Purpose: Electrocardiography (ECG)-derived machine learning models can predict echocardiography (echo)-derived indices of systolic or diastolic function. However, systolic and diastolic dysfunction frequently coexists, which necessitates an integrated assessment for optimal risk-stratification. We explored an ECG-derived model that emulates an echo-derived model that combines multiple parameters for identifying patient phenogroups at risk for major adverse cardiac events (MACE).
Methods: In this substudy of a prospective, multicenter study, patients from 3 institutions (n=727) formed an internal cohort, and the fourth institution was reserved as an external test set (n=518). A previously validated patient similarity analysis model was used for labeling the patients as low-/high-risk phenogroups. These labels were utilized for training an ECG-derived deep neural network model to predict MACE risk per phenogroup. After 5-fold cross-validation training, the model was tested on the reserved external dataset.
Results: Our ECG-derived model showed robust classification of patients, with area under the receiver operating characteristic curve of 0.86 (95% CI: 0.79-0.91) and 0.84 (95% CI: 0.80-0.87), sensitivity of 80% and 76%, and specificity of 88% and 75% for the internal and external test sets, respectively. The ECG-derived model demonstrated an increased probability for MACE in high-risk vs low-risk patients (21% vs 3%; P<0.001), which was similar to the echo-trained model (21% vs 5%; P<0.001), suggesting comparable utility.
Conclusions: This novel ECG-derived machine learning model provides a cost-effective strategy for predicting patient subgroups in whom an integrated milieu of systolic and diastolic dysfunction is associated with a high risk of MACE.
Purpose: There has been increasing interest in patient-reported experience measures (PREMs) to evaluate the patient experience and satisfaction with care. We conducted a prospective multicenter cohort study to determine any association between patients' satisfaction of care and their outcomes 1 year after lumbar spine surgery.
Methods: Satisfaction with care was recorded through telephone interviews and a standardized questionnaire. Baseline data collection (300 patients) and 1-year follow-up (209 patients) were conducted through The Swedish National Register for Spine Surgery (Swespine). Exposures were patient experiences, health care professional (HCP) attitudes, shared decision-making, and overall satisfaction with care. Associations were evaluated using adjusted analysis of covariance (ANCOVA) models.
Results: Satisfaction with HCP attitudes was not associated with improvements at 1 year in Oswestry Disability Index (ODI) or back pain; however a significantly greater improvement in leg pain score was reported by patients who were highly satisfied (3.0 points) versus the moderate/low satisfaction group (1.3 points; P=0.008). For shared decision-making, high satisfaction was associated with significantly greater improvements, as compared to moderate/low satisfaction, in ODI (20 vs 11 points; P=0.001), back pain (2.6 vs 1.7 points; P=0.05), and leg pain (3.2 vs 1.9 points, P=0.007). Similarly, high overall satisfaction with care was associated with significantly greater improvements in ODI (18 vs 10 points; P=0.02), back pain (3.2 vs 0.6 points; P<0.001), and leg pain (2.6 vs 1.1 points; P=0.009).
Conclusions: Findings indicate that shared decision-making on perioperative care and patients' overall satisfaction with care were associated with better health outcomes 1 year after lumbar spine surgery.
Purpose: Up to 74% of breast cancer survivors (BCS) have at least one preexisting comorbid condition, with diabetes (type 2) common. The purpose of this study was to examine differences in health-related outcomes (anemia, neutropenia, and infection) and utilization of health care resources (inpatient, outpatient, and emergency visits) in BCS with and without diabetes.
Methods: In this retrospective cohort study, data were leveraged from the electronic health records of a large health network linked to the Indiana State Cancer Registry. BCS diagnosed between January 2007 and December 2017 and who had received chemotherapy were included. Multivariable logistic regression and generalized linear models were used to determine differences in health outcomes and health care resources.
Results: The cohort included 6851 BCS, of whom 1121 (16%) had a diagnosis of diabetes. BCS were, on average, 55 (standard deviation: 11.88) years old, the majority self-reported race as White (90%), and 48.8% had stage II breast cancer. BCS with diabetes were significantly older (mean age of 60.6 [SD: 10.34] years) than those without diabetes and were often obese (66% had body mass index of ≥33). BCS with diabetes had higher odds of anemia (odds ratio: 1.43; 95% CI: 1.04, 1.96) and infection (odds ratio: 1.86; 95% CI: 1.35, 2.55) and utilized more outpatient resources (P<0.0001).
Conclusions: Diabetes has a deleterious effect on health-related outcomes and health care resource utilization among BCS. These findings support the need for clinical practice guidelines to help clinicians manage diabetes among BCS throughout the cancer trajectory and for coordinated models of care to reduce high resource utilization.
Findings from a recent study describing prevalence of common disease conditions in the largest documented cohort of individuals with Down syndrome (DS) in the United States strongly suggested significant disparity in endocrine disorders among these individuals when compared with age- and sex-matched individuals without DS. This retrospective, descriptive study is a follow-up report documenting prevalence of 21 endocrine disorder conditions, across 28 years of data, from 6078 individuals with DS and 30,326 age- and sex-matched controls, abstracted from electronic medical records within a large integrated health system. Overall, individuals with DS experienced higher prevalence of adrenal insufficiency and Addison's disease; thyroid disorders, including hypothyroidism, hyperthyroidism, Hashimoto's disease, and Graves' disease; prolactinoma/hyperprolactinemia; diabetes insipidus; type I diabetes mellitus; and gout. Conversely, those with DS had lower prevalence of polycystic ovary syndrome and type II diabetes mellitus. Many prevalences of endocrine conditions seen in individuals with DS significantly differ relative to their non-DS matched counterparts. These varied findings warrant further exploration into how screening for and treatment of endocrine conditions may need to be approached differently for individuals with DS.
Purpose: Medical trainees are likely at differential risk of exposure to COVID-19 per respective clinical activity. We sought to determine the seroprevalence of COVID-19 antibody (Ab) among resident and fellow physicians with varying degrees of exposure to COVID-19.
Methods: A cross-sectional study of Milwaukee-based resident and fellow physicians, encompassing December 2019-June 2020, was conducted. Relevant variables of interest were ascertained by survey and payroll data, and Abbott ARCHITECT Ab test (index cut-off of ≥1.4) was performed. Descriptive statistics were generated, with 95% CI calculated for the study's primary outcome of seroprevalence.
Results: Among survey respondents (92 of 148, 62%), 61% were male, 44% were non-White, mean age was 31 years, 94% had no underlying conditions, and 52% were either family or internal medicine residents. During the study period, ≥32% reported cough, headache, or sore throat and 62% traveled outside of Wisconsin. Overall, 83% thought they had a COVID-19 exposure at work and 33% outside of work; 100% expressed any exposure. Of those exposed at work, 56% received COVID-19 pay, variously receiving 69 mean hours (range: 0-452). Ultimately, 82% (75 of 92) had an Ab test completed; 1 individual (1.3%; 95% CI: 0.0-3.9) tested seropositive, was not previously diagnosed, and had received COVID-19 pay.
Conclusions: The low Ab seroprevalence found in resident and fellow physicians was similar to the concurrently reported 3.7% Ab-positive rate among 2456 Milwaukee-based staff in the same integrated health system. Ultimately, COVID-19 seroconversion may be nominal in properly protected resident and fellow physicians despite known potential exposures.