ABSTRACT
Uno de los principales problemas durante la dentición mixta es la determinación de la futura discrepancia entre tamaño dentario y el espacio disponible. Para predecir el ancho mesiodistal de los dientes permanentes no erupcionados se han introducido diferentes métodos de análisis. Objetivo: El propósito de este estudio fue comparar el método Tanaka-Johnston con una nueva ecuación de regresión para predecir el ancho mesiodistal de caninos y premolares permanentes no erupcionados en una población de la región de Valparaíso, Chile. Material y método: Este estudio fue realizado en la Facultad de Odontología de la Universidad de Valparaíso, desde octubre de 2022 a junio de 2023 (8 meses), la muestra estuvo compuesta por 202 modelos de estudio del departamento de ortodoncia (91 hombres y 111 mujeres) en el rango de edad de 11 -20 años. Resultados: Se demostró que el método elaborado por Lara-Sandoval presenta mayor fiabilidad respecto a las medidas mesiodistales reales de los pacientes (ICC 0,773 para maxilar y 0,762 para mandíbula), en comparación con el método de Tanaka-Johnston (ICC 0,665 para maxilar y 0,623 para mandíbula). No existen diferencias significativas entre los valores reales y el método de Lara-Sandoval. Conclusión: El método de Lara-Sandoval es mejor que el propuesto por Tanaka-Johnston para determinar el ancho mesiodistal de caninos y premolares para esta muestra. Es necesario validar este método en otras regiones del país para ser utilizado con mayor seguridad que el ya existente como método estándar nacional.
One of the main orthodontic problems in mixed dentition is the determination of future tooth and size arch discrepancy. In order to predict the mesiodistal widths of unerupted permanent teeth different methods of analyses have been introduced. The aim of this study is to compare the Tanaka-Johnston analysis with a new regressive equation to predict the mesiodistal width of unerupted permanent canines and premolars in a Chilean population sample, from Valparaíso region. This study was conducted at the Universidad de Valparaíso Dental Faculty, from october 2022 to june 2023 (8 months), and the sample comprised historical dental casts from 202 patients (91 boys and 111 girls) in the age range of 11-20 from the orthodontics department. All the patients are from the Valparaíso region, Chile. The results show that the predictions of the new regressive equation method are closer to the actual mesiodistal measurements of the patients (ICC 0,773 for maxilla and 0,762 for mandible), compared to the Tanaka- Johnston method (ICC 0,665 for maxilla and 0,623 for mandible). There are no significant differences between the real values and the Lara-Sandoval method. Lara-Sandoval method is better than the one proposed by Tanaka-Johnston to determine the mesiodistal width of canines and premolars in this sample population. It is necessary to validate this method in other regions of the country to be used with greater security than the ones that already exists as a national standard method.
ABSTRACT
Introducción. La diabetes es una enfermedad crónica que se caracteriza por el aumento de la concentración de la glucosa en sangre. Puede generar complicaciones que afectan la calidad de vida y aumentan los costos de la atención en salud. En los últimos años, las tasas de prevalencia y mortalidad han aumentado en todo el mundo. El desarrollo de modelos con gran desempeño predictivo puede ayudar en la identificación temprana de la enfermedad. Objetivo. Desarrollar un modelo basado en la inteligencia artificial para apoyar la toma de decisiones clínicas en la detección temprana de la diabetes. Materiales y métodos. Se llevó a cabo un estudio de corte transversal, utilizando un conjunto de datos que incluía edad, signos y síntomas de pacientes con diabetes y de individuos sanos. Se utilizaron técnicas de preprocesamiento para los datos. Posteriormente, se construyó el modelo basado en mapas cognitivos difusos. El rendimiento se evaluó mediante tres parámetros: exactitud, especificidad y sensibilidad. Resultados. El modelo desarrollado obtuvo un excelente desempeño predictivo, con una exactitud del 95 %. Además, permitió identificar el comportamiento de las variables involucradas usando iteraciones simuladas, lo que proporcionó información valiosa sobre la dinámica de los factores de riesgo asociados con la diabetes. Conclusiones. Los mapas cognitivos difusos demostraron ser de gran valor para la identificación temprana de la enfermedad y en la toma de decisiones clínicas. Los resultados sugieren el potencial de estos enfoques en aplicaciones clínicas relacionadas con la diabetes y respaldan su utilidad en la práctica médica para mejorar los resultados de los pacientes.
