RESUMO
INTRODUCTION: The prevalence of cognitive impairment and dementia in the older population is increasing, and thereby, early detection of cognitive decline is essential for effective intervention. METHODS: This study included 2,288 participants with normal cognitive function from the Ma'anshan Healthy Aging Cohort Study. Forty-two potential predictors, including demographic characteristics, chronic diseases, lifestyle factors, anthropometric indices, physical function, and baseline cognitive function, were selected based on clinical importance and previous research. The dataset was partitioned into training, validation, and test sets in a proportion of 60% for training, 20% for validation, and 20% for testing, respectively. Recursive feature elimination was used for feature selection, followed by six machine learning algorithms that were employed for model development. The performance of the models was evaluated using area under the curve (AUC), specificity, sensitivity, and accuracy. Moreover, SHapley Additive exPlanations (SHAP) was conducted to access the interpretability of the final selected model and to gain insights into the impact of features on the prediction outcomes. SHAP force plots were established to vividly show the application of the prediction model at the individual level. RESULTS: The final predictive model based on the Naive Bayes algorithm achieved an AUC of 0.820 (95% CI, 0.773-0.887) on the test set, outperforming other algorithms. The top ten influential features in the model included baseline Mini-Mental State Examination (MMSE), education, self-reported economic status, collective or social activities, Pittsburgh sleep quality index (PSQI), body mass index, systolic blood pressure, diastolic blood pressure, instrumental activities of daily living, and age. The model demonstrated the potential to identify individuals at a higher risk of cognitive impairment within 3 years from older adults. CONCLUSION: The predictive model developed in this study contributes to the early detection of cognitive impairment in older adults by primary healthcare staff in community settings.
Assuntos
Disfunção Cognitiva , Aprendizado de Máquina , Humanos , Masculino , Feminino , Idoso , Disfunção Cognitiva/diagnóstico , Disfunção Cognitiva/epidemiologia , Estudos de Coortes , Fatores de Risco , Idoso de 80 Anos ou mais , Algoritmos , Teorema de Bayes , Pessoa de Meia-Idade , Testes NeuropsicológicosRESUMO
BACKGROUND AND OBJECTIVE: Many studies regarding health analysis request structured datasets but the legacy resources provide scattered data. This study aims to establish a health informatics transformation model (HITM) based upon intelligent cloud computing with the self-developed analytics modules by open source technique. The model was exemplified by the open data of type 2 diabetes mellitus (DM2) with related cardiovascular diseases. METHODS: The Apache-SPARK framework was employed to generate the infrastructure of the HITM, which enables the machine learning (ML) algorithms including random forest, multi-layer perceptron classifier, support vector machine, and naïve Bayes classifier as well as the regression analysis for intelligent cloud computing. The modeling applied the MIMIC-III open database as an example to design the health informatics data warehouse, which embeds the PL/SQL-based modules to extract the analytical data for the training processes. A coupling analysis flow can drive the ML modules to train the sample data and validate the results. RESULTS: The four modes of cloud computation were compared to evaluate the feasibility of the cloud platform in accordance with its system performance for more than 11,500 datasets. Then, the modeling adaptability was validated by simulating the featured datasets of obesity and cardiovascular-related diseases for patients with DM2 and its complications. The results showed that the run-time efficiency of the platform performed in around one minute and the prediction accuracy of the featured datasets reached 90%. CONCLUSIONS: This study helped contribute the modeling for efficient transformation of health informatics. The HITM can be customized for the actual clinical database, which provides big data for training, with the proper ML modules for a predictable process in the cloud platform. The feedback of intelligent computing can be referred to risk assessment in health promotion.