, 77,4%, 79,9%, 6,20, y 0,46 respectivamente. En conclusión, la escala predictiva con un punto de corte >7 es útil para predecir la presencia de la HDAV en pacientes que acuden a la emergencia por HDA.

Our objective was to develop a diagnostic test to predict the etiology of Variceal Upper Gastrointestinal Bleeding (VUGIB). We conducted a retrospective cohort study. Medical records of patients over 18 years of age with Upper Gastrointestinal Bleeding (UGIB) who attended the emergency service of Hospital Cayetano Heredia (HCH) in Lima-Peru between 2019 and 2022 were reviewed; demographic, laboratory and clinical data were collected. Subsequently, predictive variables of variceal upper gastrointestinal bleeding (VUGIB) were identified using multiple logistic regression. Each variable with predictive capacity was assigned a score with a cut-off point and served to build a predictive scale for VUGIB. 197 medical records of patients with UGIB were included, of which 127 (64%) had non-variceal bleeding, and 70 (36%), variceal. Four independent predictors were identified: hematemesis (red vomit) (OR: 4,192, 95% CI: 1.586-11.082), platelet count (OR: 3.786, 95% CI: 1.324-10.826), history of UGIB (OR: 2.634, 95% CI: 1.017-6.820), signs of chronic liver disease (OR: 11.244, 95% CI: 3.067-35.047), with which a predictive scale was constructed, with a cut-off point >7 and ≤7; which showed a sensitivity, specificity, positive predictive value, negative predictive value, positive likelihood ratio, and negative of 58.6%, 90.6%, 77.4%, 79.9%, 6.20, and 0.46 respectively. In conclusion, the predictive scale with a cut-off point >7 is useful for predicting the presence of VUGIB in patients who attend the emergency room for UGIB.

Predictive factors and risk analysis of recurrent laryngeal nerve invasion in papillary thyroid carcinoma ≤ 1 cm

ABSTRACT Objective: The recurrent laryngeal nerve (RLN) may be involved by papillary thyroid carcinoma ≤ 1 centimeter (PTC ≤ 1 cm). Current study investigated the predictive factors of RLN invasion in PTC ≤ 1 cm, the risk factors of disease recurrence in RLN invaded cases and the results of surgical management for RLN invasion. Materials and methods: Data of 374 PTC ≤ 1 cm patients were retrospectively collected. We performed univariate and multivariate analysis to identify predictive factors of RLN invasion and risk factors of disease recurrence. The abilities of factors in predicting RLN invasion were evaluated. Surgical outcomes and recurrence free survival (RFS) of patients were analyzed. Results: A total of 28 patients suffered RLN invasion, among which seven had disease recurrence. Preoperative vocal cord palsy (VCP), gross extrathyroidal extension, larger tumor size and tumor on the dorsal side of thyroid were verified as predictive factors of RLN invasion. RLN involved patients had poorer RFS, but better than those who also had upper-aerodigestive tract invasion. Upper-aerodigestive tract invasion, lateral neck lymph nodes metastasis (LNM) and BRAF V600E mutation were independent risk factors of disease recurrence in RLN invaded cases. Tumor shaving showed better RLN function preservation without increasing recurrent risk. Conclusions: Current study confirmed the rarity of RLN invasion in PTC ≤ 1 cm. Various aggressive features were verified as predictive factors of RLN invasion. Tumor shaving showed superiority in preserving nerve function without increasing recurrent risk. Special attentions should be paid for disease recurrence when RLN invasion accompanied by upper-aerodigestive tract invasion, lateral neck LNM or BRAF V600E mutation.

