Quasi-experimental study designs, often described as nonrandomized, pre-post intervention studies, are common in the medical informatics literature. Yet little has been written about the benefits and limitations of the quasi-experimental approach as applied to informatics studies. This paper outlines a relative hierarchy and nomenclature of quasi-experimental study designs that is applicable to medical informatics intervention studies. In addition, the authors performed a systematic review of two medical informatics journals, the Journal of the American Medical Informatics Association (JAMIA) and the International Journal of Medical Informatics (IJMI), to determine the number of quasi-experimental studies published and how the studies are classified on the above-mentioned relative hierarchy. They hope that future medical informatics studies will implement higher level quasi-experimental study designs that yield more convincing evidence for causal links between medical informatics interventions and outcomes.

Background COVID-19 has infected millions of people worldwide and is responsible for several hundred thousand fatalities. The COVID-19 pandemic has necessitated thoughtful resource allocation and early identification of high-risk patients. However, effective methods to meet these needs are lacking. Objective The aims of this study were to analyze the electronic health records (EHRs) of patients who tested positive for COVID-19 and were admitted to hospitals in the Mount Sinai Health System in New York City; to develop machine learning models for making predictions about the hospital course of the patients over clinically meaningful time horizons based on patient characteristics at admission; and to assess the performance of these models at multiple hospitals and time points. Methods We used Extreme Gradient Boosting (XGBoost) and baseline comparator models to predict in-hospital mortality and critical events at time windows of 3, 5, 7, and 10 days from admission. Our study population included harmonized EHR data from five hospitals in New York City for 4098 COVID-19–positive patients admitted from March 15 to May 22, 2020. The models were first trained on patients from a single hospital (n=1514) before or on May 1, externally validated on patients from four other hospitals (n=2201) before or on May 1, and prospectively validated on all patients after May 1 (n=383). Finally, we established model interpretability to identify and rank variables that drive model predictions. Results Upon cross-validation, the XGBoost classifier outperformed baseline models, with an area under the receiver operating characteristic curve (AUC-ROC) for mortality of 0.89 at 3 days, 0.85 at 5 and 7 days, and 0.84 at 10 days. XGBoost also performed well for critical event prediction, with an AUC-ROC of 0.80 at 3 days, 0.79 at 5 days, 0.80 at 7 days, and 0.81 at 10 days. In external validation, XGBoost achieved an AUC-ROC of 0.88 at 3 days, 0.86 at 5 days, 0.86 at 7 days, and 0.84 at 10 days for mortality prediction. Similarly, the unimputed XGBoost model achieved an AUC-ROC of 0.78 at 3 days, 0.79 at 5 days, 0.80 at 7 days, and 0.81 at 10 days. Trends in performance on prospective validation sets were similar. At 7 days, acute kidney injury on admission, elevated LDH, tachypnea, and hyperglycemia were the strongest drivers of critical event prediction, while higher age, anion gap, and C-reactive protein were the strongest drivers of mortality prediction. Conclusions We externally and prospectively trained and validated machine learning models for mortality and critical events for patients with COVID-19 at different time horizons. These models identified at-risk patients and uncovered underlying relationships that predicted outcomes.

