Explainable machine learning for predicting conversion to neurological disease: Results from 52,939 medical records.

Objective: This study assesses the application of interpretable machine learning modeling using electronic medical record data for the prediction of conversion to neurological disease. Methods: A retrospective dataset of Cleveland Clinic patients diagnosed with Alzheimer's disease, amyotrophic lateral sclerosis, multiple sclerosis, or Parkinson's disease, and matched controls based on age, sex, race, and ethnicity was compiled. Individualized risk prediction models were created using eXtreme Gradient Boosting for each neurological disease at four timepoints in patient history. The prediction models were assessed for transparency and fairness. Results: At timepoints 0-months, 12-months, 24-months, and 60-months prior to diagnosis, Alzheimer's disease models achieved the area under the receiver operating characteristic curve on a holdout test dataset of 0.794, 0.742, 0.709, and 0.645; amyotrophic lateral sclerosis of 0.883, 0.710, 0.658, and 0.620; multiple sclerosis of 0.922, 0.877, 0.849, and 0.781; and Parkinson's disease of 0.809, 0.738, 0.700, and 0.651, respectively. Conclusions: The results demonstrate that electronic medical records contain latent information that can be used for risk stratification for neurological disorders. In particular, patient-reported outcomes, sleep assessments, falls data, additional disease diagnoses, and longitudinal changes in patient health, such as weight change, are important predictors.

Feasibility and Efficacy of Intensive Dialectical Behavior Therapy Skills Training in An Outpatient Setting for A Group of Patients with Extensive Care Needs - A Transdiagnostic Approach.

PURPOSE: Dialectical behavior therapy (DBT) is a treatment originally developed för chronically suicidal adults. It is common to adapt it by using one specific component, the DBT skills training (DBT-ST) and apply it in a group therapy setting for a variety of mental disorders. The primary aim of the study was to explore whether patients with extended care needs would report improved mental health after participating in an intensive form of DBT-ST. The secondary aim was to explore whether the use of psychiatric inpatient care for the group would decrease. METHODS: Thirty-seven participants completed the Clinical Outcomes in Routine Evaluation - Outcome Measure (CORE-OM), and visual analogue scale (VAS) at three time points: pre-intervention, post-intervention and at 6-month follow-up after intensive DBT-ST. RESULTS: One-way ANOVA showed a significant effect for time on the CORE-OM: F (2,35) = 7.93, p = .001, η2 = 0.312 (large effect size). Post hoc tests indicated a significant difference between pre-intervention and post-intervention (p = .001) and between pre-intervention and follow-up (p = .01). A Friedman test indicated a statistically significant difference in the VAS scale scores across the three time points, with p-values between 0.00 and 0.05. There was no difference in psychiatric healthcare consumption. CONCLUSION: These study results confirm to some extent the feasibility and effectiveness of the intensive DBT-ST in a transdiagnostic clinical setting. The participants had a positive outcome from the skills training program, but psychiatric healthcare consumption did not decrease.

Implementation Experience with a 30-Day Hospital Readmission Risk Score in a Large, Integrated Health System: A Retrospective Study.