A Master Mind Game Code Algorithm Approach to Help Surgical Decision-Making between Retropharyngeal Fat Grafting and Pharyngoplasty for the Treatment of Velopharyngeal Incompetence

Abstract Introduction Velopharyngeal insufficiency (VPI) is a controversial pathology with many surgical options. Objectives To compare pharyngoplasty and retropharyngeal fat grafting and to build a prognostic tool to achieve perfect speech. Methods Retrospective observational cohort study of 114 patients operated for VPI from 1982 to 2019 in a single tertiary center. The instrumental assessment was made using an aerophonoscope and nasofibroscopy. The variables sex, age, genetic syndromes, and type of diagnosis were analyzed with logistic regression model adjusted with propensity score. To generalize results and to build a surgical predictive tool, a marginal analysis concludes the study. Results Among the patients (median [range] age 7 [4-48]), 63 (55.26%) underwent pharyngoplasty and 51 (44.74%) graft. The graft group had no complication, but it had a failure rate of 7.84%. The pharyngoplasty group had no failure, but one patient had postoperative obstructive sleep apnea. The marginal analysis demonstrated that age lower than 7 years, cleft lip and palate, absence of syndrome, and intermittent VPI were important predictive factors of good result regardless of surgical technique. Conclusions Without a statistical demonstration of the superiority of pharyngoplasty over graft, and in the uncertainty of literature background, our perfect-speech patient profile represents an important tool for a postoperative forecast of results in which, like in the Master Mind game, every feature has to be considered not individually but as a pattern of characteristics whose association contributes to the outcome.

Factores predictivos de rotura de aneurismas intracraneales

Introducción: Un aneurisma intracraneal roto provoca una hemorragia subaracnoidea. La enfermedad presenta una alta mortalidad y morbilidad. Sin embargo, no todos se rompen. Mejorar la predicción de rotura permitirá un tratamiento quirúrgico preventivo en un grupo de pacientes y evitará una intervención quirúrgica con riesgos en otro grupo de enfermos. Es necesario identificar factores predictivos para mejorar la estratificación del riesgo de rotura y optimizar el tratamiento de los aneurismas intracraneales incidentales. Objetivo: Identificar factores predictivos de rotura de aneurismas intracraneales. Métodos: En una muestra de 152 pacientes espirituanos con aneurismas intracraneales saculares rotos (n = 138) y no rotos (n = 22) y 160 imágenes de angiografía por tomografía computarizada, se realizaron mensuraciones de los índices o factores morfológicos, los cuales se combinaron mediante análisis de regresión logística con variables demográficas y clínicas. Resultados: El grupo de edad con mayor frecuencia de presentación de aneurismas fue el de mayor de 65 años. La muestra estuvo representada, en su gran mayoría, por el sexo femenino. Se identificaron tres factores clínicos y cuatro factores morfológicos estadísticamente significativos, asociados con la rotura. El índice de no esfericidad (p = 0,002 y el sexo femenino (p = 0,02) fueron los de mayor significación estadística. Conclusiones: Se detectaron siete factores predictivos de rotura de aneurismas intracraneales estadísticamente significativos, de los cuales el índice de no esfericidad resultó el de mayor significación.

Introduction: A ruptured intracranial aneurysm causes a subarachnoid hemorrhage. The disease has high mortality and morbidity. However, not all of them break. Improving the rupture prediction will allow preventive surgical treatment in a group of patients and it will avoid risky surgical intervention in another group of patients. It is necessary to identify predictive factors to improve rupture risk stratification and to optimize treatment of incidental intracranial aneurysms. Objective: To identify rupture predictive factors for intracranial aneurysms. Methods: Measurements of the morphological indices or factors were performed in a sample of 152 patients from Sancti Spiritus with ruptured (n = 138) and unruptured (n = 22) saccular intracranial aneurysms and 160 computed tomography angiography images. They were combined using logistic regression analysis with demographic and clinical variables. Results: The age group with the highest frequency of aneurysm presentation was older than 65. The sample was represented, in its vast majority, by the female sex. Three clinical factors and four statistically significant morphological factors associated with rupture were identified. The non-sphericity index (p = 0.002) and the female sex (p = 0.02) were the most statistically significant. Conclusions: Seven statistically significant predictors of intracranial aneurysm rupture were detected, the non-sphericity index being the most significant.

