Predicting Incident Adenocarcinoma of the Esophagus or Gastric Cardia Using Machine Learning of Electronic Health Records.

BACKGROUND & AIMS: Tools that can automatically predict incident esophageal adenocarcinoma (EAC) and gastric cardia adenocarcinoma (GCA) using electronic health records to guide screening decisions are needed. METHODS: The Veterans Health Administration (VHA) Corporate Data Warehouse was accessed to identify Veterans with 1 or more encounters between 2005 and 2018. Patients diagnosed with EAC (n = 8430) or GCA (n = 2965) were identified in the VHA Central Cancer Registry and compared with 10,256,887 controls. Predictors included demographic characteristics, prescriptions, laboratory results, and diagnoses between 1 and 5 years before the index date. The Kettles Esophageal and Cardia Adenocarcinoma predictioN (K-ECAN) tool was developed and internally validated using simple random sampling imputation and extreme gradient boosting, a machine learning method. Training was performed in 50% of the data, preliminary validation in 25% of the data, and final testing in 25% of the data. RESULTS: K-ECAN was well-calibrated and had better discrimination (area under the receiver operating characteristic curve [AuROC], 0.77) than previously validated models, such as the Nord-Trøndelag Health Study (AuROC, 0.68) and Kunzmann model (AuROC, 0.64), or published guidelines. Using only data from between 3 and 5 years before index diminished its accuracy slightly (AuROC, 0.75). Undersampling men to simulate a non-VHA population, AUCs of the Nord-Trøndelag Health Study and Kunzmann model improved, but K-ECAN was still the most accurate (AuROC, 0.85). Although gastroesophageal reflux disease was strongly associated with EAC, it contributed only a small proportion of gain in information for prediction. CONCLUSIONS: K-ECAN is a novel, internally validated tool predicting incident EAC and GCA using electronic health records data. Further work is needed to validate K-ECAN outside VHA and to assess how best to implement it within electronic health records.

Yield of Repeat Endoscopy for Barrett's Esophagus After Normal Index Endoscopy.

INTRODUCTION: Guidelines suggest 1-time screening with esophagogastroduodenoscopy (EGD) for Barrett's esophagus (BE) in individuals at an increased risk of esophageal adenocarcinoma (EAC). We aimed to estimate the yield of repeat EGD performed at prolonged intervals after a normal index EGD. METHODS: We conducted a national retrospective analysis within the U S Veterans Health Administration, identifying patients with a normal index EGD between 2003 and 2009 who subsequently had a repeat EGD. We tabulated the proportion with a new diagnosis of BE, EAC, or esophagogastric junction adenocarcinoma (EGJAC) and conducted manual chart review of a sample. We fitted logistic regression models for the odds of a new diagnosis of BE/EAC/EGJAC. RESULTS: We identified 71,216 individuals who had a repeat EGD between 1 and 16 years after an index EGD without billing or cancer registry codes for BE/EAC/EGJAC. Of them, 4,088 had a new billing or cancer registry code for BE/EAC/EGJAC after the repeat EGD. On manual review of a stratified sample, most did not truly have new BE/EAC/EGJAC. A longer duration between EGD was associated with greater odds of a new diagnosis (adjusted odds ratio [aOR] for each 5 years 1.31; 95% confidence interval [CI] 1.19-1.44), particularly among those who were younger during the index EGD (ages 19-29 years: aOR 3.92; 95% CI 1.24-12.4; ages 60-69 years: aOR 1.19; 95% CI 1.01-1.40). DISCUSSION: The yield of repeat EGD for BE/EAC/EGJAC seems to increase with time after a normal index EGD, particularly for younger individuals. Prospective studies are warranted to confirm these findings.

Eliciting patient views on the allocation of limited healthcare resources: a deliberation on hepatitis C treatment in the Veterans Health Administration.

BACKGROUND: In response to the development of highly effective but expensive new medications, policymakers, payors, and health systems are considering novel and pragmatic ways to provide these medications to patients. One approach is to target these treatments to those most likely to benefit. However, to maximize the fairness of these policies, and the acceptance of their implementation, the values and beliefs of patients should be considered. The provision of treatments for chronic hepatitis C (CHC) in the resource-constrained context of the Veterans Health Administration (VHA) offered a real-world example of this situation, providing the opportunity to test the value of using Democratic Deliberation (DD) methods to solicit the informed opinions of laypeople on this complex issue. METHODS: We recruited Veterans (n = 30) from the VHA to attend a DD session. Following educational presentations from content experts, participants engaged in facilitated small group discussions to: 1) identify strategies to overcome CHC treatment barriers and 2) evaluate, vote on, and modify/improve two CHC treatment policies - "first come, first served" (FCFS) and "sickest first" (SF). We used transcripts and facilitators' notes to identify key themes from the small group discussions. Additionally, participants completed pre- and post-DD surveys. RESULTS: Most participants endorsed the SF policy over the FCFS policy, emphasizing the ethical and medical appropriateness of treating the sickest first. Concerns about SF centered on the difficulty of implementation (e.g., how is "sickest" determined?) and unfairness to other Veterans. Proposed modifications focused on: 1) the need to consider additional health factors, 2) taking behavior and lifestyle into account, 3) offering education and support, 4) improving access, and 5) facilitating better decision-making. CONCLUSIONS: DD offered a robust and useful method for addressing the allocation of the scarce resource of CHC treatment. Participants were able to develop a modified version of the SF policy and offered diverse recommendations to promote fairness and improve quality of care for Veterans. DD is an effective approach for incorporating patient preferences and gaining valuable insights for critical healthcare policy decisions in resource-limited environments.