Citations

AbstractThis study aims to examine transition of care (TOC) practices of multidisciplinary vascular anomalies centers (VACs). Thirty‐seven of 71 VAC leaders to whom the survey was sent completed the questionnaire. TOC and transfer practices varied with only 16% of VACs having TOC programs. The most frequently cited barriers to developing a TOC program were lack of resources and difficulty finding expert adult providers.

Goals: To better understand the characteristics, treatment approaches, and outcomes of patients with esophageal lichen planus (ELP). Background: ELP is a rare, often unrecognized and misdiagnosed disorder. Data on this unique patient population are currently limited to small, single-center series. Study: A multicenter, retrospective descriptive study was conducted of adults diagnosed with ELP over a 5-year period, between January 1, 2015, and October 10, 2020, from 7 centers across the United States. Results: Seventy-eight patients (average age 65 y, 86% female, 90% Caucasian) were included. Over half had at least 1 extraesophageal manifestation. Esophageal strictures (54%) and abnormal mucosa (50%) were frequent endoscopic findings, with the proximal esophagus the most common site of stricture. Approximately 20% had normal endoscopic findings. Topical steroids (64%) and/or proton pump inhibitors (74%) dominated management; endoscopic response favored steroids (43% vs. 29% respectively). Almost half of the patients required switching treatment modalities during the study period. Adjunctive therapies varied significantly between centers. Conclusions: Given its at times subtle clinical and endoscopic signs, a high index of suspicion and biopsy will improve ELP diagnosis, especially in those with extraesophageal manifestations. Effective therapies are lacking and vary significantly. Prospective investigations into optimal treatment regimens are necessary.

ASCO Rapid Recommendations Updates highlight revisions to select ASCO guideline recommendations as a response to the emergence of new and practice-changing data. The rapid updates are supported by an evidence review and follow the guideline development processes outlined in the ASCO Guideline Methodology Manual . The goal of these articles is to disseminate updated recommendations, in a timely manner, to better inform health practitioners and the public on the best available cancer care options. See the Appendix for disclaimers and other important information ( Appendix 1 and Appendix 2 , online only).

Abstract Background Alzheimer’s disease (AD) is a progressive neurological disorder with no specific curative medications. Sophisticated clinical skills are crucial to optimize treatment regimens given the multiple coexisting comorbidities in the patient population. Objective Here, we propose a study to leverage reinforcement learning (RL) to learn the clinicians’ decisions for AD patients based on the longitude data from electronic health records. Methods In this study, we selected 1736 patients from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. We focused on the two most frequent concomitant diseases—depression, and hypertension, thus creating 5 data cohorts (ie, Whole Data, AD, AD-Hypertension, AD-Depression, and AD-Depression-Hypertension). We modeled the treatment learning into an RL problem by defining states, actions, and rewards. We built a regression model and decision tree to generate multiple states, used six combinations of medications (ie, cholinesterase inhibitors, memantine, memantine-cholinesterase inhibitors, hypertension drugs, supplements, or no drugs) as actions, and Mini-Mental State Exam (MMSE) scores as rewards. Results Given the proper dataset, the RL model can generate an optimal policy (regimen plan) that outperforms the clinician’s treatment regimen. Optimal policies (ie, policy iteration and Q-learning) had lower rewards than the clinician’s policy (mean −3.03 and −2.93 vs. −2.93, respectively) for smaller datasets but had higher rewards for larger datasets (mean −4.68 and −2.82 vs. −4.57, respectively). Conclusions Our results highlight the potential of using RL to generate the optimal treatment based on the patients’ longitude records. Our work can lead the path towards developing RL-based decision support systems that could help manage AD with comorbidities.