Detección de novedad y codificación predictiva en el sistema auditivo: Impacto clínico en disfunciones auditivas y vestibulares. Revisión de la literatura / Deviance detection and predictive coding in the auditory system: Clinical impact in auditory and vestibular dysfunctions

Una propiedad fundamental de los sistemas sensoriales es su capacidad para detectar estímulos novedosos en el entorno. El sistema nervioso posee neuronas que disminuyen su respuesta a los estímulos sonoros que se repiten a lo largo del tiempo y otras neuronas que aumentan su frecuencia de disparo ante estímulos novedosos, siendo la diferencia entre ambas respuestas conocida como adaptación-específica a estímulos. En las últimas décadas, se ha propuesto que el cerebro establece, continuamente, predicciones de los estímulos novedosos y del entorno basándose en sus experiencias previas y en modelos de representación internos, teoría denominada codificación predictiva. En esta revisión, abordaremos algunos conceptos de la adaptación-específica a estímulos y codificación predictiva, centrándonos principalmente en el sistema auditivo. Por último, propondremos una explicación teórica basada en el marco de la codificación predictiva para algunas disfunciones neuropsiquiátricas, auditivas y vestibulares.

A fundamental property of sensory systems is their ability to detect novel stimuli in the environment. The nervous system possesses neurons that decrease their response to sound stimuli that are repeated over time and other neurons that increase their firing rate to novel stimuli, the difference between the two responses being known as stimulus-specific adaptation. In recent decades, it has been proposed that the brain continuously makes predictions of novel stimuli and the environment based on its previous experiences and internal representational models, a theory called predictive coding. In this review, we will address some concepts of stimulus-specific adaptation and predictive coding, focusing mainly on the auditory system. Finally, we will propose a theoretical explanation based on the predictive coding framework for some neuropsychiatric, auditory, and vestibular dysfunctions.

Predictive validity and cut-off point of the Turkish version of the Infant Colic Scale in the diagnosis of colic

Abstract Objective: To investigate the predictive validity and cut-off point of the Turkish version of the Infant Colic Scale (ICS) in the diagnosis of colic. Methods: This methodological study was carried out in a pediatric outpatient clinic of a university hospital in Turkey with infants aged 6-16 weeks (n = 133). The data were collected using the Mother-Infant Description Form, the ICS, and the Rome IV criteria form. The scale is a 6-point Likert-type scale consisting of 19 items in total. A low total mean score obtained from it indicates that the probability of colic increases, while a high mean score indicates that the probability of colic decreases. The Rome IV criteria were used as the gold standard. Results: The mean score obtained from the ICS was 59.4 ± 13.7. According to the Rome IV criteria, 26.3% of the infants had colic. The area under the ROC curve was 87.4% (95% CI = 0.815-0.934, SE = 0.30, p = 0.001), and the cut-off point for the best sensitivity value (88.6%) and the best specificity value (70.5%) of the ICS was determined to be 60.5. According to the cut-off point, the positive predictive value was 51%, and the negative predictive value was 94%. Conclusion: The predictive validity of the Turkish version of the ICS was found to be at a good level with high sensitivity and acceptable specificity for a cut-off point of 60.5. Healthcare professionals working in the child field can use the ICS to exclude colic in infants.

