ABSTRACT
Abstract@#Myopia has become a major public health issue of global concern. Scientific and effective myopia prediction models can help identify high risk groups for myopia, thereby achieving precise prevention. With the rapid development of genome wide association studies and the establishment of large scale prospective population cohorts, the polygenic risk score (PRS) model has been used to predict myopia phenotypes, advancing the myopia prediction window and thus predicting high myopia risk for early screening and intervention for at risk groups. The review aims to systematically elaborate the identification and verification of myopia genes in recent years, briefly describe the practice and effectiveness evaluation of the PRS model in myopia prevention research at home and abroad, reveal the application value in myopia prediction research, and emphasize the relationship between the PRS prediction model and outdoor activities. Close eye use and other preventive measures are of great significance to promote the precise prevention of myopia in children and adolescents.
ABSTRACT
Objective To establish a clinical prediction model for preeclampsia by monitoring risk rating of MP gestation and levels of placental growth factor(PLGF)combined with uterine artery pulsatility index(PI)measured during examination of fetal nuchal translucency(NT).Methods Twenty-four patients with preeclampsia who met the inclusion criteria were selected as the case group,and 95 healthy pregnant women during the same period were randomly selected as the control group.Serum concentrations of PLGF,uterine artery PI values measured by quantitative immunofluorescence assay at 11-14 weeks of gestation,risk ratings for MP hypertension monitoring at 11-20 weeks of gestation,and other relevant data,BMI,age,gestation,mode of delivery,neonatal birth weight and Apgar score were collected in the two groups.Results Results of univariate regression analysis showed that BMI,age,high risk of PI,MP and PLGF<12 were influencing factors for adverse outcomes.Results of multivariate regression analysis showed that high PI,medium high risk in MP and PLGF<12 were independent risk factors for adverse outcomes.The prediction model of PE established was logit(P)=-15.767 + 0.020×PI + 0.072×MP risk(medium-high risk = 1,low risk = 0)+ 0.181×PLGF classification(<12 = 1,≥12 = 0),with an AUC area of 0.883,specificity of 0.816 and sensitivity of 0.846.Conclusion The combination of PI,MP risk and PLGF to establish a clinical predictive model for preeclampsia has certain value,and its combined predictive value is higher than that of single application.
ABSTRACT
Objective@#To explore the performance of machine learning prediction models in forecasting student absenteeism due to respiratory symptoms caused by air pollution in short term, aiming to provide a methodological reference for early warning systems of school diseases.@*Methods@#Utilizing data from shortterm sequences of student absenteeism due to respiratory symptoms in Jiangsu Province from September 2019 to October 2022, the study integrated average concentrations of atmospheric pollutants. A univariate distributed lag nonlinear model was employed to select optimal lag variables for the pollutants. An extreme gradient boosting(XGBoost) algorithm model was developed to predict the frequency of absenteeism due to respiratory symptoms and compared with the seasonal autoregressive integrated moving average with exogenous factors(SARIMAX) model.@*Results@#Between 2019 and 2022, an average of 9 709 students per day in Jiangsu Province were absent due to respiratory symptoms. The daily average air quality index (AQI) was 76.96,with mass concentrations of PM2.5, PM10, NO2, and O3 averaging at 35.75, 61.13, 28.89, 104.81 μg/m3, respectively. Granger causality tests indicated that AQI, PM2.5, PM10, NO2, and O3 were significant predictors of absenteeism frequency due to respirutory symptoms(F=1.46,1.79,1.67,3.41,2.18,P<0.01). The singleday lag effects of PM2.5, PM10, NO2, and O3 reached their peak relative risk (RR) values at lag4, lag0, lag0, lag4 respectively. When integrating these optimal lag variables for the pollutants, the XGBoost model demonstrated superior predictive performance to the SARIMAX model, reducing the mean absolute error (MAE) from 2.251 to 0.475, mean absolute percentage error (MAPE) from 0.429 to 0.080, and root mean square error (RMSE) from 2.582 to 0.713; at the P75 percentile alert threshold, the sensitivity improved from 0.086 to 0.694 and specificity from 0.979 to 0.988, with the Youden index increasing from 0.065 to 0.682.@*Conclusions@#The XGBoost model exhibits robust predictive performance and effective early warning capabilities for shortterm sequences of student absenteeism due to respiratory symptoms caused by air pollution. Schools could timely adopt this model to preemptively detect and control disease outbreaks, thereby enhancing school health management.
