Answers are grounded in this paper and cite their sources.
This retrospective study examined factors associated with vital status among 200 HIV-positive patients receiving antiretroviral therapy (ART) at Specialist Hospital, Gombe, Nigeria. Patients were selected by systematic sampling from ART clinic registers. The outcome was vital status as recorded in the register, coded as alive (1) or dead (0); 162 patients (81.0%) were alive and 38 patients (19.0%) were dead. Follow-up duration and dates of records were not available in the extracted dataset, so time-to-event analysis was not possible and vital status was analysed as a binary outcome. Logistic regression was used to estimate odds ratios (OR) with 95% confidence intervals (CI), and distributed FP-Growth association rule mining (minimum support 10%, minimum confidence 60%, lift >1.0) was used to identify frequent combinations of clinical characteristics associated with death. Distributed FP-Growth was implemented using Apache Spark MLlib FPGrowth (Spark 3.5, PySpark 3.5). At n = 200, distributed runtime was 0.72 ms versus serial 0.72 ms (speedup 0.99), showing that partitioning overhead dominates at this scale.
No takes yet. Share an insight, caveat, or question.
Mohammed et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: