No abstract

IMPORTANCEThe Epic Sepsis Model (ESM), a proprietary sepsis prediction model, is implemented at hundreds of US hospitals. The ESM's ability to identify patients with sepsis has not been adequately evaluated despite widespread use.OBJECTIVE To externally validate the ESM in the prediction of sepsis and evaluate its potential clinical value compared with usual care. DESIGN, SETTING, AND PARTICIPANTSThis retrospective cohort study was conducted among 27 697 patients aged 18 years or older admitted to Michigan Medicine, the academic health system of the University of Michigan,

IMPORTANCE Black patients are overrepresented in the number of COVID-19 infections, hospitalizations, and deaths in the US. Reasons for this disparity may be due to underlying comorbidities or sociodemographic factors that require further exploration. OBJECTIVE To systematically determine patient characteristics associated with racial/ethnic disparities in COVID-19 outcomes. DESIGN, SETTING, AND PARTICIPANTS This retrospective cohort study used comparative groups of patients tested or treated for COVID-19 at the University of Michigan from March 10, 2020, to April 22, 2020, with an outcome update through July 28, 2020. A group of randomly selected untested individuals were included for comparison. Examined factors included race/ethnicity, age, smoking, alcohol consumption, comorbidities, body mass index (BMI; calculated as weight in kilograms divided by height in meters squared), and residential-level socioeconomic characteristics. EXPOSURE In-house polymerase chain reaction (PCR) tests, commercial antibody tests, nasopharynx or oropharynx PCR deployed by the Michigan Department of Health and Human Services and reverse transcription-PCR tests performed in external labs. MAIN OUTCOMES AND MEASURES The main outcomes were being tested for COVID-19, having test results positive for COVID-19 or being diagnosed with COVID-19, being hospitalized for COVID-19, requiring intensive care unit (ICU) admission for COVID-19, and COVID-19-related mortality (including inpatient and outpatient). Medical comorbidities were defined from the International Classification of Diseases, Ninth Revision, and International Classification of Diseases, Tenth Revision, codes and were aggregated into a comorbidity score. Associations with COVID-19 outcomes were examined using odds ratios (ORs). RESULTS Of 5698 patients tested for COVID-19 (mean [SD] age, 47.4 [20.9] years; 2167 [38.0%] men; mean [SD] BMI, 30.0 [8.0]), most were non-Hispanic White (3740 patients [65.6%]) or non-Hispanic Black (1058 patients [18.6%]). The comparison group included 7168 individuals who were not tested (mean [SD] age, 43.1 [24.1] years; 3257 [45.4%] men; mean [SD] BMI, 28.5 [7.1]). Among 1139 patients diagnosed with COVID-19, 492 (43.2%) were White and 442 (38.8%) were Black; 523 (45.9%) were hospitalized, 283 (24.7%) were admitted to the ICU, and 88 (7.7%) died. Adjusting for age, sex, socioeconomic status, and comorbidity score, Black patients were more likely to be hospitalized compared with White patients (OR, 1.72 [95% CI, 1.15-2.58]; P = .009). In addition to older age, male sex, and obesity, living in densely populated areas was associated with increased risk of hospitalization (OR, 1.10 [95% CI, 1.01-1.19]; P = .02). In the overall population, higher risk of hospitalization was also observed in patients with preexisting type 2 diabetes (OR, 1.82 [95% CI, 1.25-2.64]; P = .02) and kidney disease (OR, 2.87 [95% CI, 1.87-4.42]; P < .001). Compared with White (continued) Key Points Question What sociodemographic and underlying health conditions are associated w...

