Applications and Performance of Machine Learning Algorithms in Emergency Medical Services: A Scoping Review.

OBJECTIVE: The aim of this study was to summarize the literature on the applications of machine learning (ML) and their performance in Emergency Medical Services (EMS). METHODS: Four relevant electronic databases were searched (from inception through January 2024) for all original studies that employed EMS-guided ML algorithms to enhance the clinical and operational performance of EMS. Two reviewers screened the retrieved studies and extracted relevant data from the included studies. The characteristics of included studies, employed ML algorithms, and their performance were quantitively described across primary domains and subdomains. RESULTS: This review included a total of 164 studies published from 2005 through 2024. Of those, 125 were clinical domain focused and 39 were operational. The characteristics of ML algorithms such as sample size, number and type of input features, and performance varied between and within domains and subdomains of applications. Clinical applications of ML algorithms involved triage or diagnosis classification (n = 62), treatment prediction (n = 12), or clinical outcome prediction (n = 50), mainly for out-of-hospital cardiac arrest/OHCA (n = 62), cardiovascular diseases/CVDs (n = 19), and trauma (n = 24). The performance of these ML algorithms varied, with a median area under the receiver operating characteristic curve (AUC) of 85.6%, accuracy of 88.1%, sensitivity of 86.05%, and specificity of 86.5%. Within the operational studies, the operational task of most ML algorithms was ambulance allocation (n = 21), followed by ambulance detection (n = 5), ambulance deployment (n = 5), route optimization (n = 5), and quality assurance (n = 3). The performance of all operational ML algorithms varied and had a median AUC of 96.1%, accuracy of 90.0%, sensitivity of 94.4%, and specificity of 87.7%. Generally, neural network and ensemble algorithms, to some degree, out-performed other ML algorithms. CONCLUSION: Triaging and managing different prehospital medical conditions and augmenting ambulance performance can be improved by ML algorithms. Future reports should focus on a specific clinical condition or operational task to improve the precision of the performance metrics of ML models.

Statin Eligibility according to 2013 ACC/AHA and USPSTF Guidelines among Jordanian Patients with Acute Myocardial Infarction: The Impact of Gender.

The objectives of this study were to evaluate statin eligibility among Middle Eastern patients admitted with acute myocardial infarction (AMI) who had no prior use of statin therapy, according to 2013 ACC/AHA and 2016 USPSTF guidelines, and to compare statin eligibility between men and women. This was a retrospective multicenter observational study of all adult patients admitted to five tertiary care centers in Jordan with a first-time AMI, no prior cardiovascular disease, and no prior statin use between April 2018 and June 2019. Ten-year atherosclerotic cardiovascular disease (ASCVD) risk score was estimated based on ACC/AHA risk score. A total of 774 patients met the inclusion criteria. The mean age was 55 years (SD ± 11.3), 120 (15.5%) were women, and 688 (88.9%) had at least one risk factor of cardiovascular disease. Compared to men, women were more likely to be older; had a history of diabetes, hypertension, and hypercholesterolemia; and had higher body mass index, systolic blood pressure, total cholesterol, and high-density lipoproteins. Compared to women, men were more likely to have a higher 10-year ASCVD risk score (14.0% vs. 17.8%, p = 0.005), and more men had a 10-year ASCVD risk score of ≥7.5% and ≥10%. The proportion of patients eligible for statin therapy was 80.2% based on the 2013 ACC/AHA guidelines and 59.5% based on the USPSTF guidelines. A higher proportion of men were eligible for statin therapy compared to women, based on both the 2013 ACC/AHA (81.4% vs. 73.5%, p = 0.050) and USPSTF guidelines (62.0% vs. 45.2%, p = 0.001). Among Middle Easterners, over half of patients with AMI would have been eligible for statin therapy prior to admission based on the 2013 ACC/AHA and USPSTF guidelines, with the presence of gender gap. Adopting these guidelines in clinical practice might positively impact primary cardiovascular preventive strategies in this region.

Normalization of Vitamin D Serum Levels in Patients with Type Two Diabetes Mellitus Reduces Levels of Branched Chain Amino Acids.

Background and Objectives: Vitamin D is involved in pancreatic beta-cell function, insulin sensitivity, and inflammation. Further, elevation in branched-chain amino acids (BCAAs) has been implicated in type 2 diabetes (T2DM) pathology. However, the relationship between vitamin D and BCAAs in T2DM remains unclear. The current study aimed to investigate the relationship between vitamin D and BCAAs in T2DM. Materials and Methods: In total, 230 participants (137 with T2DM and 93 healthy controls) were recruited in a cross-sectional study. Furthermore, an additional follow-up study was performed, including 20 T2DM patients with vitamin D deficiency. These patients were prescribed weekly vitamin D tablets (50,000 IU) for three months. The levels of several biochemical parameters were examined at the end of the vitamin D supplementation. Results: The results showed that patients with T2DM had higher serum levels of BCAAs and lower serum levels of 25-hydroxyvitamin D (25(OH)D) compared with those of the healthy controls (p < 0.01). The serum levels of vitamin D were negatively correlated with BCAA levels in T2DM patients (r = −0.1731, p < 0.05). In the follow-up study, 25(OH)D levels were significantly improved (p < 0.001) following vitamin D supplementation. Vitamin D supplementation significantly reduced the levels of BCAAs, HbA1c, total cholesterol, triglycerides, and fasting glucose (p < 0.01). Conclusion: Overall, these results suggest a role for BCAAs and vitamin D in the etiology and progression of T2DM. Thus, managing vitamin D deficiency in patients with T2DM may improve glycemic control and lower BCAA levels.