ABSTRACT
Objective@#To construct a nonsuicidal selfinjury (NSSI) risk prediction model for middle school students using different machine learning algorithms and evaluate the models effectiveness, so as to provide guidance for the prevention and control of NSSI in campus.@*Methods@#In March 2023, a total of 3 372 middle and high school students from schools in Nanchang, Fuzhou and Shangrao cities in Jiangxi Province were selected by combining stratified random cluster sampling and convenient sampling methods. Questionnaire surveys were conducted using various instruments including general information questionnaire, Selfesteem Scale, Ottawa Selfinjury Scale, Social Support Assessment Scale, Chinese Version of the Olweus Bullying Questionnaire, Event Attribution Style Scale, Adolescent Resilience Scale, and Adolescent Life Events Scale. Data were divided into training set (n=2 361) and test set (n=1 011) at a ratio of 7∶3, and variables were selected based on univariate and LASSO regression results. Four machine learning algorithms including namely random forest, support vector machine, Logistic regression and XGBoost, were used to construct NSSI risk prediction models, and the models performance was evaluated and compared using metrics including area under curve (AUC), sensitivity, specificity, positive predictive value, negative predictive value and F1 score.@*Results@#The detection rate of NSSI among middle school students was 34.4%. Univariate analysis showed that there were statistically significant differences in NSSI detection rates among middle school students of different grades, genders, registered residence locations, whether they were class cadres and four types of bullying (physical, verbal, relational bullying and cyberbullying) (χ2=27.17, 15.81, 11.54, 4.63;68.22, 140.63, 77.81, 13.95, P<0.05). NSSI was included as the dependent variable in the LASSO regression model for variable screening, and the results regression identified 10 predictive variables including grade level, selfesteem, subjective support, support utilization, verbal bullying, emotional control, interpersonal relationships, punishment, loss of relatives and property, and health and adaptation issues. The AUC values of random forest, support vector machine, Logistic regression, and XGBoost algorithms were 0.76, 0.76, 0.76 and 0.77, respectively, with no statistically significant differences between pairwise comparisons (Z=-0.59-0.82, P>0.05). Sensitivity values were 0.62, 0.61, 0.62 and 0.61, respectively. Specificity values were 0.74, 0.78, 0.78 and 0.78, respectively. Positive predictive values were 0.56, 0.59, 0.60 and 0.59, respectively. Negative predictive values were 0.79, 0.79, 0.80 and 0.79, respectively. F1 scores were 0.59, 0.60, 0.61 and 0.60, respectively.@*Conclusions@#All four nonsuicidal selfinjury risk prediction models perform well, with the Logistic regression model slightly outperforming the others. Schools and parents should pay attention to the predictive factors corresponding to NSSI, so as to reduce the occurrence of NSSI among middle school students.
ABSTRACT
ABSTRACT Purpose: The emergency medical service is a fundamental part of healthcare, albeit crowded emergency rooms lead to delayed and low-quality assistance in actual urgent cases. Machine-learning algorithms can provide a smart and effective estimation of emergency patients' volume, which was previously restricted to artificial intelligence (AI) experts in coding and computer science but is now feasible by anyone without any coding experience through auto machine learning. This study aimed to create a machine-learning model designed by an ophthalmologist without any coding experience using AutoML to predict the influx in the emergency department and trauma cases. Methods: A dataset of 356,611 visits at Hospital da Universidade Federal de São Paulo from January 01, 2014 to December 31, 2019 was included in the model training, which included visits/day and the international classification disease code. The training and prediction were made with the Amazon Forecast by 2 ophthalmologists with no prior coding experience. Results: The forecast period predicted a mean emergency patient volume of 216.27/day in p90, 180.75/day in p50, and 140.35/day in p10, and a mean of 7.42 trauma cases/ day in p90, 3.99/day in p50, and 0.56/day in p10. In January of 2020, there were a total of 6,604 patient visits and a mean of 206.37 patients/day, which is 13.5% less than the p50 prediction. This period involved a total of 199 trauma cases and a mean of 6.21 cases/day, which is 55.77% more traumas than that by the p50 prediction. Conclusions: The development of models was previously restricted to data scientists' experts in coding and computer science, but transfer learning autoML has enabled AI development by any person with no code experience mandatory. This study model showed a close value to the actual 2020 January visits, and the only factors that may have influenced the results between the two approaches are holidays and dataset size. This is the first study to apply AutoML in hospital visits forecast, showing a close prediction of the actual hospital influx.
RESUMO Objetivo: Esse estudo tem como objetivo criar um modelo de Machine Learning por um oftalmologista sem experiência em programação utilizando auto Machine Learning predizendo influxo de pacientes em serviço de emergência e casos de trauma. Métodos: Um dataset de 366,610 visitas em Hospital Universitário da Universidade Federal de São Paulo de 01 de janeiro de 2014 até 31 de dezembro de 2019 foi incluído no treinamento do modelo, incluindo visitas/dia e código internacional de doenças. O treinamento e predição foram realizados com o Amazon Forecast por dois oftalmologistas sem experiência com programação. Resultados: O período de previsão estimou um volume de 206,37 pacientes/dia em p90, 180,75 em p50, 140,35 em p10 e média de 7,42 casos de trauma/dia em p90, 3,99 em p50 e 0,56 em p10. Janeiro de 2020 teve um total de 6.604 pacientes e média de 206,37 pacientes/dia, 13,5% menos do que a predição em p50. O período teve um total de 199 casos de trauma e média de 6,21 casos/dia, 55,77% mais casos do que a predição em p50. Conclusão: O desenvolvimento de modelos era restrito a cientistas de dados com experiencia em programação, porém a transferência de ensino com a tecnologia de auto Machine Learning permite o desenvolvimento de algoritmos por qualquer pessoa sem experiencia em programação. Esse estudo mostra um modelo com valores preditos próximos ao que ocorreram em janeiro de 2020. Fatores que podem ter influenciados no resultado foram feriados e tamanho do banco de dados. Esse é o primeiro estudo que aplicada auto Machine Learning em predição de visitas hospitalares com resultados próximos aos que ocorreram.
