Search

Abstract Artificial intelligence (AI) and machine learning describe a broad range of algorithm types that can be trained based on datasets to make predictions. The increasing sophistication of AI has created new opportunities to apply these algorithms within within trauma care. Our paper overviews the current uses of AI along the continuum of trauma care, including injury prediction, triage, emergency department volume, assessment, and outcomes. Starting at the point of injury, algorithms are being used to predict severity of motor vehicle crashes, which can help inform emergency responses. Once on the scene, AI can be used to help emergency services triage patients remotely in order to inform transfer location and urgency. For the receiving hospital, these tools can be used to predict trauma volumes in the emergency department to help allocate appropriate staffing. After patient arrival to hospital, these algorithms not only can help to predict injury severity, which can inform decision-making, but also predict patient outcomes to help trauma teams anticipate patient trajectory. Overall, these tools have the capability to transform trauma care. AI is still nascent within the trauma surgery sphere, but this body of the literature shows that this technology has vast potential. AI-based predictive tools in trauma need to be explored further through prospective trials and clinical validation of algorithms.

Abstract Background In accordance with international guidance for tuberculosis (TB) prevention, the Tanzanian Ministry of Health recommends isoniazid preventive therapy (IPT) for children aged 12 months and older who are living with HIV. Concerns about tolerability, adherence, and potential mistreatment of undiagnosed TB with monotherapy have limited uptake of IPT globally, especially among children, in whom diagnostic confirmation is challenging. We assessed IPT implementation and adherence at a pediatric HIV clinic in Tanzania. Methods In this prospective cohort study, eligible children living with HIV aged 1–15 years receiving care at the DarDar Pediatric Program in Dar es Salaam who screened negative for TB disease were offered a 6-month regimen of daily isoniazid. Patients could choose to receive IPT via facility- or community-based care. Parents/caregivers and children provided informed consent and verbal assent respectively. Isoniazid was dispensed with the child’s antiretroviral therapy every 1–3 months. IPT adherence and treatment completion was determined by pill counts, appointment attendance, and self-report. Patients underwent TB symptom screening at every visit. Results We enrolled 66 children between July and December 2017. No patients/caregivers declined IPT. Most participants were female (n = 43, 65.1%) and the median age was 11 years (interquartile range [IQR] 8, 13). 63 (95.5%) participants chose the facility-based model; due to the small number of participants who chose the community-based model, valid comparisons between the two groups could not be made. Forty-nine participants (74.2%) completed IPT within 10 months. Among the remaining 17, 11 had IPT discontinued by their provider due to adverse drug reactions, 5 lacked documentation of completion, and 1 had unknown outcomes due to missing paperwork. Of those who completed IPT, the average monthly adherence was 98.0%. None of the participants were diagnosed with TB while taking IPT or during a median of 4 months of follow-up. Conclusions High adherence and treatment completion rates can be achieved when IPT is integrated into routine, self-selected facility-based pediatric HIV care. Improved record-keeping may yield even higher completion rates. IPT was well tolerated and no cases of TB were detected. IPT for children living with HIV is feasible and should be implemented throughout Tanzania.

An amendment to this paper has been published and can be accessed via the original article.