Introduction. Diabetes is a chronic disease characterized by a high blood glucose level. It can lead to complications that affect the quality of life and increase the costs of healthcare. In recent years, prevalence and mortality rates have increased worldwide. The development of models with high predictive performance can help in the early identification of the disease. Objective. To develope a model based on artificial intelligence to support clinical decision-making in the early detection of diabetes. Materials and methods. We conducted a cross-sectional study, using a dataset that contained age, signs, and symptoms of patients with diabetes and of healthy individuals. Pre-processing techniques were applied to the data. Subsequently, we built the model based on fuzzy cognitive maps. Performance was evaluated with three metrics: accuracy, specificity, and sensitivity. Results. The developed model obtained an excellent predictive performance with an accuracy of 95%. In addition, it allowed to identify the behavior of the variables involved using simulated iterations, which provided valuable information about the dynamics of the risk factors associated with diabetes. Conclusions. Fuzzy cognitive maps demonstrated a high value for the early identification of the disease and in clinical decision-making. The results suggest the potential of these approaches in clinical applications related to diabetes and support their usefulness in medical practice to improve patient outcomes.
ABSTRACT
Innovative computer techniques are now being utilized not only in academic research but also in commercial dental practice, revolutionizing various areas of dentistry. This digitalization trend is driven by the increasing demands for treatment and diagnosis in the eld. Accurate diagnosis is crucial in dentistry, whether it be in orthodontics, maxillofacial surgery, periodontics, or prosthetics, as it forms the basis for creating effective treatment plans and restoring patients' oral health. While a specialist's expertise plays a vital role in diagnosis and treatment planning, it is susceptible to the inherent risks of human error, given the multifactorial nature of dental conditions. Consequently, there is growing interest in leveraging multi-parametric pattern recognition methods, including statistics, machine learning, and articial intelligence (AI), to enhance clinical decision-making. The introduction of clinical decision support systems (CDSS) and genetic algorithms (GAs) in dental research and clinical practice holds great promise for both healthcare professionals and patients. Extensive work has been undertaken to develop CDSS in dentistry, and this article reviews the latest advancements in this eld.
ABSTRACT
Background: Various clinical applications have been attempted using artificial intelligence (AI) clinical decision support system (CDSS), and it has become a starting point for personalized cancer treatment. We aimed to identify the degree of agreement between the AI?CDSS, Watson for Oncology (WFO), and the clinician in treatment recommendations for Korean breast cancer patients and to provide guidelines for future improvement. Methods: One hundred and eighty?three breast cancer patients who underwent treatment at the Pusan National University Hospital between January 1, 2016 and May 31, 2017 were enrolled in this study. The concordance between WFO抯 and clinicians� treatment recommendations were examined according to various factors. Results: WFO gave the same treatment option recommendations as clinicians in 74 (40.4%) of the cases. According to the logistic regression, the difference in recommendation concordance between stage I and stage III was statistically significant (P = 0.004), and there was no difference among other factors. Conclusion: The concordance of treatment recommendations was low overall. However, this is largely attributable to the differences of medical insurance system and healthcare environment between the United States and Korea. In the future, region?specific features should be considered or reflected during the development of AI?CDSS.
ABSTRACT
In recent years, the artificial intelligence machine learning and deep learning technology have made leap progress. Using clinical decision support system for auxiliary diagnosis and treatment is the inevitable developing trend of wisdom medical. Clinicians tend to ignore the interpretability of models while pursuing its high accuracy, which leads to the lack of trust of users and hamper the application of clinical decision support system. From the perspective of explainable artificial intelligence, the authors make some preliminary exploration on the construction of clinical decision support system in the field of liver disease. While pursuing high accuracy of the model, the data governance techniques, intrinsic interpretability models, post-hoc visualization of complex models, design of human-computer interactions, providing knowledge map based on clinical guidelines and data sources are used to endow the system with interpretability.
ABSTRACT
Objective:To develop an implementation protocol of clinical decision-support system about pediatric parenteral nutrition administration based on Guideline Implementation with Decision Support Checklist.Methods:From November to December 2021, using 4 dimensions and 16 items of Guideline Implementation with Decision Support Checklist, an multidisciplinary expert consultation was conducted, based on the previous clinical decision-support system and implementation protocol draft, to identify qualitative suggestions and quantitative assessment, and form the final protocol.Results:According to the Guideline Implementation with Decision Support Checklist, experts evaluated the implementation protocol draft, ranked the scores of 4 dimensions, system, content, context, and implementation, successively. Based on 12 updated suggestions, the final protocol included 4 dimensions and 12 interventions, including CDS updates, preparation before launching, experimental application and promotion, and systematic monitoring.Conclusions:The development of Guideline Implementation with Decision Support Checklist-based implementation protocol of clinical decision-support system about pediatric parenteral nutrition administration facilitated the thorough and structured consideration and agreement of multidisciplinary team, thus to optimize protocol and provide foundation for clinical practice.