BACKGROUND: Driven by quality outcomes and economic incentives, predicting 30-day hospital readmissions remains important for healthcare systems. The Cleveland Clinic Health System (CCHS) implemented an internally validated readmission risk score in the electronic medical record (EMR). OBJECTIVE: We evaluated the predictive accuracy of the readmission risk score across CCHS hospitals, across primary discharge diagnosis categories, between surgical/medical specialties, and by race and ethnicity. DESIGN: Retrospective cohort study. PARTICIPANTS: Adult patients discharged from a CCHS hospital April 2017-September 2020. MAIN MEASURES: Data was obtained from the CCHS EMR and billing databases. All patients discharged from a CCHS hospital were included except those from Oncology and Labor/Delivery, patients with hospice orders, or patients who died during admission. Discharges were categorized as surgical if from a surgical department or surgery was performed. Primary discharge diagnoses were classified per Agency for Healthcare Research and Quality Clinical Classifications Software Level 1 categories. Discrimination performance predicting 30-day readmission is reported using the c-statistic. RESULTS: The final cohort included 600,872 discharges from 11 Northeast Ohio and Florida CCHS hospitals. The readmission risk score for the cohort had a c-statistic of 0.6875 with consistent yearly performance. The c-statistic for hospital sites ranged from 0.6762, CI [0.6634, 0.6876], to 0.7023, CI [0.6903, 0.7132]. Medical and surgical discharges showed consistent performance with c-statistics of 0.6923, CI [0.6807, 0.7045], and 0.6802, CI [0.6681, 0.6925], respectively. Primary discharge diagnosis showed variation, with lower performance for congenital anomalies and neoplasms. COVID-19 had a c-statistic of 0.6387. Subgroup analyses showed c-statistics of > 0.65 across race and ethnicity categories. CONCLUSIONS: The CCHS readmission risk score showed good performance across diverse hospitals, across diagnosis categories, between surgical/medical specialties, and by patient race and ethnicity categories for 3 years after implementation, including during COVID-19. Evaluating clinical decision-making tools post-implementation is crucial to determine their continued relevance, identify opportunities to improve performance, and guide their appropriate use.

Personalized predictions of patient outcomes during and after hospitalization using artificial intelligence.

Hospital systems, payers, and regulators have focused on reducing length of stay (LOS) and early readmission, with uncertain benefit. Interpretable machine learning (ML) may assist in transparently identifying the risk of important outcomes. We conducted a retrospective cohort study of hospitalizations at a tertiary academic medical center and its branches from January 2011 to May 2018. A consecutive sample of all hospitalizations in the study period were included. Algorithms were trained on medical, sociodemographic, and institutional variables to predict readmission, length of stay (LOS), and death within 48-72 h. Prediction performance was measured by area under the receiver operator characteristic curve (AUC), Brier score loss (BSL), which measures how well predicted probability matches observed probability, and other metrics. Interpretations were generated using multiple feature extraction algorithms. The study cohort included 1,485,880 hospitalizations for 708,089 unique patients (median age of 59 years, first and third quartiles (QI) [39, 73]; 55.6% female; 71% white). There were 211,022 30-day readmissions for an overall readmission rate of 14% (for patients ≥65 years: 16%). Median LOS, including observation and labor and delivery patients, was 2.94 days (QI [1.67, 5.34]), or, if these patients are excluded, 3.71 days (QI [2.15, 6.51]). Predictive performance was as follows: 30-day readmission (AUC 0.76/BSL 0.11); LOS > 5 days (AUC 0.84/BSL 0.15); death within 48-72 h (AUC 0.91/BSL 0.001). Explanatory diagrams showed factors that impacted each prediction.

Therapeutic alliance in guided internet-delivered cognitive behavioural treatment of depression, generalized anxiety disorder and social anxiety disorder.

Guided internet-delivered cognitive behaviour therapy (ICBT) has been found to be effective in several controlled trials, but the mechanisms of change are largely unknown. Therapeutic alliance is a factor that has been studied in many psychotherapy trials, but the role of therapeutic alliance in ICBT is less well known. The present study investigated early alliance ratings in three separate samples. Participants from one sample of depressed individuals (N = 49), one sample of individuals with generalized anxiety disorder (N = 35), and one sample with social anxiety disorder (N = 90) completed the Working Alliance Inventory (WAI) modified for ICBT early in the treatment (weeks 3-4) when they took part in guided ICBT for their conditions. Results showed that alliance ratings were high in all three samples and that the WAI including the subscales of Task, Goal and Bond had high internal consistencies. Overall, correlations between the WAI and residualized change scores on the primary outcome measures were small and not statistically significant. We conclude that even if alliance ratings are in line with face-to-face studies, therapeutic alliance as measured by the WAI is probably less important in ICBT than in regular face-to-face psychotherapy.