A prospective validation and comparison of three multivariate models for prediction of difficult intubation in adult patients

Abstract Purpose Several bedside clinical tests have been proposed to predict difficult tracheal intubation. Unfortunately, when used alone, these tests show less than ideal prediction performance. Some multivariate tests have been proposed considering that the combination of some criteria could lead to better prediction performance. The goal of our research was to compare three previously described multivariate models in a group of adult patients undergoing general anesthesia. Methods This study included 220 patients scheduled for elective surgery under general anesthesia. A standardized airway evaluation which included modified Mallampati class (MM), thyromental distance (TMD), mouth opening distance (MOD), head and neck movement (HNM), and jaw protrusion capacity was performed before anesthesia. Multivariate models described by El-Ganzouri et al., Naguib et al., and Langeron et al. were calculated using the airway data. After anesthesia induction, an anesthesiologist performed the laryngoscopic classification and tracheal intubation. The sensitivity, specificity, and receiver operating characteristic (ROC) curves of the models were calculated. Results The overall incidence of difficult laryngoscopic view (DLV) was 12.7%. The area under curve (AUC) for the Langeron, Naguib, and El-Ganzouri models were 0.834, 0.805, and 0.752, respectively, (Langeron > El-Ganzouri, p= 0.004; Langeron = Naguib, p= 0.278; Naguib = El-Ganzouri, p= 0.101). The sensitivities were 85.7%, 67.9%, and 35.7% for the Langeron, Naguib, and El-Ganzouri models, respectively. Conclusion The Langeron model had higher overall prediction performance than that of the El-Ganzouri model. Additionally, the Langeron score had higher sensitivity than the Naguib and El-Ganzouri scores, and therefore yielded a lower incidence of false negatives.

Estimación del riesgo cardiovascular global en hipertensos de la Universidad de Ciencias Médicas de Cienfuegos

Fundamento: a pesar de la importancia del cálculo del riesgo cardiovascular global en hipertensos y los beneficios de su implementación en la Atención Primaria de Salud, en la Universidad de Ciencias Médicas de Cienfuegos son insuficientes los estudios sobre su estimación. Objetivo: determinar el riesgo cardiovascular global en hipertensos de la Universidad de Ciencias Médicas de Cienfuegos en el año 2021. Métodos: se realizó un estudio descriptivo, transversal y correlacional. La muestra estuvo conformada por 105 hipertensos entre 40-80 años de la Universidad de Ciencias Médicas de Cienfuegos en el 2021. Las variables estudiadas fueron: edad, género, colesterol total, tabaquismo, presión arterial sistólica, diabetes mellitus diagnosticada y el riesgo cardiovascular global. Se calcularon la frecuencia absoluta y relativa de las variables y se aplicó la Chi cuadrado de Pearson en la asociación de las variables y el riesgo cardiovascular bajo con un nivel de significación p=0,05. Los resultados se presentaron en tablas. Resultados: predominó el género femenino, el grupo etáreo de 50-69 años, los no diabéticos y los no fumadores, con colesterol normal y prehipertensos. El 93,3 % presentó riesgo cardiovascular global bajo y el 6,7 % de moderado a crítico. Los pacientes no diabéticos y con presión arterial sistólica normal presentaron asociación significativa con el riesgo cardiovascular bajo. Conclusiones: los hipertensos de la Universidad de Ciencias Médicas de Cienfuegos presentan un riesgo cardiovascular global bajo, se mostró una correlación entre el riesgo cardiovascular bajo y la presión arterial sistólica normal y los antecedentes de no diabetes, lo que condicionaría protección a eventos cardiovasculares y cerebrovasculares en el futuro.