ABSTRACT
The clinical decision support system can provide medical staff with targeted patient diagnosis, treatment and care plan according to the recommendations of the guidelines, and assist medical staff to make clinical decisions. However, the adherence to clinical decision support system which based on guidelines was poor in clinical practice. Therefore, this article reviewed the influence factors of adherence to clinical decision support system which based on guideline from four aspects: system factors, individual factors, organizational factors and environmental factors, so as to improve the hindering factors and promote the application of clinical decision support system which based on guideline in future research and clinical practice.
ABSTRACT
Objective:To study the practical efficacy of the clinical decision support system for diagnosis and treatment of thyroid cancer (CDSS-TC) in assisting doctors to complete several diagnosis and treatment tasks, and to make a preliminary evaluation of its clinical practicability according to the test results.Methods:From Jan. 2022 to Mar. 2022, 90 patients with thyroid cancer who were admitted to the Head and Neck Surgery Department of Shaw Hospital affiliated to Zhejiang University were prospectively analyzed, and the average time spent in reading the pre-operative B-ultrasound report, as well as the individual fitness of the dose adjustment of eugenol in 70 patients with thyroid cancer after surgery. A retrospective analysis was made of the compliance of the basis of the "recommended scheme" and the deviation of the basis of the doctor’s "final scheme" for the preoperative surgery of 120 patients with thyroid cancer who were treated for the first time in the head and neck surgery of Shaw Hospital affiliated to Zhejiang University from Mar. 2021 to May. 2021. All cases were treated by pure artificial (group A) and CDSS-TC assisted (group B) , and the differences in organization were compared.Results:The average time for disposal of a single B-ultrasound report in Group B was much shorter than that in Group A ( P=5.600E-04) ; The number of patients with excellent grade and the total number of patients with excellent grade and qualified grade recommended by the doctor in group B were significantly higher than those in group A ( P=7.819E-20 and P=1.335E-18) ; The conformity rate of the basis of CDSS-TC "Recommended Scheme" ≥ 98%; The deviation rate of the basis for "final protocol" of doctors in group B was lower than that in group A ( P=0.059 for total resection or not, P=0.075 for lateral neck dissection or not) . Conclusions:CDSS-TC can accurately extract the disease-related source information in all the original examination/laboratory reports, and provide accurate decision-making suggestions through efficient correlation analysis. In view of the accurate and objective conclusions of its analysis, it can provide high-quality and all-link decision support for doctors’ clinical diagnosis and treatment, and is an ideal information work platform.
ABSTRACT
Objective: Medication-related errors in patients are among the leading causes of preventable health damage and harm worldwide. In the United States, these errors cause at least one death a day and damage approximately 1.3 million people annually. According to the World Health Organization, the global expenditure on medication-related errors is estimated to be U$ 42 billion per year. In Brazil, the rate of potential drug interactions varies between 28% and 63.6% for primary care patients. The prevalence of drug interactions has increased following an aging population, increased chronic conditions, combined use of different drugs, and increased prescription drugs per patient. Methods: The data used for this study were obtained through the database from Nexodata do Brasil S.A a private health technology company with an electronic prescription system and a data intelligence area. Results: 65,867 electronic prescriptions were evaluated during 2019. Of these, 4,828 prescriptions had an average of 2.5 interactions. These interactive prescriptions were generated by 197 different doctors, totaling 24.5 prescriptions with interaction per doctor over 12 months. A total of 12,005 interactions were identified, 15.6% classified as mild, 70.9% as moderate, and 13.5% as severe. Conclusion: By implementing an electronic prescription tool, a reduction of 32.9% in the number of prescriptions with drug interaction was observed.
ABSTRACT
Clinical decision support system based on medical artificial intelligence(AI)is a key link in medical artificial intelligence transformation of Alzheimer's disease.This paper reviews the status of medical AI used for diagnosis and treatment of Alzheimer's disease, proposed the deficiencies existing in the current application process, in order to provide new ideas for the development of a more professional clinical decision support system for Alzheimer's disease that is suitable for China's national conditions.
