Application of a time-series deep learning model to predict cardiac dysrhythmias in electronic health records.

BACKGROUND: Cardiac dysrhythmias (CD) affect millions of Americans in the United States (US), and are associated with considerable morbidity and mortality. New strategies to combat this growing problem are urgently needed. OBJECTIVES: Predicting CD using electronic health record (EHR) data would allow for earlier diagnosis and treatment of the condition, thus improving overall cardiovascular outcomes. The Guideline Advantage (TGA) is an American Heart Association ambulatory quality clinical data registry of EHR data representing 70 clinics distributed throughout the US, and has been used to monitor outpatient prevention and disease management outcome measures across populations and for longitudinal research on the impact of preventative care. METHODS: For this study, we represented all time-series cardiovascular health (CVH) measures and the corresponding data collection time points for each patient by numerical embedding vectors. We then employed a deep learning technique-long-short term memory (LSTM) model-to predict CD from the vector of time-series CVH measures by 5-fold cross validation and compared the performance of this model to the results of deep neural networks, logistic regression, random forest, and Naïve Bayes models. RESULTS: We demonstrated that the LSTM model outperformed other traditional machine learning models and achieved the best prediction performance as measured by the average area under the receiver operator curve (AUROC): 0.76 for LSTM, 0.71 for deep neural networks, 0.66 for logistic regression, 0.67 for random forest, and 0.59 for Naïve Bayes. The most influential feature from the LSTM model were blood pressure. CONCLUSIONS: These findings may be used to prevent CD in the outpatient setting by encouraging appropriate surveillance and management of CVH.

Time-series cardiovascular risk factors and receipt of screening for breast, cervical, and colon cancer: The Guideline Advantage.

BACKGROUND: Cancer is the second leading cause of death in the United States. Cancer screenings can detect precancerous cells and allow for earlier diagnosis and treatment. Our purpose was to better understand risk factors for cancer screenings and assess the effect of cancer screenings on changes of Cardiovascular health (CVH) measures before and after cancer screenings among patients. METHODS: We used The Guideline Advantage (TGA)-American Heart Association ambulatory quality clinical data registry of electronic health record data (n = 362,533 patients) to investigate associations between time-series CVH measures and receipt of breast, cervical, and colon cancer screenings. Long short-term memory (LSTM) neural networks was employed to predict receipt of cancer screenings. We also compared the distributions of CVH factors between patients who received cancer screenings and those who did not. Finally, we examined and quantified changes in CVH measures among the screened and non-screened groups. RESULTS: Model performance was evaluated by the area under the receiver operator curve (AUROC): the average AUROC of 10 curves was 0.63 for breast, 0.70 for cervical, and 0.61 for colon cancer screening. Distribution comparison found that screened patients had a higher prevalence of poor CVH categories. CVH submetrics were improved for patients after cancer screenings. CONCLUSION: Deep learning algorithm could be used to investigate the associations between time-series CVH measures and cancer screenings in an ambulatory population. Patients with more adverse CVH profiles tend to be screened for cancers, and cancer screening may also prompt favorable changes in CVH. Cancer screenings may increase patient CVH health, thus potentially decreasing burden of disease and costs for the health system (e.g., cardiovascular diseases and cancers).

Determinants of Potentially Unnecessary Cervical Cancer Screenings in American Women.

OBJECTIVES: To identify factors responsible for potentially clinically unnecessary cervical cancer screenings in women with prior hysterectomy. METHODS: A retrospective cross-sectional study was conducted using the Centers for Disease Control and Prevention's Behavioral Risk Factor Surveillance System (BRFSS). This study targeted adult women and examined whether they received a both a Papanicolaou (Pap) test and undergone a hysterectomy in the last three years. We conducted multivariate analyses, including weighted proportions and odds ratios (ORs), based on the modified BRFSS weighting method (raking). The inclusion criteria were adult women (>18 years old) who reported having received a Pap test within the last 3 years. RESULTS: Of all women (n=252 391), 72 366 had received a Pap test, and 32 935 of those women (45%, or 12.5 million, weighted) had a prior hysterectomy. We found that age, race/ethnicity, marital status, family income, health status, time since last routine checkup, and health insurance coverage were all significant predictors. Black, non-Hispanic women were 2.23 times more likely to receive Pap testing after a hysterectomy than white women (OR, 2.23; 95% confidence interval [CI], 1.99 to 2.50). Similarly, the odds for Hispanic women were 2.34 times higher (OR, 2.34; 95% CI, 1.97 to 2.80). The odds were also higher for those who were married (OR, 1.17; 95% CI, 1.08 to 1.27), healthier (OR, 1.24; 95% CI, 1.14 to 1.35), and had health insurance (OR, 1.54; 95% CI, 1.28 to 1.84), after controlling for confounders. CONCLUSIONS: We conclude that women may potentially receive Pap tests even if they are not at risk for cervical cancer, and may not be adequately informed about the need for screenings. We recommend strategies to disseminate recommendations and information to patients, their families, and care providers.

Demographic and Survivorship Disparities in Non-muscle-invasive Bladder Cancer in the United States.

OBJECTIVES: To examine survivorship disparities in demographic factors and risk status for non-muscle-invasive bladder cancer (NMIBC), which accounts for more than 75% of all urinary bladder cancers, but is highly curable with early identification and treatment. METHODS: We used the US National Cancer Institute's Surveillance, Epidemiology, and End Results registries over a 19-year period (1988-2006) to examine survivorship disparities in age, sex, race/ethnicity, and marital status of patients and risk status classified by histologic grade, stage, size of tumor, and number of multiple primary tumors among NMIBC patients (n=29 326). We applied Kaplan-Meier (K-M) and Cox proportional hazard methods for survival analysis. RESULTS: Among all urinary bladder cancer patients, the majority of NMIBCs were in male (74.1%), non-Latino white (86.7%), married (67.8%), and low-risk (37.6%) to intermediate-risk (44.8%) patients. The mean age was 68 years. Survivorship (in median life years) was highest for non-Latino white (5.4 years), married (5.4 years), and low-risk (5.7 years) patients (K-M analysis, p<0.001). We found significantly lower survivorship for elderly, male (female hazard ratio [HR], 0.96), Latino (HR, 1.20), and unmarried (married HR, 0.93) patients. CONCLUSIONS: Survivorship disparities were ubiquitous across age, sex, race/ethnicity, and marital status groups. Non-white, unmarried, and elderly patients had significantly shorter survivorship. The implications of these findings include the need for a heightened focus on health policy and more organized efforts to improve access to care in order to increase the chances of survival for all patients.