METHODS: This study uses outpatient data from the HKL's Patient Management System (SPP) throughout 2019. The final data set has 246,943 appointment records with 13 attributes used for both descriptive and predictive analyses. The predictive analysis was carried out using seven machine learning algorithms, namely, logistic regression (LR), decision tree (DT), k-near neighbours (k-NN), Naïve Bayes (NB), random forest (RF), gradient boosting (GB) and multilayer perceptron (MLP).
RESULTS: The descriptive analysis showed that the no-show rate was 28%, and attributes such as the month of the appointment and the gender of the patient seem to influence the possibility of a patient not showing up. Evaluation of the predictive model found that the GB model had the highest accuracy of 78%, F1 score of 0.76 and area under the curve (AUC) value of 0.65.
CONCLUSION: The predictive model could be used to formulate intervention steps to reduce no-shows, improving patient care quality.
METHODOLOGY: We conducted a retrospective data retrieval from the medical records of 254 paediatric patients who had been diagnosed with confirmed cases of dengue fever. The clinical characteristics were compared between severe and non-severe dengue. Multiple logistic regression analysis was utilised to elucidate the variables that exhibited associations with severe dengue.
RESULTS: A total of 254 paediatric patients were included, among whom 15.4% (n = 39) were diagnosed with severe dengue. Multiple logistic regression analysis identified lethargy, systolic blood pressure (SBP) below 90 mmHg, capillary refilled time (CRT) longer than 2 seconds, ascites, and hepatomegaly were independently associated with severe dengue.
CONCLUSION: In paediatric patients, severe dengue is associated with specific clinical indicators, including lethargy, low systolic blood pressure, prolonged capillary refill time (CRT), and the presence of ascites and hepatomegaly. Identifying these clinical features early is crucial for primary care physicians, as it enables accurate diagnosis and timely intervention to manage severe dengue effectively.
METHODS AND ANALYSIS: The NeST Registry is designed as a product registry that would provide information on the use and safety of NeuroAiD in clinical practice. An online NeST Registry was set up to allow easy entry and retrieval of essential information including demographics, medical conditions, clinical assessments of neurological, functional and cognitive state, compliance, concomitant medications, and side effects, if any, among patients on NeuroAiD. Patients who are taking or have been prescribed NeuroAiD may be included. Participation is voluntary. Data collected are similar to information obtained during standard care and are prospectively entered by the participating physicians at baseline (before initialisation of NeuroAiD) and during subsequent visits. The primary outcome assessed is safety (ie, non-serious and serious adverse event), while compliance and neurological status over time are secondary outcomes. The in-person follow-up assessments are timed with clinical appointments. Anonymised data will be extracted and collectively analysed. Initial target sample size for the registry is 2000. Analysis will be performed after every 500 participants entered with completed follow-up information.
ETHICS AND DISSEMINATION: Doctors who prescribe NeuroAiD will be introduced to the registry by local partners. The central coordinator of the registry will discuss the protocol and requirements for implementation with doctors who show interest. Currently, the registry has been approved by the Ethics Committees of Universiti Kebangsaan Malaysia (Malaysia) and National Brain Center (Indonesia). In addition, for other countries, Ethics Committee approval will be obtained in accordance with local requirements.
TRIAL REGISTRATION NUMBER: NCT02536079.