ABSTRACT
Objective:To evaluate the effectiveness of antimicrobial stewardship based on self-developed antibiotic clinical decision support system (aCDSS) in the inpatients at a tertiary hospital for consecutive 6 years, and to provide reference for rational use and antimicrobial stewardship.Methods:aCDSS was self-designed based on information technology and applied in clinical use in our hospital from 2015. Data of inpatient information and antibacterial use from January 2015 to December 2020 were collected from HIS and aCDSS. A retrospective study was conducted in all inpatients on the utilization rate and antibiotic use density.Results:Since 2015, with the comprehensive implementation of antimicrobial stewardship based on the aCDSS,there was a significant decline on the annual rate of antibiotic usage from 44.18% in 2015 to 38.70% in 2020, as well as on the usage rate of extended-spectrum antimicrobial agents including carbapenems, broad-spectrum β-lactam/β-lactamase inhibitors, tigecycline, broad-spectrum cephalosporins, fluoroquinolones, as well as glycopeptide and antifungal drugs. Compared with 2015, the usage of carbapenems, tigecycline and broad-spectrum β-lactam/β-lactamase inhibitors was declined nearly 50% in 2020, and the density of carbapenems and tigecycline were decreased by 29.6% and 7.1%, respectively in 2020. On the other side, the utilization rate and use density of narrow-spectrum cephalosporins continued to increase by year, the use density of narrow-spectrum cephalosporins accounting for 28.2% of all antibiotics in 2020.Conclusions:With the comprehensive implementation of aCDSS, the utilization rate and density of broad-spectrum and high-priced antibacterial drugs in our hospital have decreased continuously to decline in the past 6 years, while the proportion of narrow-spectrum antimicrobials has increased year by year, indicating that the structure of antimicrobial use has been continuously optimized and that antimicrobial stewardship based on the information technology have achieved remarkable results.
ABSTRACT
Introdução: A pandemia da COVID-19 representa um grande desafio para os sistemas de saúde de todo o mundo, com demandas sem precedentes em todos os níveis de atenção à saúde. Na atenção primária, além do cuidado dos indivíduos com sintomas gripais, a descontinuidade do acompanhamento de pacientes com doenças crônicas é causa de grande preocupação. Na atenção hospitalar, a necessidade imediata de assistir pacientes com formas graves e críticas da COVID-19, exigiu ampliação de leitos convencionais e de cuidados intensivos, recursos tecnológicos para suporte avançado de vida e capacitação em tempo recorde, à medida que avançavam os conhecimentos sobre a doença. Objetivos: O presente trabalho possui dois objetivos principais. Objetivo 1: Avaliar o impacto da pandemia da COVID-19 em uma coorte de pessoas com hipertensão e diabetes na atenção primária, além de desenvolver e implementar uma solução digital para melhorar o monitoramento no domicílio. Objetivo 2: Avaliar se o escore de risco ABC2-SPH é capaz de predizer a necessidade de ventilação mecânica em pacientes com COVID-19 e comparar seu desempenho ao de outros escores desenvolvidos para predizer ventilação mecânica, mortalidade e outros desfechos, inclusive em pacientes não COVID. Métodos: Para alcançar o objetivo 1: Foi desenvolvido um estudo multimetodológico. Uma avaliação quasi-experimental analisou o impacto da pandemia na frequência de consultas e controle de pacientes com hipertensão e diabetes em 34 unidades básicas de saúde (UBS) em 10 municípios do Vale do Mucuri, Minas Gerais, entre junho de 2017 e dezembro de 2020, considerando como ponto de corte o dia 14 de março de 2020, quando as medidas de restrição social tiveram início. Em seguida, um estudo de factibilidade desenvolveu um aplicativo com um sistema de apoio à decisão (SAD) para agentes comunitários de saúde (ACS) para identificar, durante a visita domiciliar, pacientes com hipertensão arterial (HAS) e/ou diabetes mellitus (DM) não controlados e referenciá-los para atendimento presencial na UBS. Um painel de especialistas avaliou a viabilidade, usabilidade e utilidade do aplicativo através de questionário específico. Para alcançar o objetivo 2: Estudo de coorte retrospectiva, derivado do estudo originalmente chamado "Avaliação do perfil laboratorial, radiológico e sintomatológico de pacientes infectados com o novo coronavírus 2019 (SARS-CoV-2) em hospitais do estado de Minas Gerais" que se tornou um estudo multicêntrico, realizado em 31 hospitais, em 17 cidades de cinco estados. O estudo incluiu pacientes que foram internados em dois períodos: março a setembro de 2020 e março a dezembro de 2021, com diagnóstico de COVID-19 confirmado. Neste estudo, o escore de risco ABC2-SPH, desenvolvido para predição de mortalidade intra-hospitalar por COVID-19, foi avaliado quanto à possibilidade de predizer a necessidade de ventilação mecânica e comparado a outros escores: CALL, PREDI-CO, SUM, STSS, COVID_IRS_NLR, CURB-65, SOFA e 4C Mortality Score. Resultados: Objetivo 1: Dos 5070 pacientes, 4810 (94,9%) tinham HAS, 1371 (27,4%) tinham DM e 1111 (23,1%) tinham as duas doenças. Houve redução significativa no número de consultas semanais quando comparados o período antes e depois do início das medidas de restrição social (107 [IQR 60,0, 153,0] vs 20,0 [IQR 7,0, 29,0], respectivamente, p <0,001. Apenas 15,2% de todos os pacientes retornaram para consulta durante a pandemia. Indivíduos com HAS que retornaram tinham níveis de pressão arterial sistólica (120,0 [IQR 120,0-140,0]) e diastólica (80,0 [IQR 80,0-80,0]) menores do que os níveis apresentados antes da pandemia por aqueles que não retornaram (130,0 [IQR 120,0-140,0] e 80,0 [IQR 80,0-90,0]), p<0,001. Além disso, aqueles que retornaram tiveram uma proporção maior de HAS controlada (64,3% vs 52,8%). Para o DM, não houve diferenças nos níveis de glicohemoglobina. Em relação ao SAD, os especialistas concordaram que os ACS podem incorporá-lo facilmente em suas rotinas e o aplicativo pode identificar pacientes em risco e melhorar o tratamento. Objetivo 2: Ao longo do estudo, foram incluídos 4.831 pacientes, com idade mediana de 59,0 (IQR 48,0, 70,0) anos e 46,3% do sexo feminino. Destes, 34,2% necessitaram de tratamento intensivo, 26,6% necessitaram de VMI e 18,7% faleceram. Os pacientes que necessitaram de VMI apresentaram maior prevalência de HAS, DM, obesidade e mortalidade quando comparados aos que não necessitaram (64,3% vs 2,3%, p<0,001). Com base no conjunto de dados imputados, o ABC2-SPH apresentou AUROC 0,677 (IC 95% 0,681-0,694). Considerando apenas os casos completos, a AUROC foi de 0,70 (IC 95% 0,68-0,72), tendo o melhor desempenho entre os escores com amostras maiores de casos completos. No geral, as discriminações dos escores foram de regular a ruim. O SOFA Score teve a maior sensibilidade, 0,84 (IC 95% 0,81-0,86). O escore SOFA teve a maior sensibilidade 0,84 (IC 95% 0,81-0,86). Conclusões: A pandemia da COVID-19 causou uma queda significativa no número de consultas de pacientes com HAS e DM na atenção primária. Um SAD para ACS mostrou-se viável e útil para identificar pacientes descontrolados em casa. O escore ABC2-SPH demonstrou melhor desempenho do que os outros escores, mas não com precisão suficiente para prever com segurança a necessidade de ventilação mecânica em pacientes hospitalizados com COVID-19. Novos estudos devem ser realizados para desenvolver escores fáceis de aplicar que tenham melhor calibração e discriminação para auxiliar na difícil decisão de instituir o suporte ventilatório avançado.
Introduction: The COVID-19 pandemic represents a major challenge for health systems around the world, with unprecedented demands on all levels of health care. In primary care, in addition to the care of individuals with flu-like symptoms, the discontinuity of monitoring patients with chronic diseases is a cause of great concern. In hospital care, the immediate need to assist patients with severe and critical forms of COVID-19 required the expansion of conventional and intensive care beds, technological resources for advanced life support and training in record time, as knowledge about the disease evolved. Objectives: The present study has two main objectives. Objective 1: To assess the impact of the COVID-19 pandemic on a cohort of people with hypertension and diabetes in primary care, and to develop and implement a digital solution to improve home monitoring. Objective 2: To assess whether the ABC2-SPH risk score can predict the need for invasive mechanical ventilation (IMV) in patients with COVID-19 and to compare its performance with other scores developed to predict IMV, mortality and other outcomes, including in non-COVID patients. Methods: To achieve objective 1: A multi-methodological study was developed. A quasi-experimental evaluation analyzed the impact of the pandemic on the frequency of consultations and control of patients with hypertension and diabetes in 34 primary health care centers (PHCC) in 10 municipalities in Mucuri Valley (Vale do Mucuri), Minas Gerais, between June 2017 and December 2020, considering March 14, 2020, as the cut-off point, when social restriction measures began. Then, a feasibility study developed an application with a decision support system (DSS) for community health workers (CHW) to identify, during home visits, patients with uncontrolled hypertension and/or diabetes and refer them for in person consultation at the PHCC. A panel of experts evaluated the app's feasibility, usability and usefulness through a specific questionnaire. To achieve objective 2: Retrospective cohort study, derived from the study originally called "Evaluation of the laboratory, radiological and symptomatologic profile of patients infected with the new coronavirus 2019 (SARS-CoV-2) in hospitals in the state of Minas Gerais", which became a multicenter study, carried out in 31 hospitals, in 17 cities in five states The study included patients who were hospitalized in two periods: March to September 2020 and March to December 2021, with a confirmed diagnosis of COVID-19 . In