IMPORTANCEThe National COVID Cohort Collaborative (N3C) is a centralized, harmonized, highgranularity electronic health record repository that is the largest, most representative COVID-19 cohort to date. This multicenter data set can support robust evidence-based development of predictive and diagnostic tools and inform clinical care and policy.OBJECTIVES To evaluate COVID-19 severity and risk factors over time and assess the use of machine learning to predict clinical severity. DESIGN, SETTING, AND PARTICIPANTSIn a retrospective cohort study of 1 926 526 US adults with SARS-CoV-2 infection (polymerase chain reaction >99% or antigen <1%) and adult patients without SARS-CoV-2 infection who served as controls from 34 medical centers nationwide between January 1, 2020, and December 7, 2020, patients were stratified using a World Health Organization COVID-19 severity scale and demographic characteristics. Differences between groups over time were evaluated using multivariable logistic regression. Random forest and XGBoost models were used to predict severe clinical course (death, discharge to hospice, invasive ventilatory support, or extracorporeal membrane oxygenation). MAIN OUTCOMES AND MEASURESPatient demographic characteristics and COVID-19 severity using the World Health Organization COVID-19 severity scale and differences between groups over time using multivariable logistic regression. RESULTSThe cohort included 174 568 adults who tested positive for SARS-CoV-2 (mean [SD] age, 44.4 [18.6] years; 53.2% female) and 1 133 848 adult controls who tested negative for SARS-CoV-2 (mean [SD] age, 49.5 [19.2] years; 57.1% female). Of the 174 568 adults with SARS-CoV-2, 32 472(18.6%) were hospitalized, and 6565 (20.2%) of those had a severe clinical course (invasive ventilatory support, extracorporeal membrane oxygenation, death, or discharge to hospice). Of the hospitalized patients, mortality was 11.6% overall and decreased from 16.4% in March to April 2020 to 8.6% in September to October 2020 (P = .002 for monthly trend). Using 64 inputs available on the first hospital day, this study predicted a severe clinical course using random forest and XGBoost models (area under the receiver operating curve = 0.87 for both) that were stable over time. The factor most strongly associated with clinical severity was pH; this result was consistent across machine learning methods. In a separate multivariable logistic regression model built for inference, (continued) Key Points Question In a US data resource large enough to adjust for multiple confounders, what risk factors are associated with COVID-19 severity and severity trajectory over time, and can machine learning models predict clinical severity? Findings In this cohort study of 174 568 adults with SARS-CoV-2, 32 472 (18.6%) were hospitalized and 6565 (20.2%) were severely ill, and first-day machine learning models accurately predicted clinical severity. Mortality was 11.6%

Rationale:Recent studies described association between chronic obstructive pulmonary disease (COPD) and increased risk of cardiovascular diseases (CVD). In their analysis none of these studies accounted for sociodemographic factors, health behaviors, and patient comorbidities simultaneously.Objective:To study whether COPD diagnosis is an independent risk factor for CVD.Methods:Subjects aged 40 years and older (N = 18,342) from the sample adult file of the 2002 National Health Interview Survey (NHIS) were included in the analysis. Chi-squared tests and odds ratios (OR) were utilized to compare the data. Multiple logistic regression was employed to analyze the association between COPD and CVD with simultaneous control for sociodemographic factors (age, gender, race, marital status, education, income), health behaviors (tobacco use, alcohol consumption, physical activity), and patient comorbidities (diabetes, hypertension, high cholesterol, and obesity). The analysis employed NHIS sampling weights to generate data representative of the entire US population.Results:The COPD population had increased prevalence of CVD (56.5% vs 25.6%; P < 0.0001). Adjusted logistic regression showed that COPD patients (N = 958) were at higher risk of having coronary heart disease (OR = 2.0, 95% CI: 1.5–2.5), angina (OR = 2.1, 95% CI: 1.6–2.7), myocardial infarction (OR = 2.2, 95% CI: 1.7–2.8), stroke (OR = 1.5, 95% CI: 1.1–2.1), congestive heart failure (OR = 3.9, 95% CI: 2.8–5.5), poor circulation in lower extremities (OR = 2.5, 95% CI: 2.0–3.0), and arrhythmia (OR = 2.4, 95% CI: 2.0–2.8). Overall, the presence of COPD increased the odds of having CVD by a factor of 2.7 (95% CI: 2.3–3.2).Conclusions:These findings support the conclusion that COPD is an independent risk factor for CVD.

