Comparison of Machine Learning and Conventional Statistical Modeling for Predicting Readmission Following Acute Heart Failure Hospitalization.

INTRODUCTION: Developing accurate models for predicting the risk of 30-day readmission is a major healthcare interest. Evidence suggests that models developed using machine learning (ML) may have better discrimination than conventional statistical models (CSM), but the calibration of such models is unclear. OBJECTIVES: To compare models developed using ML with those developed using CSM to predict 30-day readmission for cardiovascular and non-cardiovascular causes in HF patients. METHODS: We retrospectively enrolled 10,919 patients with HF (> 18 years) discharged alive from a hospital or emergency department (2004-2007) in Ontario, Canada. The study sample was randomly divided into training and validation sets in a 2:1 ratio. CSMs to predict 30-day readmission were developed using Fine-Gray subdistribution hazards regression (treating death as a competing risk), and the ML algorithm employed random survival forests for competing risks (RSF-CR). Models were evaluated in the validation set using both discrimination and calibration metrics. RESULTS: In the validation sample of 3602 patients, RSF-CR (c-statistic=0.620) showed similar discrimination to the Fine-Gray competing risk model (c-statistic=0.621) for 30-day cardiovascular readmission. In contrast, for 30-day non-cardiovascular readmission, the Fine-Gray model (c-statistic=0.641) slightly outperformed the RSF-CR model (c-statistic=0.632). For both outcomes, The Fine-Gray model displayed better calibration than RSF-CR using calibration plots of observed vs. predicted risks across the deciles of predicted risk. CONCLUSIONS: Fine-Gray models had similar discrimination but superior calibration to the RSF-CR model, highlighting the importance of reporting calibration metrics for ML-based prediction models. The discrimination was modest in all readmission prediction models regardless of the methods used.

To mix or not to mix? A holistic approach to stratification-preserving and destratification aeration of drinking-water supply reservoirs.

Aeration is used globally as a remediation method for lakes and reservoirs with methods generally falling into two categories, those which preserve natural stratification (hypolimnetic aeration; HA) and those which destratify reservoirs through mixing of the water column (destratification aeration; DA). The United Kingdom and Australia largely focus on DA methods to manage harmful algal blooms and decrease trace metal concentrations, whereas the United States and Europe frequently focus on HA techniques to increase dissolved oxygen (DO) concentrations and decrease benthic nutrient and metal release from the sediment. A more holistic understanding of how the different techniques influence water quality in regard to raw water supply and ecosystem health should lead to more efficient treatment, reducing wasted energy and other costs during both reservoir management and the drinking-water treatment process. This study compares HA and DA on stratification, DO, and cyanobacteria concentrations in a single drinking-water supply reservoir during the 2016 summer stratification period. HA preserved stratification but could not maintain sufficient hypolimnetic DO past late April in this functionally eutrophic reservoir, establishing conditions favourable to cyanobacteria. An incipient cyanobacteria bloom formed that was subsequently dispersed after DA was initiated on May 05. Continuous monitoring revealed the formation of these issues in real-time and informed a switch from HA to DA, thereby allowing for a pro-active rather than reactive approach to reservoir management and subsequent drinking-water treatment. Both HA and DA are put forward as successful aeration strategies depending on management goals; however, performance is strongly site-specific. Such approaches are likely to become increasingly important as reservoir management tools to combat stratification-driven water quality issues under the pressing threats of anthropogenic activity and climate change.

Neurocognitive and psychiatric outcomes associated with postacute COVID-19 infection without severe medical complication: a meta-analysis.