this study, the ABC2-SPH risk score, developed to predict in-hospital mortality from COVID-19, was evaluated for the possibility of predicting the need for mechanical ventilation and compared to other scores: CALL, PREDI-CO, SUM, STSS, COVID_IRS_NLR, CURB-65, SOFA and 4C Mortality Score Results: Objective 1: Of 5070 patients, 4810 (94.9%) had hypertension, 1371 (27.4%) had DM, and 1111 (23.1%) had both diseases. There was a significant reduction in the weekly number of consultations (107, IQR 60.0-153.0 before vs 20.0, IQR 7.0-29.0) after social restriction; P<.001. Only 15.2% (772/5070) of all patients returned for a consultation during the pandemic. Individuals with hypertension had lower systolic (120.0, IQR 120.0-140.0 mm Hg) and diastolic (80.0, IQR 80.0-80.0 mmHg) blood pressure than those who did not return (130.0, IQR 120.0-140.0 mm Hg) and (80.0, IQR 80.0-90.0 mm Hg; P<.001). Also, those who returned had a higher proportion of controlled hypertension (64.3% vs 52.8%). For DM, there were no differences in glycohemoglobin levels. Concerning the DSS, the experts agreed that the CHWs can easily incorporate it into their routines and the app can identify patients at risk and improve treatment. Objective 2: Throughout the study, 4831 patients were included, median age 59.0 (IQR 48.0, 70.0) years-old and 46.3% female. Of those, 34.2 % required intensive care treatment, 26.6% required IMV and 18.7% died. Patients who required IMV had higher prevalence of hypertension, diabetes, obesity, and mortality when compared to those who did not require it (64.3% vs 2.3%, p<0.001). Based on the imputed dataset, the ABC2-SPH AUROC was 0.677 (95% CI 0.681-0.694). Considering only complete cases, the AUROC was 0.70, having the best performance among scores that had larger samples of complete cases. When the data were imputed, was 0.67. Considering only complete cases, the AUROC was 0.70 (95% CI 0.68-0.72, having the best performance among scores that had larger samples of complete cases. Overall, the score discriminations ranged from poor to fair. The SOFA Score had the highest sensitivity, 0.84 (95% CI 0.81-0.86). Conclusions: The COVID-19 pandemic caused a significant drop in the number of consultations of patients with hypertension and diabetes in primary care. An SSD for CHW proved to be feasible and useful for identifying uncontrolled patients at home. ABC2-SPH demonstrated better performance than the other scores, but not accurately enough to reliably predict the need for IMV COVID-19 hospitalized patients. Research should continue to develop easy-to-use scores with better calibration and discrimination, given the importance of assisting clinicians in decision-making when initiating advanced ventilatory support.
Subject(s)
Telemedicine , Diabetes Mellitus , COVID-19 , Hypertension , Primary Health Care , Respiration, Artificial , Mortality , Academic Dissertation , Decision Support Systems, Clinical , Pandemics , Patient CareABSTRACT
ABSTRACT Objective: To analyze the critical alarms predictors of clinical deterioration/sepsis for clinical decision making in patients admitted to a reference hospital complex. Methods: An observational retrospective cohort study. The Machine Learning (ML) tool, Robot Laura®, scores changes in vital parameters and lab tests, classifying them by severity. Inpatients and patients over 18 years of age were included. Results: A total of 122,703 alarms were extracted from the platform, classified as 2 to 9. The pre-selection of critical alarms (6 to 9) indicated 263 urgent alerts (0.2%), from which, after filtering exclusion criteria, 254 alerts were delimited for 61 inpatients. Patient mortality from sepsis was 75%, of which 52% was due to sepsis related to the new coronavirus. After the alarms were answered, 82% of the patients remained in the sectors. Conclusions: Far beyond technology, ML models can speed up assertive clinical decisions by nurses, optimizing time and specialized human resources.
RESUMEN Objetivo: Analizar alarmas críticas predictoras de deterioración clínica/sepsis para toma de decisiones clínicas en pacientes internados en complejo hospitalario de referencia. Métodos: Estudio observacional de cohorte retrospectivo. La herramienta Machine Learning (ML), Robot Laura®, puntúa alteraciones en parámetros vitales y exámenes laboratoriales, clasificándolos por gravedad. Incluyeron pacientes internados y mayores de 18 años. Resultados: Extrajeron 122.703 alarmas de la plataforma, clasificadas de 2 hasta 9. La preselección de alarmas críticas (6 a 9) apuntó 263 alertas urgentes (0,2%), entre ellas, después del filtro de criterios de exclusión, delimitaron 254 alertas para 61 pacientes internados. La mortalidad de pacientes por sepsis fue de 75%, entre ellos 52% debido a sepsis relacionada al nuevo coronavirus. Después de las alarmas ser atendidas, 82% de los pacientes permanecieron en los sectores. Conclusiones: Más allá de la tecnología, modelos de ML pueden agilizar la decisión clínica asertiva de enfermeros, optimizando tiempos y recursos humanos especializados.
