Novel Generative Recurrent Neural Network Framework to Produce Accurate, Applicable, and Deidentified Synthetic Medical Data for Patients With Metastatic Cancer.

PURPOSE: Sensitive patient data cannot be easily shared/analyzed, severely limiting the innovative progress of research, specifically for marginalized/under-represented populations. Existing methods of deidentification are subject to data breaches. The objective of this study was to develop a neural network capable of generating a synthetic version of data for patients with novel postoperative metastatic cancer. METHODS: We analyzed a metastatic cancer patient cohort of 167,474 patients obtained from the National Surgical Quality Improvement Program. Twenty-seven clinical features were analyzed. We created a volume-matched synthetic cohort of 167,474 patients and a reduced-size synthetic cohort of 5,000 patients. The volume-matched and reduced-size synthetic cohorts were compared against the ground truth data to analyze differences in principal component distribution, underlying statistical properties/associations, intervariable correlations, and machine learning classifier performance when developed on the synthetic data. RESULTS: Among 167,474 patients with metastatic cancer in the original data, 50,669 (30.3%) died within 30 days of their index surgery. Our model was able to accurately capture underlying statistical properties, principal components, and intervariable correlations within the ground truth data, yielding an accuracy of 93.2% with a loss of 0.21%, and develop synthetic data capable of training accurate machine learning classifiers. The reduced-size synthetic data accurately replicated all categorical variables and every continuous variable with statistically similar records (P > .05), with the sole exception of preoperative albumin (P < .05). The volume-matched synthetic data frame was able to accurately replicate all categorical variables (P > .05). CONCLUSION: This described methodology can be applied to any structured medical data from any setting, significantly expedite scientific analysis/innovation, and be used to develop improved predictive classifiers with boosted tree-based algorithms, serving as the potential new gold standard of medical data sharing and data augmentation.

Machine learning models to prognose 30-Day Mortality in Postoperative Disseminated Cancer Patients.

Patients with disseminated cancer at higher risk for postoperative mortality see improved outcomes with altered clinical management. Being able to risk stratify patients immediately after their index surgery to flag high risk patients for healthcare providers is vital. The combination of physician uncertainty and a demonstrated optimism bias often lead to an overestimation of patient life expectancy which can precent proper end of life counseling and lead to inadequate postoperative follow up. In this cohort study of 167,474 postoperative patients with multiple types of disseminated cancer, patients at high risk of 30-day postoperative mortality were accurately identified using our machine learning models based solely on clinical features and preoperative lab values. Extreme Gradient Boosting, Random Forest, and Logistic Regression machine learning models were developed on the cohort. Among 167,474 disseminated cancer patients, 50,669 (30.3%) died within 30 days of their index surgery; After preprocessing, 28 features were included in the model development. The cohort was randomly divided into 133,979 patients (80%) for training the models and 33,495 patients (20%) for testing. The extreme gradient boosting model had an AUC of 0.93 (95% CI: 0.926-0.931), the random forest model had an AUC of 0.93 (95% CI: 0.930-0.934), and the logistic regression model had an AUC of 0.90 (95% CI: 0.900-0.906 the index operation. Ultimately, Machine learning models were able to accurately predict short-term postoperative mortality among a heterogenous population of disseminated cancer patients using commonly accessible medical features. These models can be included in electronic health systems to guide clinical judgements that affect direct patient care, particularly in low-resource settings.

Machine learning methods to predict presence of residual cancer following hysterectomy.