ABSTRACT
Resumo Objetivo. Este estudo teve como objetivo estimar a prevalência da doença de Chagas (DC) crônica (DCC) na população brasileira, em mulheres e em mulheres em idade fértil. Métodos. Foi realizada uma metanálise da literatura para extrair dados de prevalência de DCC na população brasileira, em mulheres e em mulheres em idade fértil, em municípios do Brasil, no período 2010-2022. Indicadores relacionados com a DCC disponíveis nos sistemas de informação em saúde foram selecionados em escala municipal. A modelagem estatística dos dados extraídos da metanálise em função daqueles obtidos dos sistemas de informação foi aplicada a modelos lineares, lineares generalizados e aditivos. Resultados. Foram selecionados os cinco modelos mais adequados de um total de 549 modelos testados para obtenção de um modelo de consenso (R2 ajustado = 54%). O preditor mais importante foi o cadastro autorreferido de DCC do sistema de informação da Atenção Primária à Saúde. Dos 5 570 munícipios brasileiros, a prevalência foi estimada como zero em 1 792 (32%); nos 3 778 municípios restantes, a prevalência média da doença foi estimada em 3,25% (± 2,9%). O número de portadores de DCC foi estimado na população brasileira (~3,7 milhões), mulheres (~2,1 milhões) e mulheres em idade fértil (~590 mil). A taxa de reprodução da doença foi calculada em 1,0336. Todas as estimativas se referem ao intervalo 2015-2016. Conclusões. As prevalências estimadas de DCC, especialmente entre mulheres em idade fértil, evidenciam o desafio da transmissão vertical em municípios brasileiros. Estas estimativas são comparadas aos padrões de projeções matemáticas, sugerindo sua incorporação ao Pacto Nacional para a Eliminação da Transmissão Vertical da DC.
ABSTRACT Objective. The objective of this study is to estimate the prevalence of chronic Chagas disease (CCD) in Brazil: in the general population, in women, and in women of childbearing age. Methods. A meta-analysis of the literature was conducted to extract data on the prevalence of CCD in municipalities in Brazil in the 2010-2022 period: in the general population, in women, and in women of childbearing age. Municipal-level CCD indicators available in health information systems were selected. Statistical modeling of the data extracted from the meta-analysis (based on data obtained from information systems) was applied to linear, generalized linear, and additive models. Results. The five most appropriate models were selected from a total of 549 models tested to obtain a consensus model (adjusted R2 = 54%). The most important predictor was self-reported CCD in the primary health care information system. Zero prevalence was estimated in 1 792 (32%) of Brazil's 5 570 municipalities; in the remaining 3 778 municipalities, average prevalence of the disease was estimated at 3.25% (± 2.9%). The number of carriers of CCD was estimated for the Brazilian population (~3.7 million), for women (~2.1 million) and for women of childbearing age (~590 000). The disease reproduction rate was calculated at 1.0336. All estimates refer to the 2015-2016 period. Conclusions. The estimated prevalence of CCD, especially among women of childbearing age, highlights the challenge of vertical transmission in Brazilian municipalities. Mathematical projections suggest that these estimates should be included in the national program for the elimination of vertical transmission of Chagas disease.
Resumen Objetivo. El objetivo de este estudio fue estimar la prevalencia de la enfermedad de Chagas crónica en la población brasileña en general, en las mujeres y en las mujeres en edad fértil. Métodos. Se realizó un metanálisis de la bibliografía para extraer datos sobre la prevalencia de la enfermedad de Chagas crónica en la población brasileña en general, en las mujeres y en las mujeres en edad fértil, en los municipios de Brasil durante el período 2010-2022. Se seleccionaron los indicadores relacionados con esa enfermedad disponibles en los sistemas municipales de información de salud. La modelización estadística de los datos extraídos del metanálisis, en función de los obtenidos de los sistemas de información, se aplicó a modelos lineales, lineales generalizados y aditivos. Resultados. Se seleccionaron los cinco modelos más apropiados de un total de 549 modelos evaluados, para obtener un modelo de consenso (R2 ajustado = 54%). El factor predictor más importante fue el registro de la enfermedad de Chagas crónica autodeclarada en el sistema de información de atención primaria de salud. De los 5570 municipios brasileños, en 1792 (32%) la prevalencia estimada fue nula y en los 3778 restantes la prevalencia media fue del 3,25% (± 2,9%). El número estimado de pacientes con enfermedad de Chagas crónica en la población brasileña en general, en las mujeres y en las mujeres en edad fértil fue de ~3,7 millones, ~2,1 millones y ~590 000, respectivamente. La tasa calculada de reproducción de la enfermedad fue de 1,0336. Todas las estimaciones se refieren al período 2015-2016. Conclusiones. La prevalencia estimada de la enfermedad de Chagas crónica, especialmente en las mujeres en edad fértil, pone de manifiesto el desafío que representa la transmisión vertical en los municipios brasileños. Estas estimaciones están en línea con los patrones de las proyecciones matemáticas, y sugieren la necesidad de incorporarlas al Pacto Nacional para la Eliminación de la Transmisión Vertical de la Enfermedad de Chagas.
