An intervention based on Well-Being Therapy to prevent alcohol use and other unhealthy lifestyle behaviors among students: a three-arm cluster randomized controlled trial.

Unhealthy lifestyle, such as alcohol use, and negative health outcomes have been associated with impairments in psychological well-being. The primary objective of the study was to test the efficacy of an intervention based on Well-Being Therapy to prevent or stem alcohol use, binge drinking and other unhealthy lifestyle among Italian adolescents in school settings. A three-arm cluster randomized controlled trial including three test periods (baseline, post-test, six-month follow-up) was implemented. Seven classes (144 students) were randomly assigned to receive well-being intervention (WBI), lifestyle intervention (LI), or no intervention (NI). Primary outcomes were alcohol use (AUDIT-C), binge drinking and other unhealthy lifestyle behaviors (i.e. unhealthy diet, physical inactivity, tobacco and cannabis smoking, poor sleep and Internet addiction). Linear mixed models and mixed-effects logistic regression were used to test the efficacy of WBI in comparison with LI and NI. At six-month follow-up, AUDIT-C total score increased more in NI in comparison with WBI (p = 0.044) and LI (p = 0.016), whereas the odds of being classified as at-risk drinker were lower in WBI (p = 0.038) and LI (p = 0.002), than NI. Only WBI showed a protective effect for cannabis use at post-test in comparison with NI (p = 0.003) and LI (p = 0.014). Sleep hours at night decreased more in NI than in LI (p = 0.027) at six months. Internet addiction decreased more in WBI (p = 0.002) and LI (p = 0.005) at post-test in comparison with NI. Although both interventions showed a positive impact on adolescent lifestyle, the positive effect of WBI on cannabis use underlines how this approach might be promising to stem adolescents' substance use.

Structured deep embedding model to generate composite clinical indices from electronic health records for early detection of pancreatic cancer.

The high-dimensionality, complexity, and irregularity of electronic health records (EHR) data create significant challenges for both simplified and comprehensive health assessments, prohibiting an efficient extraction of actionable insights by clinicians. If we can provide human decision-makers with a simplified set of interpretable composite indices (i.e., combining information about groups of related measures into single representative values), it will facilitate effective clinical decision-making. In this study, we built a structured deep embedding model aimed at reducing the dimensionality of the input variables by grouping related measurements as determined by domain experts (e.g., clinicians). Our results suggest that composite indices representing liver function may consistently be the most important factor in the early detection of pancreatic cancer (PC). We propose our model as a basis for leveraging deep learning toward developing composite indices from EHR for predicting health outcomes, including but not limited to various cancers, with clinically meaningful interpretations.

Well-Being Therapy and Lifestyle Intervention in Type 2 Diabetes: A Pilot Randomized Controlled Trial.

OBJECTIVE: This pilot randomized controlled trial evaluates the preliminary efficacy of a 4-month well-being therapy (WBT) and lifestyle intervention among adults with type 2 diabetes and overweight/obesity. METHODS: Fifty-eight patients were recruited from two outpatient clinics and randomized to receive the WBT-lifestyle intervention or the lifestyle intervention alone. Data were collected at baseline (T0), immediate postintervention (T1), 6-month follow-up (T2), and 12-month follow-up (T3). Primary efficacy outcomes included changes in weight, psychological distress, and well-being, whereas secondary efficacy outcomes included changes in lifestyle and physiological parameters. RESULTS: Compared with the lifestyle-alone intervention, the WBT-lifestyle intervention showed greater improvements in depression (p = .009, d = -0.6), hostility (p = .018, d = -0.6), and personal growth (p = .026, d = 0.5) at T1, in self-reported physical activity at T2 (p = .013, d = 0.7) and T3 (p = .040, d = 0.5), and in triglycerides (p = .019, d = -1.12) at T3. There were no differences between treatment groups in weight and other physiological parameters. CONCLUSIONS: These findings suggest that WBT may be a valuable addition to lifestyle interventions for improving short-term psychological outcomes and promoting long-term healthy changes in physical activity, with a potential impact on physiological outcomes.Trial Registration:ClinicalTrials.gov identifier: NCT03609463.

Deep learning on time series laboratory test results from electronic health records for early detection of pancreatic cancer.