RESUMO Objetivo: Analisar os alarmes críticos preditores de deterioração clínica/sepse para tomada de decisão clínica nos pacientes internados em complexo hospitalar de referência. Métodos: Estudo observacional de coorte retrospectivo. A ferramenta de Machine Learning (ML), Robô Laura®, pontua alterações nos parâmetros vitais e exames laboratoriais, classificando-os por gravidade. Incluíram-se pacientes internados e maiores de 18 anos. Resultados: Extraíram-se 122.703 alarmes da plataforma, classificados de 2 até 9. A pré-seleção dos alarmes críticos (6 a 9) apontou 263 alertas urgentes (0,2%), dos quais, após o filtro de critérios de exclusão, delimitaram se 254 alertas para 61 pacientes internados. A mortalidade dos pacientes por sepse foi de 75%, dos quais 52% devido à sepse relacionada ao novo coronavírus. Após os alarmes serem atendidos, 82% dos pacientes permaneceram nos setores. Conclusões: Muito além da tecnologia, modelos de ML podem agilizar a decisão clínica assertiva dos enfermeiros, otimizando tempos e recursos humanos especializados.
ABSTRACT
Patient safety.Estudo transversal. Objetivo: avaliar a sensibilidade e especificidade de sistemas de rastreamento de acesso aberto para interações medicamentosas potenciais (IMp) em comparação com o DRUG-REAX® system e analisar o impacto clínico potencial das IMp de gravidades "Contraindicada" e "Maior" não detectadas. Métodos: amostra composta por 140 pacientes em acompanhamento em um ambulatório especializado no atendimento a pessoas com doenças crônicas não transmissíveis (DCNT) de um hospital universitário. As IMp foram identificadas e classificadas no DRUG-REAX® System e em oito sistemas de rastreamento de acesso aberto. As IMp de gravidade "Contraindicada" e "Maior" foram analisadas segundo o impacto clínico. Utilizou-se estatística descritiva e calculou-se sensibilidade e especificidade dos sistemas de rastreamento na identificação das IMp. Resultados: Os sistemas de acesso aberto pertencentes as bases Drugs.com, UCLA School of Health e CVC Caremark apresentaram sensibilidade e especificidade > 70%. A totalidade dos sistemas de acesso aberto não detectou os pares ciprofibrato + estatinas e metformina + sitagliptina, cujos impactos clínicos incluíram risco de miopatia e rabdomiólise e hipoglicemia, respectivamente. Cerca de um terço (37,5%) dos sistemas de acesso aberto não detectou a IMp ácido acetilsalicílico + hidroclorotiazida, capaz de ocasionar nefrotoxicidade. Conclusão: A maioria dos pares de IMp integra o rol terapêutico de pacientes com DCNT e cujos impactos clínicos são tempo-dependentes. A combinação de julgamento clínico, revisão periódica do plano terapêutico e os atributos de precisão (sensibilidade e especificidade) são fundamentais para garantir a segurança do paciente, sobretudo no contexto ambulatorial. (AU)
This study aims to evaluate the sensitivity and specificity of open-access screening systems in detecting potential drug-drug interactions (PDDIs) compared to the DRUG-REAX® system and analyze the potential clinical impact of PDDIs of "Contraindicated" and "Major" severities not detected. A cross-sectional study was conducted in an outpatient clinic specialized in caring for patients with noncommunicable diseases (NCDs) of a university hospital. PDDIs were identified and classified in the DRUG-REAX® System and eight open-access screening systems. The "Contraindicated" and "Major" severity PDDIs were analyzed according to clinical impact. Descriptive statistics were used and the sensitivity and specificity of the screening systems were calculated to identify the PDDIs. Results: The open-access systems Drugs.com, UCLA School of Health and CVC Caremark showed sensitivity and specificity > 70%. All open access systems did not detect the pairs ciprofibrate + statins and metformin + sitagliptin, whose clinical impacts included the risk of myopathy/ rhabdomyolysis and hypoglycemia, respectively. About a third (37.5%) of open-access systems did not detect PDDI acetylsalicylic acid + hydrochlorothiazide, which is capable of causing nephrotoxicity. Conclusion: Most pairs of PDDIs are part of the therapeutic role of patients with NCDs and whose clinical impacts are time-dependent. The combination of clinical judgment, periodic review of the therapeutic plan and the attributes of precision (sensitivity and specificity) are essential to ensure patient safety, especially in the outpatient setting. (AU)
Subject(s)
Mass Screening , Access to Information , Drug Interactions , Patient Safety , Noncommunicable Diseases , Hospitals, UniversityABSTRACT
Objective:To analyze the application status and problems of clinical decision support system(CDSS) in medical institutions in China, and put forward corresponding suggestions.Methods:From April to May in 2020, a questionnaire survey was conducted in 1 013 medical institutions in 31 provinces of China. The contents of the questionnaire included the current situation of CDSS installation and deployment, the purpose of establishment, the source of knowledge base, the content to be optimized and the factors hindering the use.Results:199(19.64%) medical institutions had CDSS, among which 123 were used in the whole hospital and 76 in some departments; 426 medical institutions did not use CDSS, but had plans to use it. It was found that the current CDSS system had setbacks, such as big cognitive difference, lack of authority in knowledge, high difficulty in data governance, lack of industry standards and so on.Conclusions:In the future, the standardized use of CDSS in medical institutions could be promoted from the aspects of raising awareness, establishing knowledge authority and establishing standards.