ABSTRACT
ABSTRACT BACKGROUND: Although studies have examined the relationship between variables associated with active aging and quality of life (QoL), no studies have been identified to have investigated the effect of a structural model of active aging on QoL in a representative sample of older people in the community. OBJECTIVE: To measure the domains and facets of QoL in older people and identify the effect of the structural model of active aging on the self-assessment of QoL. DESIGN AND SETTING: This cross-sectional analytical study included 957 older people living in urban areas. Data were collected from households using validated instruments between March and June 2018. Descriptive, confirmatory factor, and structural equation modeling analyses were performed. RESULTS: Most older people self-rated their QoL as good (58.7%), and the highest mean scores were for the social relationships domain (70.12 ± 15.4) and the death and dying facet (75.43 ± 26.7). In contrast, the lowest mean scores were for the physical domains (64.41 ± 17.1) and social participation (67.20 ± 16.2) facets. It was found that active aging explained 50% of the variation in self-assessed QoL and directly and positively affected this outcome (λ = 0.70; P < 0.001). CONCLUSION: Active aging had a direct and positive effect on the self-assessment of QoL, indicating that the more individuals actively aged, the better the self-assessment of QoL.
ABSTRACT
SUMMARY OBJECTIVE: The aim of this study was to assess the performance of the CALL Score tool in predicting the death outcome in COVID-19 patients. METHODS: A total of 897 patients were analyzed. Univariate and multivariate logistic regression analyses were conducted to determine the association between characteristics of the CALL Score and the occurrence of death. The relationship between CALL Score risk classification and the occurrence of death was also examined. Receiver operating characteristic curve analysis was performed to identify optimal cutoff points for the CALL Score and the outcome. RESULTS: The study revealed that age>60 years, DHL>500, and lymphocyte count ≤1000 emerged as independent predictors of death. Higher risk classifications of the CALL Score were associated with an increased likelihood of death. The optimal CALL Score cutoff point for predicting the death outcome was 9.5 (≥9.5), with a sensitivity of 70.4%, specificity of 80.3%, and accuracy of 80%. CONCLUSION: The CALL Score showed promising discriminatory ability for death outcomes in COVID-19 patients. Age, DHL level, and lymphocyte count were identified as independent predictors. Further validation and external evaluation are necessary to establish the robustness and generalizability of the CALL Score in diverse clinical settings.
ABSTRACT
ABSTRACT Objective: The purpose of this study was to assess performance in the Brazilian Lung Cancer Registry Database by using the parsimonious EuroLung risk models for morbidity and mortality. Methods: The EuroLung1 and EuroLung2 models were tested and evaluated through calibration (calibration plot, Brier score, and the Hosmer-Lemeshow test) and discrimination (ROC AUCs), in a national multicenter registry of 1,031 patients undergoing anatomic lung resection. Results: The evaluation of performance in Brazilian health care facilities utilizing risk-adjustment models, specifically EuroLung1 and EuroLung2, revealed substantial miscalibration, as evidenced by calibration plots and Hosmer-Lemeshow tests in both models. In terms of calibration, EuroLung1 exhibited a calibration plot with overlapping points, characterized by a slope of 1.11 and a Brier score of 0.15; the Hosmer-Lemeshow test yielded a statistically significant p-value of 0.015; and the corresponding ROC AUC was 0.678 (95% CI: 0.636-0.721). The EuroLung2 model displayed better calibration, featuring fewer overlapping points in the calibration plot, with a slope of 1.22, with acceptable discrimination, as indicated by a ROC AUC of 0.756 (95% CI: 0.670-0.842). Both models failed to accurately predict morbidity and mortality outcomes in this specific health care context. Conclusions: Discrepancies between the EuroLung model predictions and outcomes in Brazil underscore the need for model refinement and for a probe into inefficiencies in the Brazilian health care system.
ABSTRACT
Objetivo: Verificar as associações diretas e indiretas entre variáveis demográficas, econômicas, biopsicossociais e comportamentais com a incapacidade funcional de idosos com catarata autorreferida. Método: Estudo transversal entre 260 idosos com catarata autorreferida e residentes na área urbana de uma microrregião de saúde de Minas Gerais. A coleta dos dados foi realizada nos domicílios mediante a aplicação de instrumentos validados no Brasil. Procederam-se as análises descritiva e de trajetórias (p<0,05). Resultados: O declínio funcional ocorreu de forma hierárquica. O pior desempenho físico associou-se diretamente à maior incapacidade funcional para as atividades básicas (p= 0,003), instrumentais (p<0,001) e avançadas (p= 0,003) da vida diária. A inatividade física esteve associada diretamente à maior incapacidade funcional para as atividades instrumentais (p<0,001) e avançadas (p<0,001). A menor escolaridade (p= 0,020), o maior número de sintomas depressivos (p<0,001) e o menor escore de apoio social (p<0,001) associaram-se diretamente à maior incapacidade funcional para as atividades avançadas, tal como a maior idade (p= 0,001) para as instrumentais. Observaram-se associações indiretas, mediadas pelo pior desempenho físico, entre o sexo feminino e o maior número de morbidades com a incapacidade funcional para as três atividades da vida diária. Conclusão: Idosos com catarata autorreferida apresentaram comprometimento da capacidade funcional relacionado à idade mais avançada, à baixa escolaridade, ao pior desempenho físico, à inatividade física, à presença de sintomas depressivos e ao menor nível de apoio social.