BACKGROUND: Cognitive symptoms are often reported by those with a history of COVID-19 infection. No comprehensive meta-analysis of neurocognitive outcomes related to COVID-19 exists despite the influx of studies after the COVID-19 pandemic. This study meta-analysed observational research comparing cross-sectional neurocognitive outcomes in adults with COVID-19 (without severe medical/psychiatric comorbidity) to healthy controls (HCs) or norm-referenced data. METHODS: Data were extracted from 54 studies published between January 2020 and June 2023. Hedges' g was used to index effect sizes, which were pooled using random-effects modelling. Moderating variables were investigated using meta-regression and subgroup analyses. RESULTS: Omnibus meta-analysis of 696 effect sizes extracted across 54 studies (COVID-19 n=6676, HC/norm-reference n=12 986; average time since infection=~6 months) yielded a small but significant effect indicating patients with COVID-19 performed slightly worse than HCs on cognitive measures (g=-0.36; 95% CI=-0.45 to -0.28), with high heterogeneity (Q=242.30, p<0.001, τ=0.26). Significant within-domain effects was yielded by cognitive screener (g=-0.55; 95% CI=-0.75 to -0.36), processing speed (g=-0.44; 95% CI=-0.57 to -0.32), global cognition (g=-0.40; 95% CI=-0.71 to -0.09), simple/complex attention (g=-0.38; 95% CI=-0.46 to -0.29), learning/memory (g=-0.34; 95% CI=-0.46 to -0.22), language (g=-0.34; 95% CI=-0.45 to -0.24) and executive function (g=-0.32; 95% CI=-0.43 to -0.21); but not motor (g=-0.40; 95% CI=-0.89 to 0.10), visuospatial/construction (g=-0.09; 95% CI=-0.23 to 0.05) and orientation (g=-0.02; 95% CI=-0.17 to 0.14). COVID-19 samples with elevated depression, anxiety, fatigue and disease severity yielded larger effects. CONCLUSION: Mild cognitive deficits are associated with COVID-19 infection, especially as detected by cognitive screeners and processing speed tasks. We failed to observe clinically meaningful cognitive impairments (as measured by standard neuropsychological instruments) in people with COVID-19 without severe medical or psychiatric comorbidities.

Improving usual care outcomes in major depression in youth by targeting memory specificity: A randomized controlled trial of adjunct computerized memory specificity training (c-MeST).

OBJECTIVE: Extending on previous findings that computerized Memory Specificity Training (c-MeST) improves memory specificity and depressive symptoms in Major Depressive Disorder (MDD) in adults, this study aimed to assess the effects of c-MeST in youth with MDD on memory specificity and depression in addition to other treatment. METHODS: Participants aged 15-25 (N = 359, 76 % female; M age = 19.2, SD = 3.1), receiving predominantly psychological therapy or counseling (85 %) and/or antidepressants (52 %) were randomized to usual care and c-MeST or usual care. Cognitive and clinical outcomes were assessed at baseline and at one, three, and six-month follow-ups. RESULTS: The usual care and c-MeST group reported higher memory specificity at one-month (d = 0.42, p = .022), but not at three or six months (d's < 0.15, p's > 0.05). The rate of MDE was numerically lower in the c-MeST group at each follow-up time-point, but group was not a statistically significant predictor at one month (64 % usual care and c-MeST vs. 68 % usual care, OR = 0.81, p = .606), three months (67 % usual care and c-MeST vs. 72 % usual care, OR = 0.64, p = .327) or six months (55 % usual care and c-MeST vs. 68 % usual care, OR = 0.56, p = .266). The usual care and c-MeST group did report lower depressive symptoms at one month (d = 0.42, p = .023) and six-months (d = 0.84, p = .001), but not three-months (d = 0.13, p > .05). CONCLUSIONS: c-MeST may reduce symptoms in youth with MDD when provided alongside other treatments. However, there are significant limitations to this inference, including high attrition in the study and a need for more data on the acceptability of the intervention.

Guided recall of positive autobiographical memories increases anticipated pleasure and psychological resources, and reduces depressive symptoms: a replication and extension of a randomised controlled trial of brief positive cognitive-reminiscence therapy.

Reminiscence-based interventions focus on recalling autobiographical memories and reflective reasoning to develop a healthy and adaptive view of oneself and one's life. This study aimed to replicate the effects of a three-session, group-based, positive-memory version of cognitive-reminiscence therapy (CRT) on psychological resources and mental well-being and extend the findings to anticipated pleasure. The participants (N = 75, Mage = 43.7 (SD = 16.7), 60% females) were randomised to CRT or control group. Anticipated pleasure, psychological resources (schemas of positive self-esteem, self-efficacy, meaning in life, optimism), mental well-being (depression, anxiety, and stress symptoms) and theorised change processes (automatic negative thoughts, awareness of narrative identity) were assessed. Relative to the control group, the CRT group reported significantly higher anticipated pleasure (d = 0.76-0.93) and psychological resources of self-esteem, self-efficacy, and optimism (d's = 0.58-0.99) at post-CRT and follow-up, and lower depressive symptoms post-CRT and at follow-up (d = 0.56-0.67). Findings on meaning in life and negative automatic thinking were partially replicated. This study replicates findings of the effectiveness of this intervention for improving psychological resources such as self-worth, confidence and optimism and depressive symptoms, and indicates additional effects on anticipated pleasure. CRT may serve as a standalone intervention, or as an adjunct "memory booster" for interventions focused on future thinking and related anticipated reward.

