Machine Learning Prediction of Quality of Life Improvement During Antidepressant Treatment of Patients With Major Depressive Disorder: A STAR*D and CAN-BIND-1 Report.

Background: Quality of life (QoL) is an important patient-centric outcome to evaluate in treatment of major depressive disorder (MDD). This work sought to investigate the performance of several machine learning methods to predict a return to normative QoL in patients with MDD after antidepressant treatment.Methods: Several binary classification algorithms were trained on data from the first 2 weeks of the Sequenced Treatment Alternatives to Relieve Depression (STAR*D) study (n = 651, conducted from 2001 to 2006) to predict week 9 normative QoL (score ≥ 67, based on a community normative sample, on the Quality of Life Enjoyment and Satisfaction Questionnaire-Short Form [Q-LES-Q-SF]) after treatment with citalopram. Internal validation was performed using a STAR*D holdout dataset, and external validation was performed using the Canadian Biomarker Integration Network in Depression-1 (CAN-BIND-1) dataset (n = 175, study conducted from 2012 to 2017) after treatment with escitalopram. Feature importance was calculated using SHapley Additive exPlanations (SHAP).Results: Random Forest performed most consistently on internal and external validation, with balanced accuracy (area under the receiver operator curve) of 71% (0.81) on the STAR*D dataset and 69% (0.75) on the CAN-BIND-1 dataset. Random Forest Classifiers trained on Q-LES-Q-SF and Quick Inventory of Depressive Symptomatology-Self-Rated variables had similar performance on both internal and external validation. Important predictive variables came from psychological, physical, and socioeconomic domains.Conclusions: Machine learning can predict normative QoL after antidepressant treatment with similar performance to that of prior work predicting depressive symptom response and remission. These results suggest that QoL outcomes in MDD patients can be predicted with simple patient-rated measures and provide a foundation to further improve performance and demonstrate clinical utility.Trial Registration: ClinicalTrials.gov identifiers NCT00021528 and NCT01655706.

The Impact of a Clinical Decision Support System for Addressing Physical Activity and Healthy Eating During Smoking Cessation Treatment: Hybrid Type I Randomized Controlled Trial.

BACKGROUND: People who smoke have other risk factors for chronic diseases, such as low levels of physical activity and poor diet. Clinical decision support systems (CDSSs) might help health care practitioners integrate interventions for diet and physical activity into their smoking cessation programming but could worsen quit rates. OBJECTIVE: The aims of this study are to assess the effects of the addition of a CDSS for physical activity and diet on smoking cessation outcomes and to assess the implementation of the study. METHODS: We conducted a pragmatic hybrid type I effectiveness-implementation trial with 232 team-based primary care practices in Ontario, Canada, from November 2019 to May 2021. We used a 2-arm randomized controlled trial comparing a CDSS addressing physical activity and diet to treatment as usual and used the Reach, Effectiveness, Adoption, Implementation, and Maintenance framework to measure implementation outcomes. The primary outcome was self-reported 7-day tobacco abstinence at 6 months. RESULTS: We enrolled 5331 participants in the study. Of these, 2732 (51.2%) were randomized to the intervention group and 2599 (48.8%) to the control group. At the 6-month follow-up, 29.7% (634/2137) of respondents in the intervention arm and 27.3% (552/2020) in the control arm reported abstinence from tobacco. After multiple imputation, the absolute group difference was 2.1% (95% CI -0.5 to 4.6; F1,1000.42=2.43; P=.12). Mean exercise minutes changed from 32 (SD 44.7) to 110 (SD 196.1) in the intervention arm and from 32 (SD 45.1) to 113 (SD 195.1) in the control arm (group effect: B=-3.7 minutes; 95% CI -17.8 to 10.4; P=.61). Servings of fruit and vegetables changed from 2.64 servings to 2.42 servings in the intervention group and from 2.52 servings to 2.45 servings in the control group (incidence rate ratio for intervention group=0.98; 95% CI 0.93-1.02; P=.35). CONCLUSIONS: A CDSS for physical activity and diet may be added to a smoking cessation program without affecting the outcomes. Further research is needed to improve the impact of integrated health promotion interventions in primary care smoking cessation programs. TRIAL REGISTRATION: ClinicalTrials.gov NCT04223336 https://www.clinicaltrials.gov/ct2/show/NCT04223336. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.2196/19157.