Objective: To verify the direct and indirect associations between demographic, economic, biopsychosocial and behavioral variables with the functional disability of the elderly with self-reported cataract. Method: Cross-sectional study among 260 elderly people with self- reported cataract and residents in the urban area of ââa health micro-region in Minas Gerais. Data collection was carried out in the households through the application of instruments validated in Brazil. Descriptive and trajectory analyzes were carried out (p<0.05). Results: The functional decline occurred in a hierarchical manner. The worst physical performance was directly associated with greater functional incapacity for basic (p= 0.003), instrumental (p<0.001) and advanced (p= 0.003) activities of daily living. Physical inactivity was directly associated with greater functional disability for instrumental (p<0.001) and advanced (p<0.001) activities. Lower schooling (p= 0.020), higher number of depressive symptoms (p<0.001) and lower social support score (p<0.001) were directly associated with greater functional incapacity for advanced activities, such as older age (p= 0.001) for the instruments. Indirect associations, mediated by worse physical performance, were observed between females and the highest number of morbidities with functional incapacity for the three activities of daily living. Conclusion: Elderly people with self-reported cataract showed impairment of functional capacity related to older age, low education, worse physical performance, physical inactivity, presence of depressive symptoms and lower level of social support.
ABSTRACT
ABSTRACT BACKGROUND: Increased longevity is accompanied by new social and health demands, such as the race/color social construct, indicating the need to identify the specific needs of older adults to maintain and improve their quality of life. OBJECTIVE: We aimed to verify the direct and indirect associations of demographic, economic, and biopsychosocial characteristics with self-assessed quality of life in older adults according to race/color. DESIGN AND SETTING: This cross-sectional study included 941 older adults living in the urban area of a health microregion in Minas Gerais, Brazil. METHODS: Older adults were divided into three groups: white (n = 585), brown (n = 238), and black (n = 102) race/color. Descriptive and trajectory analyses were performed (P < 0.05). RESULTS: Among the three groups, worse self-assessed quality of life was directly associated with lower social support scores and greater numbers of depressive symptoms. Worse self-assessed quality of life was also directly associated with a higher number of functional disabilities in basic activities of daily living and the absence of a partner among older adults of brown and black race/color. Lower monthly income and higher numbers of morbidities and compromised components of the frailty phenotype were observed among participants of white race/color, as well as lower levels of education in the brown race/color group. CONCLUSION: Factors associated with poorer self-assessed quality of life among older adults in the study community differed according to race/color.
ABSTRACT
Abstract BACKGROUND: Obesity is a risk factor for falls in older adults, but the effects of body fat distribution and its interaction with other factors are not well established. OBJECTIVES: To verify the occurrence of falls among older adults with and without abdominal obesity and the effects of sociodemographic, health, and behavioral variables on this outcome. DESIGN AND SETTING: A cross-sectional study in an urban area of Alcobaça, Brazil. METHODS: Men and women older than 60 years with (270) and without (184) abdominal obesity were included. Sociodemographic, health, and behavioral data were collected using validated questionnaires in Brazil. Descriptive and path analyses were performed (P < 0.05). RESULTS: The occurrence of falls was high in participants with abdominal obesity (33.0%). In both groups, a higher number of morbidities (β = 0.25, P < 0.001; β = 0.26, P = 0.002) was directly associated with a higher occurrence of falls. Among participants without abdominal obesity, a lower number of medications (β = -0.16; P = 0.04), a higher number of depressive symptoms (β = 0.15; P = 0.04), worse performance on the agility and dynamic balance tests (β = 0.37; P < 0.001), and lower functional disability for basic activities of daily living (β = -0.21; P = 0.006) were directly associated with the occurrence of falls. CONCLUSION: Adults older than 60 years with abdominal obesity have a higher prevalence of falls. Different factors were associated with the occurrence of falls in both groups.