Background: despite the importance of calculating global cardiovascular risk in hypertensive patients and the benefits of its implementation in Primary Health Care, studies on its estimation are insufficient at the University of Medical Sciences of Cienfuegos. Objective: to determine the global cardiovascular risk in hypertensive patients at the University of Medical Sciences of Cienfuegos in the year 2021. Methods: a descriptive, cross-sectional and correlational study was carried out. The sample consisted of 105 hypertensive patients between 40-80 years of age from the University of Medical Sciences of Cienfuegos in 2021. The variables studied were: age, gender, total cholesterol, smoking, systolic blood pressure, diagnosed diabetes mellitus, and global cardiovascular risk. The absolute and relative frequency of the variables were calculated and Pearson's Chi square was applied in the association of the variables and low cardiovascular risk with a significance level of p=0.05. The results were presented in tables. Results: the female gender, the age group of 50-69 years, non-diabetics and non-smokers, with normal cholesterol and prehypertensive predominated. 93.3 % presented low overall cardiovascular risk and 6.7 % moderate to critical. Non-diabetic patients with normal systolic blood pressure presented a significant association with low cardiovascular risk. Conclusions: hypertensive patients at the University of Medical Sciences of Cienfuegos have a low overall cardiovascular risk, a correlation was shown between low cardiovascular risk and normal systolic blood pressure and a history of non-diabetes, which would determine protection against cardiovascular and cerebrovascular events in the future

Applicability of the acute leukemia (AL) - EBMT score as a prognostic model for allogeneic hematopoietic stem cell transplantation: a single-center, prospective, cohort study at a reference transplant center in Brazil

Abstract Introduction The Acute Leukemia-European Society for Blood and Marrow Transplantation (AL-EBMT) risk score was recently developed and validated by Shouval et al. Objective To assess the ability of this score in predicting the 2-year overall survival (OS-2), leukemia-free survival (LFS-2) and transplant-related mortality (TRM) in acute leukemia (AL) adult patients undergoing a first allogeneic hematopoietic stem cell transplant (HSCT) at a transplant center in Brazil. Methods In this prospective, cohort study, we used the formula published by Shouval et al. to calculate the AL-EBMT score and stratify patients into three risk categories. Results A total of 79 patients transplanted between 2008 and 2018 were analyzed. The median age was 38 years. Acute myeloid leukemia was the most common diagnosis (68%). Almost a quarter of the cases were at an advanced stage. All hematopoietic stem cell transplantations (HSCTs) were human leukocyte antigen-matched (HLA-matched) and the majority used familial donors (77%). Myeloablative conditioning was used in 92% of the cases. Stratification according to the AL-EBMT score into low-, intermediate- and high-risk groups yielded the following results: 40%, 12% and 47% of the cases, respectively. The high scoring group was associated with a hazard ratio of 2.1 (p= 0.007), 2.1 (p= 0.009) and 2.47 (p= 0.01) for the 2-year OS, LFS and TRM, respectively. Conclusion This study supports the ability of the AL-EBMT score to reasonably predict the 2-year post-transplant OS, LFS and TRM and to discriminate between risk categories in adult patients with AL, thus confirming its usefulness in clinical decision-making in this setting. Larger, multicenter studies may further help confirm these findings.

Early Results of Type I Tympanoplasty in Underprivileged Nepalese Children and Factors Influencing the Surgical Outcomes

Abstract Introduction Type I Tympanoplasty is a common ear surgery performed in Nepalese children, but no studies have been published about the success rate of the procedure and the factors affecting surgical outcomes. Objectives To find out the surgical outcome of type I tympanoplasty and to evaluate the factors affecting the success of the surgery in Nepalese children. Methods This is a retrospective study conducted by analyzing the medical records of a five-year period. Children aged 8-16 years who underwent type I tympanoplasty were included in the study. Surgical pro-forma and records of pre and post-operative pure tone audiometry were documented. Outcome of the surgery was considered a success in terms of graft uptake and hearing improvement six months after surgery. Results Out of 629 children who underwent type I tympanoplasty, anatomical success was observed in 93.32% (n = 587) and functional success in 76% (n = 478). Factors such as age, site and size of the perforation, status of the middle ear and contralateral ear, surgical approach, and the graft used were not the predictors of the surgical outcome. Conclusions The surgical outcome of type I tympanoplasty in Nepalese children was good. Although surgical outcome was better with older children, post-aural approach, temporalis fascia, inferiorly positioned perforations, and in children with dry middle ear mucosa, none of the parameters considered in this study were found to be a significant predictive factor of the surgical outcome.