Rates of Mental Illness and Addiction among High-Cost Users of Medical Services in Ontario.

OBJECTIVE: To quantify the burden of mental illness and addiction among high-costing users of medical services (HCUs) using population-level data from Ontario, and compare to a referent group of nonusers. METHOD: We conducted a population-level cohort study using health administrative data from fiscal year 2011-2012 for all Ontarians with valid health insurance as of April 1, 2011 (N = 10,909,351). Individuals were grouped based on medical costs for hospital, emergency, home, complex continuing, and rehabilitation care in 2011-2012: top 1%, top 2% to 5%, top 6% to 50%, bottom 50%, and a zero-cost nonuser group. The rate of diagnosed psychotic, major mood, and substance use disorders in each group was compared to the zero-cost referent group with adjusted odds ratios (AORs) for age, sex, and socioeconomic status. A sensitivity analysis included anxiety and other disorders. RESULTS: Mental illness and addiction rates increased across cost groups affecting 17.0% of the top 1% of users versus 5.7% of the zero-cost group (AOR, 3.70; 95% confidence interval [CI], 3.59 to 3.81). This finding was most pronounced for psychotic disorders (3.7% vs. 0.7%; AOR, 5.07; 95% CI, 4.77 to 5.38) and persisted for mood disorders (10.0% vs. 3.3%; AOR, 3.52; 95% CI, 3.39 to 3.66) and substance use disorders (7.0% vs. 2.3%; AOR, 3.82; 95% CI, 3.66 to 3.99). When anxiety and other disorders were included, the rate of mental illness was 39.3% in the top 1% compared to 21.3% (AOR, 2.39; 95% CI, 2.34 to 2.45). CONCLUSIONS: A high burden of mental illness and addiction among HCUs warrants its consideration in the design and delivery of services targeting HCUs.

Omega-6 to Omega-3 Fatty Acid Ratio in Patients with ADHD: A Meta-Analysis.

OBJECTIVE: Omega-3 and omega-6 fatty acids have been shown to be deficient in individuals with attention deficit/hyperactivity disorder compared to controls (Hawkey & Nigg, 2014). Clinical trials of omega-3 and omega-6 supplements as treatment for ADHD have demonstrated minimal efficacy (Bloch & Qawasmi, 2011; Gillies, Sinn, Lad, Leach, & Ross, 2011; Hawkey & Nigg, 2014; Puri & Martins, 2014; Sonuga-Barke et al., 2013). Existing trials have analyzed omega-3 and omega-6 separately although the tissue ratio of these fatty acids (n6/n3) may be more important than absolute levels of either. The objective of this study was to determine the relationship between blood n6/n3 and arachidonic acid to eicosapentaenoic acid (AA/EPA), to ADHD symptoms. METHOD: A systematic literature review identified original articles measuring blood n6/n3 or AA/EPA ratio in children and youth with ADHD, compared to controls without ADHD. Three databases were searched. Blood n6/n3, and AA/EPA ratios were compared between individuals with ADHD and controls. Results were pooled across studies using quantitative synthesis. RESULTS: Five articles met inclusion criteria for the meta-analysis. The pooled mean difference between patients with ADHD and controls was 1.97 (0.90-3.04) for n6/n3 (n=5 studies, I(2) 83%) and 8.25 (5.94-10.56) for AA/EPA (n=3 studies, I(2) 0%). CONCLUSIONS: Children and youth with ADHD have elevated ratios of both blood n6/n3 and AA/EPA fatty acids compared to controls. Thus an elevated n6/n3, and more specifically AA/EPA, ratio may represent the underlying disturbance in essential fatty acid levels in patients with ADHD. These findings have implications for the development of future interventions using essential fatty acids to treat ADHD, and for the use of these ratios as biomarkers for titrating and monitoring ADHD treatment with essential fatty acids.