Correction: Hamilton et al. Receptors for Insulin-Like Growth Factor-2 and Androgens as Therapeutic Targets in Triple-Negative Breast Cancer. Int. J. Mol. Sci. 2017, 18, 2305.

In the original publication [...].

Development of a Machine Learning Modelling Tool for Predicting HIV Incidence Using Public Health Data from a County in the Southern United States.

BACKGROUND: Recent advancements in Machine Learning (ML) have significantly improved the accuracy of models predicting HIV incidence. These models typically utilize electronic medical records and patient registries. This study aims to broaden the application of these tools by utilizing de-identified public health datasets for notifiable sexually transmitted infections (STIs) from a southern U.S. County known for high HIV incidence rates. The goal is to assess the feasibility and accuracy of ML in predicting HIV incidence, which could potentially inform and enhance public health interventions. METHODS: We analyzed two de-identified public health datasets, spanning January 2010 to December 2021, focusing on notifiable STIs. Our process involved data processing and feature extraction, including sociodemographic factors, STI cases, and social vulnerability index (SVI) metrics. Various ML algorithms were trained and evaluated for predicting HIV incidence, using metrics such as accuracy, precision, recall, and F1 score. RESULTS: The study included 85,224 individuals, with 2,027 (2.37%) newly diagnosed with HIV during the study period. The ML models demonstrated high performance in predicting HIV incidence among males and females. Influential predictive features for males included age at STI diagnosis, previous STI information, provider type, and SVI. For females, they included age, ethnicity, previous STIs information, overall SVI, and race. CONCLUSIONS: The high accuracy of our ML models in predicting HIV incidence highlights the potential of using public health datasets for public health interventions such as tailored HIV testing and prevention. While these findings are promising, further research is needed to translate these models into practical public health applications.

Dapagliflozin in Myocardial Infarction without Diabetes or Heart Failure.

BACKGROUND: In patients with acute myocardial infarction (MI), therapies that could further reduce the risk of adverse cardiovascular and metabolic outcomes are needed. METHODS: In this international registry-based, randomized, double-blind trial, patients without prior diabetes or chronic heart failure, presenting with acute MI and impaired left ventricular systolic function, were randomly assigned 10 mg of dapagliflozin or placebo, given once daily. The primary outcome was the hierarchical composite of death, hospitalization for heart failure, nonfatal MI, atrial fibrillation/flutter, type 2 diabetes mellitus, New York Heart Association Functional Classification at the last visit, and body weight decrease of 5% or greater at the last visit using the win ratio analysis method. The key secondary outcome was the same hierarchical composite excluding the body weight component. RESULTS: We enrolled 4017 patients of whom 2019 were assigned to dapagliflozin and 1998 to placebo. The analysis of the primary hierarchical composite outcome resulted in significantly more wins for dapagliflozin than for placebo (win ratio, 1.34; 95% confidence interval [CI], 1.20 to 1.50; P<0.001). The win ratio outcome, which was adopted in a change of analysis during trial performance because of low event accrual, was mainly driven by the added cardiometabolic outcomes. The composite of time to cardiovascular death/hospitalization for heart failure occurred in 50/2019 (2.5%) patients assigned to dapagliflozin and 52/1998 (2.6%) patients assigned to placebo (hazard ratio, 0.95; 95% CI, 0.64 to 1.40). The rates of other cardiovascular events were low, with differences between the groups not reaching nominal statistical significance. No safety concerns were identified. CONCLUSIONS: In patients with acute MI as noted above, after approximately 1 year of treatment with dapagliflozin there were significant benefits with regard to improvement in cardiometabolic outcomes but no impact on the composite of cardiovascular death or hospitalization for heart failure compared with placebo. (Funded by AstraZeneca; ClinicalTrial.gov number, NCT04564742.)