ABSTRACT
Objective:To explore the predictive value of pre-biopsy serum inflammatory markers on positive prostate biopsy results, establish a nomogram model based on pre-biopsy inflammatory markers combined with other parameters, and evaluate its predictive ability for prostate biopsy results.Methods:The clinical data of 601 patients undergoing transperineal prostate biopsy who were admitted to the Second Hospital of Tianjin Medical University from August 2019 to August 2021 were retrospectively analyzed. The median age was 68(35, 89)years, and the median tPSA was 9.56(4.01, 19.95)ng/ml. The median fPSA was 1.36(0.88, 2.02)ng/ml, the median PSAD was 0.16(0.11, 0.26)ng/ml 2, and the median platelet-to-lymphocyte ratio(PLR)was 129.90(98.95, 169.89). PI-RADS v2.1 score<3 points in 189 cases(31.45%), 3 points in 174 cases(28.95%), 4 points in 190 cases(31.61%), and 5 points in 48 cases(7.99%). A simple randomization method was used to obtain 421 cases(70.00%)in the modeling group and 180 cases(30%)in the validation group.There was no significant difference in the clinical data between the two groups ( P>0.05). Univariate and multivariate logistic regression analysis were performed in the modeling group to screen independent influencing factors for the prediction of positive prostate biopsy results. A nomogram model was established and internal verification was conducted. External validation of the model was performed in the validation group. Receiver operating characteristic(ROC)curve was used to verify model discrimination, Hosmer-Lemeshow goodness-of-fit test was used to verify model calibration, and decision curve analysis (DCA) was used to evaluate the net benefit and clinical utility of the predictive model. Results:The results of univariate analysis showed that the age( OR=1.060, P<0.01), histological inflammation( OR=0.312, P<0.01), the number of biopsy needles( OR=0.949, P=0.009), f/tPSA( OR=0.954, P=0.003), PV( OR=0.973, P<0.01), PSAD( OR=29.260, P<0.01), PI-RADS v2.1 score(3-point OR=3.766, P=0.001; 4-point OR=11.800, P<0.01; 5-point OR=57.033, P<0.01), lymphocyte count( OR=1.535, P=0.013), NLR( OR=0.848, P=0.044), PLR( OR=0.994, P=0.005)and SII( OR=0.999, P=0.009)were statistically different between the prostate patients and non-prostate cancer patients in the modeling group; Multivariate analysis showed that age( OR=1.094, P<0.001), fPSA( OR=0.605, P=0.002), histological inflammation ( OR=0.241, P<0.001), PSAD ( OR=7.57, P=0.013), PLR ( OR=0.994, P=0.005) and PI-RADS v2.1 Score(3-point OR=2.737, P=0.016; 4-point OR=8.621, P<0.001; 5-point OR=47.65, P<0.001) was an independent influencing factor for prostate cancer at initial biopsy; a nomogram model based on age, fPSA, PSAD, PLR and PI-RADS v2.1 scores was established. The AUC of the modeling group was 0.849(95% CI 0.810-0.888), and the sensitivity was 80.9%, and the specificity was 76.1%; the AUC of the validation group was 0.862(95% CI 0.809-0.915), and the sensitivity was 91.9%, and the specificity was 67.8%, suggesting that the diagnostic prediction model had a good discrimination. The calibration curve showed that the prediction model was well calibrated ( χ2=6.137, P=0.632). The decision curve analysis (DCA) of the modeling and validation groups indicated a larger net benefit of the predictive model. Conclusions:The nomogram model established in this study based on age, fPSA, PSAD, PLR and PI-RADS v2.1 score showed good predictive efficacy for prostate biopsy in patients with PSA between 4-20 ng/ml.
ABSTRACT
Objective To investigate the value of a risk assessment model in predicting venous thromboembolism (VTE) in patients with liver failure after artificial liver support therapy. Methods A retrospective analysis was performed for the clinical data of 124 patients with liver failure who received artificial liver support therapy in Affiliated Drum Tower Hospital of Nanjing University Medical School from March 2019 to December 2021, among whom there were 41 patients with VTE (observation group) and 143 patients without VTE (control group). Related clinical data were compared between the two groups, and the Caprini risk assessment model was used for scoring and risk classification of the patients in both groups. The t -test was used for comparison of continuous data between two groups; the chi-square test was used for comparison of categorical data between two groups; the Mann-Whitney U rank sum test was used for comparison of ranked data between two groups. The logistic regression analysis was used to investigate the independent risk factors for VTE in patients with liver failure after artificial liver support therapy. The receiver operating characteristic (ROC) curve was used to investigate the value of Caprini score and the multivariate predictive model used alone or in combination in predicting VTE. Results The observation group had a significantly higher Caprini score than the control group (4.39±1.10 vs 3.12±1.04, t =6.805, P < 0.001). There was a significant difference between the two groups in risk classification based on Caprini scale ( P < 0.05), and the patients with high risk or extremely high risk accounted for a higher proportion among the patients with VTE. The univariate analysis showed that there were significant differences between the two groups in age ( t =6.400, P < 0.001), catheterization method ( χ 2 =14.413, P < 0.001), number of times of artificial liver support therapy ( Z =-4.720, P < 0.001), activity ( Z =-6.282, P < 0.001), infection ( χ 2 =33.071, P < 0.001), D-dimer ( t =8.746, P < 0.001), 28-day mortality rate ( χ 2 =5.524, P =0.022). The multivariate analysis showed that number of times of artificial liver support therapy (X 1 ) (odds ratio [ OR ]=0.251, 95% confidence interval [ CI ]: 0.111-0.566, P =0.001), activity (X 2 ) ( OR =0.122, 95% CI : 0.056-0.264, P < 0.001), D-dimer (X 3 ) ( OR =2.921, 95% CI : 1.114-7.662, P =0.029) were independent risk factors for VTE in patients with liver failure after artificial liver support therapy. The equation for individual predicted probability was P =1/[1+e -(7.425-1.384X 1 -2.103X 2 +1.072X 3 ) ]. The ROC curve analysis showed that Caprini score had an area under the ROC curve of 0.802 (95% CI : 0.721-0.882, P < 0.001), and the multivariate model had an area under the ROC curve of 0.768 (95% CI : 0.685-0.851, P < 0.001), while the combination of Caprini score and the multivariate model had an area under the ROC curve of 0.957 (95% CI : 0.930-0.984, P < 0.001). Conclusion The Caprini risk assessment model has a high predictive efficiency for the risk of VTE in patients with liver failure after artificial liver support therapy, and its combination with the multivariate predictive model can significantly improve the prediction of VTE.