OBJECTIF: Les acides gras omega-3 et omega-6 se sont révélés être déficients chez les personnes souffrant du trouble de déficit de l'attention avec hyperactivité (TDAH) comparativement aux sujets témoins (Hawkey et Nigg, 2014). Les essais cliniques sur les suppléments d'omega-3 et d'omega-6 comme traitement du TDAH ont démontré une efficacité minimale (Bloch et Qawasmi, 2011; Gillies, Sinn, Lad, Leach, et Ross, 2011; Hawkey et Nigg, 2014; Puri et Martins, 2014; Sonuga-Barke et al., 2013). Les essais existants ont analysé les omega-3 et omega-6 séparément, bien que le ratio tissulaire de ces acides gras (n-6/n-3) puisse être plus important que les niveaux absolus de chacun. L'objectif de cette étude était de déterminer la relation entre le n-6/n-3 sanguin et le ratio acide arachidonique sur acide eicosapentaénoïque (AA/EPA), et les symptômes du TDAH. MÉTHODE: Une revue systématique de la littérature a identifié les articles originaux mesurant le n-6/n-3 sanguin ou le ratio AA/EPA chez les enfants et les adolescents souffrant du TDAH, comparativement aux sujets témoins sans TDAH. Trois bases de données ont été recherchées. Le n-6/n-3 sanguin et les ratios AA/EPA ont été comparés entre les personnes souffrant du TDAH et les sujets témoins. Les résultats ont été totalisés entre les études à l'aide d'une synthèse quantitative. RÉSULTATS: Cinq articles satisfaisaient aux critères d'inclusion de la méta-analyse. La différence moyenne totalisée entre les patients souffrant de TDAH et les sujets témoins était de 1,97 (0,90­3,04) pour n-6/n-3 (n = 5 études, I2 83 %) et de 8,25 (5,94­10,56) pour AA/EPA (n = 3 études, I2 0 %). CONCLUSIONS: Les enfants et les adolescents souffrant du TDAH ont des ratios élevés tant du n-6/n-3 sanguin que des acides gras AA/EPA, comparativement aux sujets témoins. Donc, un ratio n-6/n-3 élevé, et plus spécifiquement le ratio AA/EPA, peuvent représenter la perturbation sous-jacente des niveaux d'acides gras essentiels chez les patients souffrant de TDAH. Ces résultats ont des implications pour le développement de futures interventions utilisant des acides gras essentiels pour traiter le TDAH, et pour l'utilisation de ces ratios comme biomarqueurs pour titrer et surveiller le traitement du TDAH avec les acides gras essentiels.

Comparison of midwifery, family medicine, and obstetric patients' understanding of weight gain during pregnancy: a minority of women report correct counselling.

OBJECTIVE: We hypothesized that differences in models of care between health care providers would result in variations in patients' reports of counselling. Our objective was to compare what women reported being advised about weight gain during pregnancy and the risks of inappropriate weight gain according to their type of health care provider. METHODS: A cross-sectional survey was conducted using a self-administered questionnaire at obstetric, midwifery, and family medicine clinics in Hamilton, Ontario. Women were eligible to participate if they had had at least one prenatal visit, could read English, and had a live, singleton pregnancy. RESULTS: Three hundred and eight women completed the survey, a 93% response rate. Care for 90% of the group was divided approximately evenly between midwives, family physicians, and obstetricians. A minority of women looked after by any of the types of care providers reported being counselled correctly about how much weight to gain during pregnancy (16.3%, 10.3%, 9.2%, and 5.7% of patients of midwives, family physicians, obstetricians, or other types of care providers, respectively, P = 0.349). A minority of women with any category of care provider was planning to gain an amount of weight that fell within the guidelines or reported being told that there were risks to themselves or their babies with inappropriate gain. CONCLUSION: In this study comparing reported counselling between patients of obstetricians, midwives, family physicians, and other health care providers, low rates of counselling about gestational weight gain were universally reported. There is a common need for more effective counselling.