Development of a Healthcare Information System for Community Care of Older Adults and Evaluation of Its Acceptance and Usability.

Objective: The need for health and social care for community-dwelling elderly is on the rise as the population ages. Through the provision of comprehensive services by multiple professionals in local communities, elderly people can receive continual care in a non-medical setting, which is favorable for early detection and intervention of potential problems. However, the lack of digitalization in primary care affects the effectiveness of the services and precludes full exploitation of the data. This study proposed an information system dedicated to caring for community-dwelling elderly people and investigated its acceptance and usability. Methods: An information system was designed for elderly care centers in the community, where data generated during care delivery, involving socio-demographic data, bio-measurements and health assessments and questionnaires, were digitized and stored for information management and exchange. A study was conducted to evaluate the acceptance and usability of the system after routine use of 6 months. The users of the system at an elderly care center were recruited to respond to a technology acceptance questionnaire and a system usability questionnaire. Results: The mean scores of the acceptance and usability questionnaires reached 5.1 out of the highest possible score of 7. The constructs of the acceptance questionnaire had good reliability. The social influence and facilitating conditions constructs had a significant correlation with the behavioral intention construct. Conclusions: The proposed information system demonstrated good acceptance and usability, which supported the feasibility of implementing it in community care centers for older adults. Further research will be conducted to address the limitation of sample size by extending the system to other elderly care centers, forming a large user base for a more in-depth and comprehensive performance evaluation.

Enhancement of prostate cancer diagnosis by machine learning techniques: an algorithm development and validation study.

BACKGROUND: To investigate the value of machine learning(ML) in enhancing prostate cancer(PCa) diagnosis. METHODS: Consecutive systematic prostate biopsies performed from Jan 2003-June 2017 were used as the training cohort, and prospective biopsies performed from July 2017-November 2019 were used as validation cohort. Men were included if PSA was 0.4-50 ng/mL, and information of digital rectal examination (DRE), Transrectal ultrasound(TRUS) prostate volume, TRUS abnormality were known. Clinically significant PCa(csPCa) was defined as Gleason 3 + 4 or above cancers. Area-under-curve (AUC) of receiver-operating characteristics (ROC) was compared between PSA, PSA density, European Randomized Study of Screening for Prostate Cancer (ERSPC) risk calculator (ERSPC-RC), and various ML techniques using PSA, DRE and TRUS information. ML techniques used included XGBoost, LightGBM, Catboost, Support vector machine (SVM), Logistic regression (LR), and Random Forest (RF), where cost sensitive learning was applied. RESULTS: Training and validation cohorts included 3881 and 778 consecutive men, respectively. RF model performed better than other ML techniques and PSA, PSA density and ERSPC-RC for prediction of PCa or csPCa in the validation cohort. In csPCa prediction, AUC of PSA, PSA density, ERSPC-RC and RF was 0.71, 0.80, 0.83 and 0.88 respectively. At 90-95% sensitivity for csPCa, RF model achieved a negative predictive value (NPV) of 97.5-98.0% and avoided 38.3-52.2% unnecessary biopsies. Decision curve analyses (DCA) showed RF model provided net clinical benefit over PSA, PSA density and ERSPC-RC. CONCLUSION: By using the same clinical parameters, ML techniques performed better than ERSPC-RC or PSA density in csPCa predictions, and could avoid up to 50% unnecessary biopsies.