ABSTRACT
Transjugular intrahepatic portosystemic shunt (TIPS) is a safe and effective method for the treatment of portal hypertension complications in patients with decompensated liver cirrhosis. At present, there are many prognostic scoring tools for risk stratification of poor prognosis after TIPS. This article briefly introduces seven prognostic scoring tools commonly used for TIPS and summarizes the clinical research evidence of each scoring tool. The literature review shows that there is currently no sufficient research evidence to determine the optimal prognostic scoring tool after TIPS. Future clinical studies should comprehensively explore the advantages and disadvantages of different scoring tools in predicting short- and long-term adverse prognostic events after TIPS and develop new prognostic scoring tools in combination with new prognostic markers.
ABSTRACT
Objective:To establish a prediction model of acute gastrointestinal injury (AGI) above grade II in elderly patients with severe pneumonia, and to evaluate and validate the model internally.Methods:A retrospective analysis was performed on 268 patients aged >65 years with severe pneumonia admitted to the Second People′s Hospital of Hefei from June 2019 to May 2022 (207 cases in the training set and 61 cases in the verification set). Sixteen indicators, including age, sex, underlying disease, pneumonia Severity index (PSI) score, dosage of sedative and analgesic drugs, and mechanical ventilation time of all patients were collected. After logistic regression analysis in the training set, a model was established to predict AGI above grade Ⅱ in elderly patients with severe pneumonia. Receiver operating characteristic (ROC) curve was drawed and correction curve was used to evaluate the reliability of the model. The model was internally validated by validation set data.Results:Among 207 patients with severe pneumonia in the training set, 50 patients developed AGI above grade Ⅱ during treatment. The prediction model was established by logistic regression analysis as follows: When L=Sequential Organ Failure Assessment (SOFA)×0.181+ PSI score×0.066+ propofol dosage×0.607+ reifentanil dosage×1.187, L>19.288, it can be considered that patients with severe pneumonia have a 93.24% chance of developing grade Ⅱ or above AGI. The ROC curve showed that the model was well differentiated, AUC=0.960. H-L test indicated (χ 2=7.39, P=0.496>0.05) the model fit was good. The sensitivity and specificity of the model were 82.00% and 96.82% respectively. AUC=94.58% (sensitivity 81.25%, specificity 93.33%), H-L test indicated ( χ 2=4.51, P=0.808>0.05) the prediction accuracy was 90.16%. Conclusions:The prediction model for AGI after severe pneumonia in elderly patients can be used clinically to help predict the occurrence of AGI in elderly patients with multiple injuries.
ABSTRACT
Objective:To explore the diagnostic value of clinical, multi-parameter magnetic resonance imaging (MP-MRI) combined with transrectal ultrasound elasticity data for prostate cancer.Methods:A retrospective analysis was conducted on patient data from November 2021 to March 2023 when transrectal prostate two-dimensional ultrasound, real-time strain elastography of the prostate, MP-MRI examination of the prostate, and prostate biopsy were performed simultaneously at the Meizhou People′s Hospital. We collected patient age, height, weight, free serum prostate specific antigen (fPSA), total prostate specific antigen (tPSA), fPSA/tPSA, MRI prostate imaging report and data system (PI-RADS) scores, and ultrasound elasticity values. Four predictive models for prostate cancer diagnosis were constructed using multivariate logistic regression for comparison, and the optimal model was selected to construct a column chart. The diagnostic performance of different models was evaluated using receiver operating characteristic (ROC) curves, and the diagnostic performance of column charts was evaluated using calibration curves.Results:This study included a total of 117 patients with 117 prostate lesions, 47 benign prostate lesions, and 70 prostate cancer lesions. There were statistically significant differences in age, fPSA, tPSA, fPSA/tPSA, PI-RADS scores, and ultrasound elasticity values between benign and malignant lesions patients (all P<0.01). The area under the curve (AUC) of the clinical model (age+ tPSA+ fPSA+ fPSA/tPSA), MRI model (PI-RADS score), ultrasound elastic model, and clinical+ MRI+ ultrasound elastic combined model for diagnosing prostate cancer were 0.86, 0.86, 0.92, and 0.98, respectively. Conclusions:Compared with a single diagnostic model, the combination of age, tPSA, fPSA/tPSA, PI-RADS scores, and ultrasound elasticity value model can improve the diagnostic rate of prostate cancer.