Introduction Outcomes are suboptimal in ulcerative colitis (UC). Telemedicine for UC is feasible and improves outcomes. Our goals were to evaluate a home telemanagement system for UC (UC HAT) on disease activity, quality of life (QoL), and adherence compared to best available care (BAC) in a randomized, controlled trial. Materials and Methods Adults with UC were randomly assigned to receive UC HAT or BAC for 12 months. UC HAT recruits answered questions regarding disease activity, adherence, side effects, and measured their weight weekly. An educational curriculum was delivered after each session. Alerts and action plans were generated based on the results. BAC underwent routine follow up, received written action plans and were given educational fact sheets. Seo Index scores, IBDQ scores, and adherence rates were compared between UC HAT and BAC at one year. Results 25 patients were randomized to UC HAT and 22 to BAC. After 12 months, 11 withdrew in UC HAT compared to 5 in BAC. Disease activity, QoL, and adherence were not different between groups at any time point post baseline. Adjusted analyses of trial completers using all available data, demonstrated decreased Seo index (11.9 in UC HAT (p=0.08) vs. 1.2 in BAC (p=0.84) and increased IBDQ scores (12.5 in UC HAT (p=0.04) vs. to −3.8 in BAC (p=0.47) from baseline in UC HAT compared to BAC. Discussion UC HAT did not improve disease activity, QoL or adherence compared to BAC after 1 year. After adjustment for baseline disease knowledge, UC HAT trial completers experienced significant gains in disease-specific quality of life from baseline compared to BAC trial completers. Our results suggest a potential benefit of UC HAT. Further research is indicated to determine if telemedicine improves outcomes in patients with IBD.

Objectives:We assessed peri-implantitis prevalence, incidence rate, and associated risk factors by analyzing electronic oral health records (EHRs) in an educational institution. Methods:We used a validated reference cohort comprising all patients receiving dental implants over a 3.5-year period (2,127 patients and 6,129 implants). Electronic oral health records of a random 10% subset were examined for an additional followup of ≥2.5 years to assess the presence of radiographic bone loss, defined as >2 mm longitudinal increase in the distance between the implant shoulder and the supporting peri-implant bone level (PBL) between time of placement and follow-up. "Intact" implants had no or ≤2 mm PBL increase from baseline. Electronic oral health record notes were reviewed to corroborate a definitive peri-implantitis diagnosis at implants with progressive bone loss. A nested case-control analysis of peri-implantitis-affected implants randomly matched by age with "intact" implants from peri-implantitis-free individuals identified putative risk factors. Results:The prevalence of peri-implantitis over an average follow-up of 2 years was 34% on the patient level and 21% on the implant level. Corresponding incidence rates were 0.16 and 0.10 per patient-year and implant-year, respectively. Multiple conditional logistic regression identified ill-fitting fixed prosthesis (OR = 5.9; 95% CI: 1.6-21.1), cement-retained prosthesis (OR = 4.5; 2.1-9.5), and radiographic evidence of periodontitis (OR = 3.6; 1.7-7.6) as statistically associated with peri-implantitis. Implant location in the mandible (OR = 0.02; 0.003-0.2) and use of antibiotics in conjunction with implant surgery (OR = 0.19; 0.05-0.7) emerged as protective exposures.Conclusions: Approximately 1/3 of the patients and 1/5 of all implants experienced peri-implantitis. Ill-fitting/ill-designed fixed and cement-retained restorations, and history of periodontitis emerged as the principal risk factors for peri-implantitis. K E Y W O R D S epidemiology, periodontology, soft tissue-implant interactions | 307 KORDBACHEH CHANGI Et Al.

Patient telemonitoring results in an aggregation of significant amounts of information about patient disease trajectory. However, the potential use of this information for early prediction of exacerbations in adult asthma patients has not been systematically evaluated. The aim of this study was to explore the utility of telemonitoring data for building machine learning algorithms that predict asthma exacerbations before they occur. The study dataset comprised daily self-monitoring reports consisting of 7001 records submitted by adult asthma patients during home telemonitoring. Predictive modeling included preparation of stratified training data sets, predictive feature selection, and evaluation of resulting classifiers. Using a 7-day window, a naive Bayesian classifier, adaptive Bayesian network, and support vector machines were able to predict asthma exacerbation occurring on day 8, with sensitivity of 0.80, 1.00, and 0.84; specificity of 0.77, 1.00, and 0.80; and accuracy of 0.77, 1.00, and 0.80, respectively. Our study demonstrated that machine learning techniques have significant potential in developing personalized decision support for chronic disease telemonitoring systems. Future studies may benefit from a comprehensive predictive framework that combines telemonitoring data with other factors affecting the likelihood of developing acute exacerbation. Approaches implemented for advanced asthma exacerbation prediction may be extended to prediction of exacerbations in patients with other chronic health conditions.

No abstract