The multi-modal and unstructured nature of observational data in Electronic Health Records (EHR) is currently a significant obstacle for the application of machine learning towards risk stratification. In this study, we develop a deep learning framework for incorporating longitudinal clinical data from EHR to infer risk for pancreatic cancer (PC). This framework includes a novel training protocol, which enforces an emphasis on early detection by applying an independent Poisson-random mask on proximal-time measurements for each variable. Data fusion for irregular multivariate time-series features is enabled by a "grouped" neural network (GrpNN) architecture, which uses representation learning to generate a dimensionally reduced vector for each measurement set before making a final prediction. These models were evaluated using EHR data from Columbia University Irving Medical Center-New York Presbyterian Hospital. Our framework demonstrated better performance on early detection (AUROC 0.671, CI 95% 0.667 - 0.675, p < 0.001) at 12 months prior to diagnosis compared to a logistic regression, xgboost, and a feedforward neural network baseline. We demonstrate that our masking strategy results greater improvements at distal times prior to diagnosis, and that our GrpNN model improves generalizability by reducing overfitting relative to the feedforward baseline. The results were consistent across reported race. Our proposed algorithm is potentially generalizable to other diseases including but not limited to cancer where early detection can improve survival.

Immunogenetics of gastrointestinal cancers: A systematic review and retrospective survey of inborn errors of immunity in humans.

BACKGROUND AND AIM: Humans with inborn errors of immunity (IEI), or primary immunodeficiencies, may be associated with a potential risk factor for early-onset gastrointestinal (GI) cancer. METHODS: We systematically reviewed all cases with clinical diagnoses of both an IEI and a GI cancer in three databases (MEDLINE, SCOPUS, and EMBASE). In total, 76 publications satisfying our inclusion criteria were identified, and data for 149 cases were analyzed. We also searched our institutional cancer registry for such cases. RESULTS: We identified 149 patients with both an IEI and a GI cancer, 95 presented gastric cancer, 13 small bowel cancer, 35 colorectal cancer, and 6 had an unspecified cancer or cancer at another site. Gastric and colon adenocarcinomas were the most common. For both gastric and colorectal cancers, age at onset was significantly earlier in patients with IEIs than in the general population, based on the SEER database. Common variable immunodeficiency (CVID) was the most common IEI associated with gastrointestinal cancer. About 12% of patients had molecular genetic diagnoses, the three most frequently implicated genes being ATM, CARMIL2, and CTLA4. Impaired humoral immunity and Epstein-Barr virus (EBV) infection were frequently reported as factors potentially underlying early-onset GI cancers in patients with IEIs. We identified one patient with CVID and early-onset gastric adenocarcinoma, recurrent diarrhea, and gastrointestinal CMV infection from a retrospective survey. CONCLUSION: Patients with IEIs should be considered at risk of early-onset GI cancers and should therefore undergo cancer screening at an earlier age.

Effect of Resident and Fellow Involvement on Outcomes of Sarcoma Surgery: A NSQIP Database Cross-Sectional Study.

BACKGROUND: The complexity of sarcoma surgery often justifies surgical assistants of higher levels of academic training: senior residents, fellows, or co-surgeons. The association between the level of training of assistants and outcomes of these procedures has yet to be studied. METHODS: The Current Procedural Terminology (CPT) codes comprising the "core" procedures for musculoskeletal oncology fellowships were gathered. After CPTs primarily capturing nononcologic procedures were excluded, the National Surgical Quality Improvement Program (NSQIP) database was used to find procedures with these CPTs. The severity of complications was assessed using the Severity Weighting of Postoperative Adverse Events in Orthopedic Surgery (SWORD) score. Resident/fellow presence was analyzed both as a binary variable and stratified by level of training. RESULTS: In 159 cases meeting inclusion criteria, higher-level assistants were associated with increased rate of any complication (p=0.006) and greater need for transfusion (p=0.001) but also tended to be used in cases of longer duration (p=0.001) and with higher total work relative value units (wRVUs) (p=0.001). Multivariate analysis showed that while higher-wRVU procedures persisted as an independent predictor of increased complications (OR 1.028 per RVU unit, p=0.002), neither the presence nor level of training of assistants had an independent effect on complication rates. Other independent predictors of 30-day complications were treatment comorbidity (OR 3.433, p=0.010) and lower extremity location of the tumor (OR 4.393, p=0.006). Severity of complications did not differ between any of the groups on either univariate or multivariate analysis. CONCLUSIONS: Trainees of higher levels of academic training tend to be present for longer, higher-complexity musculoskeletal oncology cases, but the overall severity of complications from these do not significantly differ from lower-risk cases without trainees. Orthopedic oncologists may reassure patients that the presence of trainees and co-surgeons is not only safe but it may also help reduce the severity of complications in more complex procedures.

Cases in Precision Medicine: When Patients Present With Direct-to-Consumer Genetic Test Results.

A couple is planning to start a family, and they decide to order a 23andMe test after reading about the company's carrier screening test and the new BRCA1/BRCA2 test. They bring the results to their internist for advice on how to proceed. Given the rise in public interest in human genetics and precision medicine, direct-to-consumer genetic testing is becoming increasingly popular, and clinicians should expect patients to present the results of these tests more frequently. This article uses a case scenario to provide information about what the results of these tests mean, and what they do not mean.