ABSTRACT
Objective:To analyze the Risk factors for rapid progression of inpatients with anti-melanoma differentiation associated gene5 (MDA5) antibody-positive dermamyositis (DM) complicated with interstitial lung disease (ILD), and construct a clinical predictive model.Methods:A total of 63 hospitalized patients with anti MDA5 positive DM combined with ILD (MDA5+ DM-ILD) from January 1, 2016 to May 30, 2022 at the Second Affiliated Hospital of the Air Force Military Medical University were included in the study. They were divided into a control group (DM-ILD) and an observation group (DM-RPPILD) based on whether they had rapidly progressing interstitial lung disease (RPILD). Retrospective collection and organization of clinical case data from patients were conducted, and binary logistic regression was used to summarize the risk factors of DM-RPILD. R software was used to construct a clinical prediction model for RPILD occurrence using training set data, and validation set data was used to verify the predictive ability of the model.Results:The proportion of patients with SpO 2<90% at the initial diagnosis of ILD, the titers of anti MDA5 antibodies, immunoglobulin M (IgM), serum ferritin (FER) levels, and positive rates of anti Ro52 antibodies in the observation group were higher than those in the control group, the lymphocyte (LYM) count level was lower than that of the control group (all P<0.05). Binary logistic regression analysis showed SpO 2<90% at the initial diagnosis of ILD, FER level, LYM count, and anti Ro52 antibody were the influencing factors for the occurrence of RPILD (all P<0.05). The area under the curve (AUC) of the training set prediction model for predicting resistance to MDA5+ DM-RPILD was 0.922(95% CI: 0.887-0.957), with a sensitivity of 95.7% and a specificity of 72.5%; In the validation set, the prediction model predicted an AUC of 0.939(95% CI: 0.904-0.974) for resistance to MDA5+ DM-RPILD, with a sensitivity of 90.0% and a specificity of 88.9%; The calibration curves of the training and validation sets indicated that the predictive model had good calibration ability. Conclusions:SpO 2<90% at the initial diagnosis of ILD, FER levels increase, LYM count levels decrease, and anti Ro52 antibody positivity are risk factors for RPILD. The constructed clinical model has good predictive ability and has certain guiding significance for clinical work.
ABSTRACT
Patients with advanced chronic liver disease (ACLD) are hospitalized due to hepatitis, acute decompensation or liver failure and its complications, and they often require stratified management due to different severities. The patients with acute-on-chronic liver failure (ACLF) have the highest short-term mortality rate among ACLD patients and should be treated in tertiary hospitals. Although non-ACLF patients tend to have a relatively low mortality rate, they still have the risk of progression to ACLF, and there is a significant increase in mortality rate after progression to ACLF, which requires stratified management. The patients with extremely low progression rates often have favorable clinical outcomes and can be administrated in primary hospitals, while the high-risk population should be closely monitored and timely transferred in case of disease progression. However, currently there is still a lack of accurate predictive models for evaluating the risk of progression to ACLF, and further studies are needed to find new biomarkers or algorithms.
ABSTRACT
Objective To establish a noninvasive diagnostic model for chronic hepatitis B (CHB) liver fibrosis based on LASSO regression using serological parameters, and to investigate the value of this model in the diagnosis of CHB liver fibrosis. Methods A total of 240 patients who were diagnosed with CHB in Changzhou Second People's Hospital, Nanjing Medical University, from September 2019 to September 2021 were enrolled as subjects, and according to the results of liver biopsy and pathology, they were divided into significant liver fibrosis (stage F2-F4) group with 175 patients and non-significant liver fibrosis (stage F0-F1) group with 65 patients. The two groups were compared in terms of sex, age, blood biochemical parameters, and liver stiffness measurement (LSM) measured by two-dimensional shear wave elastography, and LASSO regression and the multivariate logistic regression analysis were used screen out the risk factors for liver fibrosis. A nomogram model was established and then verified by the receiver operating characteristic (ROC) curve, calibration curve, and decision curve. A one-way analysis of variance was used for comparison of normally distributed continuous data between multiple groups, and the least significant difference t -test was used for further comparison between two groups; the Kruskal-Wallis H test was used for comparison of non-normally distributed continuous data between groups; the chi-square test was used for comparison of categorical data between groups. Results There were significant differences between the patients with stage F3/F4 liver fibrosis and those with stage F2/F0-F1 liver fibrosis in age, alanine aminotransferase, aspartate aminotransferase, alkaline phosphatase, gamma-glutamyl transpeptidase, total bilirubin, platelet count, procollagen type Ⅲ, type Ⅳ collagen, hyaluronic acid, and LSM (all P < 0.05). Five important variables were screened out by LASSO regression, and the logistic regression analysis showed that hyaluronic acid (odds ratio [ OR ]=1.432, P < 0.05), type Ⅳ collagen ( OR =1.243, P < 0.05), procollagen type Ⅲ( OR =1.146, P < 0.05), and LSM ( OR =1.656, P < 0.05) were the independent risk factors for liver fibrosis, while platelet count ( OR =0.567, P < 0.05) was a protective factor. Compared with the patients with stage F2/F0-F1 liver fibrosis, the patients with stage F3/F4 liver fibrosis had significantly higher score of the nomogram model, LSM, aspartate aminotransferase-to-platelet ratio index (APRI), King score, Forns index, and fibrosis-4 (FIB-4) index (all P < 0.05). The ROC curve was used to analyze the predictive value of the nomogram model, and the results showed an area under the ROC curve of 0.876, which was significantly higher than that of LSM, APRI, King score, Forns index, and FIB-4 (all P < 0.05). Calibration curve and decision curve showed that the nomogram model had acceptable consistency and benefit. Conclusion The noninvasive nomogram model based on LASSO regression is established by using serum parameters including hyaluronic acid, type Ⅳ collagen, procollagen type Ⅲ, platelet count, and LSM, and as a quantitative tool for the clinical diagnosis of CHB liver fibrosis, it has a high diagnostic efficiency and thus holds promise for clinical application.