Surgical management for gynecologic malignancies often involves hysterectomy, often constituting the most common gynecologic surgery worldwide. Despite maximal surgical and medical care, gynecologic malignancies have a high rate of recurrence following surgery. Current machine learning models use advanced pathology data that is often inaccessible within low-resource settings and are specific to singular cancer types. There is currently a need for machine learning models to predict non-clinically evident residual disease using only clinically available health data. Here we developed and tested multiple machine learning models to assess the risk of residual disease post-hysterectomy based on clinical and operative parameters. Data from 3656 hysterectomy patients from the NSQIP dataset over 14 years were used to develop models with a training set of 2925 patients and a validation set of 731 patients. Our models revealed the top postoperative predictors of residual disease were the initial presence of gross abdominal disease on the diaphragm, disease located on the bowel mesentery, located on the bowel serosa, and disease located within the adjacent pelvis prior to resection. There were no statistically significant differences in performances of the top three models. Extreme gradient Boosting, Random Forest, and Logistic Regression models had comparable AUC ROC (0.90) and accuracy metrics (87-88%). Using these models, physicians can identify gynecologic cancer patients post-hysterectomy that may benefit from additional treatment. For patients at high risk for disease recurrence despite adequate surgical intervention, machine learning models may lay the basis for potential prospective trials with prophylactic/adjuvant therapy for non-clinically evident residual disease, particularly in under-resourced settings.

Emergency Absentee Voting for Hospitalized Patients and Voting During COVID-19: A 50-State Study.

INTRODUCTION: Voters facing illness or disability are disproportionately under-represented in terms of voter turnout. Earlier research has indicated that enfranchisement of these populations may reinforce the implementation of policies improving health outcomes and equity. Due to the confluence of the coronavirus 2019 (COVID-19) pandemic and the 2020 election, we aimed to assess emergency absentee voting processes, which allow voters hospitalized after regular absentee deadlines to still obtain an absentee ballot, and election changes due to COVID-19 in all 50 states. METHODS: We performed a cross-sectional study collecting 34 variables pertaining to emergency voting processes and COVID-19-related election changes, including deadlines, methods of submission for applications and ballots, and specialized services for patients. Data were obtained from, in order of priority, state boards of elections websites, poll worker manuals, application forms, and state legislation. We verified all data through direct correspondence with state boards of elections. RESULTS: Emergency absentee voting processes are in place in 39 states, with the remaining states having universal vote-by-mail (n = 5) or extended regular absentee voting deadlines (n = 6). The emergency absentee period most commonly began within 24 hours following the normal absentee application deadline, which was often seven days before an election (n = 11). Unique aspects of emergency voting processes included patients designating an "authorized agent" to deliver their applications and ballots (n = 38), electronic ballot delivery (n = 5), and in-person teams that deliver ballots directly to patients (n = 18). Documented barriers in these processes nationwide include unavailable online information (n = 11), restrictions mandating agents to be family members (n = 7), physician affidavits or signatures (n = 9), and notary or witness signature requirements (n = 15). For the November 2020 presidential election, 12 states expanded absentee eligibility to allow COVID-19 as a reason to request an absentee ballot, and 18 states mailed absentee ballot applications or absentee ballots to all registered voters. CONCLUSION: While 39 states operate emergency absentee voting processes for hospitalized voters, there are considerable areas for improvement and heterogeneity in guidelines for these protocols. For future election cycles, information on emergency voting and broader election reforms due to COVID-19 may be useful for emergency providers and patients alike to improve the democratic participation of voters experiencing illness.

Emergency Mail-in Voting in Rhode Island: Protecting Civic Participation During COVID-19 and Beyond.

The COVID-19 pandemic challenges safe and equitable voting in the United States' 2020 elections, and in response, several states including Rhode Island (RI) have made significant changes to election policy. In addition to increasing accessibility of mail-in voting by mailing applications to all registered voters, RI has suspended their notary/witness requirement for both the primary and general election. However, RI's "emergency" voting process still plays a crucial role in allowing voters who missed the mail-in ballot application deadline, such as those unexpectedly hospitalized in the days leading up to the election, to still cast their ballot. COVID-19 has also forced RI to modify its emergency voting procedures, most notably allowing healthcare workers to serve on bipartisan ballot delivery teams. This commentary highlights these salient updates to voting procedures and serves as a primer as to how interested health care workers may navigate this process alongside patients and lead in the arena of patient voting rights.