ABSTRACT
Research into medical artificial intelligence (AI) has made significant advances in recent years, including surgical applications. This scoping review investigated AI-based decision support systems targeted at the intraoperative phase of surgery and found a wide range of technological approaches applied across several surgical specialties. Within the twenty-one (n = 21) included papers, three main categories of motivations were identified for developing such technologies: (1) augmenting the information available to surgeons, (2) accelerating intraoperative pathology, and (3) recommending surgical steps. While many of the proposals hold promise for improving patient outcomes, important methodological shortcomings were observed in most of the reviewed papers that made it difficult to assess the clinical significance of the reported performance statistics. Despite limitations, the current state of this field suggests that a number of opportunities exist for future researchers and clinicians to work on AI for surgical decision support with exciting implications for improving surgical care.
ABSTRACT
On May 25, 2019, the World Health Assembly approved the eleventh revision of the International Statistical Classification of Diseases and Related Health Problems (ICD-11), containing a chapter on traditional medicine. This means that the traditional East Asian medicine (TEAM) is now officially recognized as a part of mainstream medical practice. However, the patterns presented in the ICD-11 traditional medicine chapter are only the tip of the iceberg of TEAM clinical practice, and it will be necessary to supplement and upgrade the contents. In order to implement this, objectification and standardization of TEAM must be premised, and grafting with proper modern science and technology is imperative. Pattern Identification and Prescription Expert-11 (PIPE-11), which is a TEAM clinical decision support system, adopts vastly from clinical literature on pattern identification and the prescription. By adopting the rule-based reasoning method, the way of diagnosis and prescription by a TEAM practitioner in actual clinical practice is implemented as it is. PIPE-11 could support to improve both the accuracy of medical diagnosis and the reliability of the medical treatment of TEAM in clinical practices. In the field of research, it might facilitate the usage for reliable reference for symptoms and signs retrieval and patient simulation. In the field of education, it can provide a high level of training for learning pattern identification and prescription, and further be used to reinforce skills of diagnosis and prescription by providing self-simulation methods. Therefore, PIPE-11 as a digital application is expected to support the traditional medicine chapter of ICD-11 to successfully contribute to the improvement of human health.
ABSTRACT
Medical big data is a hot research topic in China,and it is also the main research direction in the field of emergency medicine.The current situation of the construction of the first-aid big data platform and the construction of the first-aid clinical decision support system were analyzed,the problems existing in the development of the first-aid big data research field were enumerated,to explore the theoretical methods for promoting the development of domestic first-aid big data,so as to provide references for the research in related fields.
ABSTRACT
OBJECTIVES: Mobile health (m-Health) technologies may provide an appropriate follow-up support service for patient groups with post-treatment conditions. While previous studies have introduced m-Health methods for patient care, a smart system that may provide follow-up communication and decision support remains limited to the management of a few specific types of diseases. This paper introduces an m-Health solution in the current climate of increased demand for electronic information exchange. METHODS: Adopting a novel design science research approach, we developed an innovative solution model for post-treatment follow-up decision support interaction for use by patients and physicians and then evaluated it by using convergent interviewing and focus group methods. RESULTS: The cloud-based solution was positively evaluated as supporting physicians and service providers in providing post-treatment follow-up services. Our framework provides a model as an artifact for extending care service systems to inform better follow-up interaction and decision-making. CONCLUSIONS: The study confirmed the perceived value and utility of the proposed Clinical Decision Support artifact indicating that it is promising and has potential to contribute and facilitate appropriate interactions and support for healthcare professionals for future follow-up operationalization. While the prototype was developed and tested in a developing country context, where the availability of doctors is limited for public healthcare, it was anticipated that the prototype would be user-friendly, easy to use, and suitable for post-treatment follow-up through mobility in remote locations.
Subject(s)
Humans , Artifacts , Climate , Decision Support Systems, Clinical , Delivery of Health Care , Developing Countries , Focus Groups , Follow-Up Studies , Patient Care , TelemedicineABSTRACT
Explaining the clinical decision support system and its related concepts, reviewing the application status of the clinical decision support system in the nursing field, summarizing the necessity and challenges of developing the clinical decision system in the nursing field, hoping to provide suggestion for the development of nursing decision support system suitable for China′s clinical status