RESUMEN
BACKGROUND: Antiretroviral therapy (ART) has transformed HIV from a fatal illness to a chronic disease. Given the high rate of treatment interruptions, HIV programs use a range of approaches to support individuals in adhering to ART and in re-engaging those who interrupt treatment. These interventions can often be time-consuming and costly, and thus providing for all may not be sustainable. OBJECTIVE: This study aims to describe our experiences developing a machine learning (ML) model to predict interruption in treatment (IIT) at 30 days among people living with HIV newly enrolled on ART in Nigeria and our integration of the model into the routine information system. In addition, we collected health workers' perceptions and use of the model's outputs for case management. METHODS: Routine program data collected from January 2005 through February 2021 was used to train and test an ML model (boosting tree and Extreme Gradient Boosting) to predict future IIT. Data were randomly sampled using an 80/20 split into training and test data sets, respectively. Model performance was estimated using sensitivity, specificity, and positive and negative predictive values. Variables considered to be highly associated with treatment interruption were preselected by a group of HIV prevention researchers, program experts, and biostatisticians for inclusion in the model. Individuals were defined as having IIT if they were provided a 30-day supply of antiretrovirals but did not return for a refill within 28 days of their scheduled follow-up visit date. Outputs from the ML model were shared weekly with health care workers at selected facilities. RESULTS: After data cleaning, complete data for 136,747 clients were used for the analysis. The percentage of IIT cases decreased from 58.6% (36,663/61,864) before 2017 to 14.2% (3690/28,046) from October 2019 through February 2021. Overall IIT was higher among clients who were sicker at enrollment. Other factors that were significantly associated with IIT included pregnancy and breastfeeding status and facility characteristics (location, service level, and service type). Several models were initially developed; the selected model had a sensitivity of 81%, specificity of 88%, positive predictive value of 83%, and negative predictive value of 87%, and was successfully integrated into the national electronic medical records database. During field-testing, the majority of users reported that an IIT prediction tool could lead to proactive steps for preventing IIT and improving patient outcomes. CONCLUSIONS: High-performing ML models to identify patients with HIV at risk of IIT can be developed using routinely collected service delivery data and integrated into routine health management information systems. Machine learning can improve the targeting of interventions through differentiated models of care before patients interrupt treatment, resulting in increased cost-effectiveness and improved patient outcomes.
RESUMEN
OBJECTIVES: The aim of this study was to characterize gastrointestinal (GI) transit times and pH in healthy cats. METHODS: GI transit times and pH were measured in six healthy, colony-housed, purpose-bred spayed female cats using a continuous, non-invasive pH monitoring system in a sequential order design. For the first period ('pre-feeding'), food was withheld for 20 h, followed by oral administration of a pH capsule. Five hours post-capsule administration, cats were meal-fed by offering them their daily allowance of food for 1 h. For the second period ('post-feeding'), food was withheld for 24 h and cats were fed for 1 h, after which a pH capsule was orally administered. Studies in both periods were repeated three times. GI transit times and pH were compared between the two periods. RESULTS: The median transit times for the pre- and post-feeding periods, respectively, were: gastric - 94 mins (range 1-4101) and 1068 mins (range 484-5521); intestinal - 1350 mins (range 929-2961) and 1534 mins (range 442-2538); and GI - 1732 mins (range 1105-5451) and 2795 mins (range 926-6563). The median GI pH values for the first and second periods, respectively, were: esophageal - 7.0 (range 3.5-7.8) and 4.5 (range 2.9-6.4); gastric - 2.7 (range 1.7-6.2) and 2.0 (range 1.1-3.3); intestinal - 8.2 (range 7.6-8.7) and 7.8 (range 6.7-8.5); first-hour small intestinal - 8.2 (range 7.4-8.7) and 8.3 (range 7.9-8.6); and last-hour large intestinal - 8.5 (range 7.0-8.9) and 7.8 (range 6.3-8.7). Gastric (P <0.0020) and intestinal pH (P <0.0059) were significantly increased in the pre-feeding period compared with the post-feeding period. CONCLUSIONS AND RELEVANCE: Gastric and intestinal pH differed significantly when the capsule was administered 5 h prior to feeding compared with 1 h after feeding. Transit times for both periods showed high degrees of intra- and inter-individual variability.
