Improved Time in Range During 28 Days of Meal Delivery for People With Type 2 Diabetes.

Objective: Nutrition therapy is a cornerstone of care for people with type 2 diabetes, yet starting new, healthy eating behaviors and sustaining them can be challenging. This decentralized, single-arm study assessed the impact of 28 days of home-delivered, pre-portioned meals (three meals per day) on continuous glucose monitoring (CGM)-derived glycemic control and quality of life. Research design and methods: We enrolled 154 people with type 2 diabetes from across the United States. All participants were enrolled in a digital-first type 2 diabetes care center of excellence and had a time in range (TIR) <70% or a glucose management index (GMI) >7%. A total of 102 participants received another set of meals for a household member. Forty-four participants were excluded from CGM-based analysis because of sparse data in the baseline or intervention period. Results: From the baseline through the intervention period, average TIR improved by 6.8% (95% CI 4.0-9.7, P <0.001), average GMI improved by 0.21% (95% CI 0.11-0.32, P <0.001), and participants' odds of achieving ≥70% TIR increased (odds ratio 2.55 [95% CI 0.93-7.80, P = 0.051]). Although average TIR increased rapidly upon initiation of meal delivery, it regressed when the delivery period ended. Conclusion: Home-delivered meals were associated with modest TIR and GMI improvements, but only in the short term. More research is needed to determine whether the effects of nutrition therapy can be extended by providing ongoing meal delivery or additional support such as behavioral intervention.

Machine Learning-Based Exploratory Clinical Decision Support for Newly Diagnosed Patients With Acute Myeloid Leukemia Treated With 7 + 3 Type Chemotherapy or Venetoclax/Azacitidine.

PURPOSE: There are currently limited objective criteria to help assist physicians in determining whether an individual patient with acute myeloid leukemia (AML) is likely to do better with induction with either standard 7 + 3 chemotherapy or targeted therapy with venetoclax plus azacitidine. The study goal was to address this need by developing exploratory clinical decision support methods. PATIENTS AND METHODS: Univariable and multivariable analysis as well as comparison of a range of machine learning (ML) predictors were performed using cohorts of 120 newly diagnosed 7 + 3-treated AML patients compared with 101 venetoclax plus azacitidine-treated patients. RESULTS: A variety of features in the two patient cohorts were identified that may potentially correlate with short- and long-term outcomes, toxicities, and other considerations. A subset of these diagnostic features was then used to develop ML-based predictors with relatively high areas under the curve of short- and long-term outcomes, hospital stays, transfusion requirements, and toxicities for individual patients treated with either venetoclax/azacitidine or 7 + 3. CONCLUSION: Potential ML-based approaches to clinical decision support to help guide individual patients with newly diagnosed AML to either 7 + 3 or venetoclax plus azacitidine induction therapy were identified. Larger cohorts with separate test and validation studies are necessary to confirm these initial findings.

Leveraging electronic health records for predictive modeling of post-surgical complications.

Hospital-specific electronic health record systems are used to inform clinical practice about best practices and quality improvements. Many surgical centers have developed deterministic clinical decision rules to discover adverse events (e.g. postoperative complications) using electronic health record data. However, these data provide opportunities to use probabilistic methods for early prediction of adverse health events, which may be more informative than deterministic algorithms. Electronic health record data from a set of 9598 colorectal surgery cases from 2010 to 2014 were used to predict the occurrence of selected complications including surgical site infection, ileus, and bleeding. Consistent with previous studies, we find a high rate of missing values for both covariates and complication information (4-90%). Several machine learning classification methods are trained on an 80% random sample of cases and tested on a remaining holdout set. Predictive performance varies by complication, although an area under the receiver operating characteristic curve as high as 0.86 on testing data was achieved for bleeding complications, and accuracy for all complications compares favorably to existing clinical decision rules. Our results confirm that electronic health records provide opportunities for improved risk prediction of surgical complications; however, consideration of data quality and consistency standards is an important step in predictive modeling with such data.