No abstract

BACKGROUND:Mobile applications or 'apps' intended to help people manage their health and chronic conditions are widespread and gaining in popularity. However, little is known about their acceptability and usability for lowincome, racially/ethnically diverse populations who experience a disproportionate burden of chronic disease and its complications. OBJECTIVE: The objective of this study was to investigate the usability of existing mobile health applications ("apps") for diabetes, depression, and caregiving, in order to facilitate development and tailoring of patient-facing apps for diverse populations. DESIGN: Usability testing, a mixed-methods approach that includes interviewing and direct observation of participant technology use, was conducted with participants (n = 9 caregivers; n = 10 patients with depression; and n = 10 patients with diabetes) on a total of 11 of the most popular health apps (four diabetes apps, four depression apps, and three caregiver apps) on both iPad and Android tablets. PARTICIPANTS: The participants were diverse: 15 (58 %) African Americans, seven (27 %) Whites, two (8 %) Asians, two (8 %) Latinos with either diabetes, depression, or who were caregivers. MAIN MEASURES: Participants were given conditionspecific tasks, such as entering a blood glucose value into a diabetes app. Participant interviews were video recorded and were coded using standard methods to evaluate attempts and completions of tasks. We performed inductive coding of participant comments to identify emergent themes. KEY RESULTS: Participants completed 79 of 185 (43 %) tasks across 11 apps without assistance. Three themes emerged from participant comments: lack of confidence with technology, frustration with design features and navigation, and interest in having technology to support their self-management.CONCLUSIONS: App developers should employ participatory design strategies in order to have an impact on chronic conditions such as diabetes and depression that disproportionately affect vulnerable populations. While patients express interest in using technologies for selfmanagement, current tools are not consistently usable for diverse patients.

With rising smartphone ownership, mobile health applications (mHealth apps) have the potential to support high-need, high-cost populations in managing their health. While the number of available mHealth apps has grown substantially, no clear strategy has emerged on how providers should evaluate and recommend such apps to patients. Key stakeholders, including medical professional societies, insurers, and policy makers, have largely avoided formally recommending apps, which forces patients to obtain recommendations from other sources. To help stakeholders overcome barriers to reviewing and recommending apps, we evaluated 137 patient-facing mHealth apps-those intended for use by patients to manage their health-that were highly rated by consumers and recommended by experts and that targeted high-need, high-cost populations. We found that there is a wide variety of apps in the marketplace but that few apps address the needs of the patients who could benefit the most. We also found that consumers' ratings were poor indications of apps' clinical utility or usability and that most apps did not respond appropriately when a user entered potentially dangerous health information. Going forward, data privacy and security will continue to be major concerns in the dissemination of mHealth apps.

Objective To provide focused evaluation of predictive modeling of electronic medical record (EMR) data to predict 30 day hospital readmission. Design Systematic review. Data source Ovid Medline, Ovid Embase, CINAHL, Web of Science, and Scopus from January 2015 to January 2019. Eligibility criteria for selecting studies All studies of predictive models for 28 day or 30 day hospital readmission that used EMR data. Outcome measures Characteristics of included studies, methods of prediction, predictive features, and performance of predictive models. Results Of 4442 citations reviewed, 41 studies met the inclusion criteria. Seventeen models predicted risk of readmission for all patients and 24 developed predictions for patient specific populations, with 13 of those being developed for patients with heart conditions. Except for two studies from the UK and Israel, all were from the US. The total sample size for each model ranged between 349 and 1 195 640. Twenty five models used a split sample validation technique. Seventeen of 41 studies reported C statistics of 0.75 or greater. Fifteen models used calibration techniques to further refine the model. Using EMR data enabled final predictive models to use a wide variety of clinical measures such as laboratory results and vital signs; however, use of socioeconomic features or functional status was rare. Using natural language processing, three models were able to extract relevant psychosocial features, which substantially improved their predictions. Twenty six studies used logistic or Cox regression models, and the rest used machine learning methods. No statistically significant difference (difference 0.03, 95% confidence interval −0.0 to 0.07) was found between average C statistics of models developed using regression methods (0.71, 0.68 to 0.73) and machine learning (0.74, 0.71 to 0.77). Conclusions On average, prediction models using EMR data have better predictive performance than those using administrative data. However, this improvement remains modest. Most of the studies examined lacked inclusion of socioeconomic features, failed to calibrate the models, neglected to conduct rigorous diagnostic testing, and did not discuss clinical impact.

he prospect of improved clinical outcomes and more efficient health systems has fueled a rapid rise in the development and evaluation of AI systems over the last decade. Because most AI systems within healthcare are complex interventions designed as clinical decision support systems, rather than autonomous agents, the interactions among the AI systems, their users and the implementation environments are defining components of the AI interventions' overall potential effectiveness. Therefore, bringing AI systems from mathematical performance to clinical utility needs an adapted, stepwise implementation and evaluation pathway, addressing the complexity of this collaboration between two independent forms of intelligence, beyond measures of effectiveness alone 1 . Despite indications that some AI-based algorithms now match the accuracy of human experts within preclinical in silico studies 2 , there