Search for: All records

BackgroundAs artificial intelligence (AI) tools are integrated more widely in psychiatric medicine, it is important to consider the impact these tools will have on clinical practice. ObjectiveThis study aimed to characterize physician perspectives on the potential impact AI tools will have in psychiatric medicine. MethodsWe interviewed 42 physicians (21 psychiatrists and 21 family medicine practitioners). These interviews used detailed clinical case scenarios involving the use of AI technologies in the evaluation, diagnosis, and treatment of psychiatric conditions. Interviews were transcribed and subsequently analyzed using qualitative analysis methods. ResultsPhysicians highlighted multiple potential benefits of AI tools, including potential support for optimizing pharmaceutical efficacy, reducing administrative burden, aiding shared decision-making, and increasing access to health services, and were optimistic about the long-term impact of these technologies. This optimism was tempered by concerns about potential near-term risks to both patients and themselves including misguiding clinical judgment, increasing clinical burden, introducing patient harms, and creating legal liability. ConclusionsOur results highlight the importance of considering specialist perspectives when deploying AI tools in psychiatric medicine. 

ABSTRACT Pharmacogenetics is a promising strategy to facilitate individualized care for patients with Major Depressive Disorder (MDD). Research is ongoing to identify the optimal genetic markers for predicting outcomes to antidepressant therapies. The primary aim of this systematic review was to summarize antidepressant pharmacogenetic studies to enhance understanding of the genes, variants, datatypes/methodologies, and outcomes investigated in the context of MDD. The secondary aim was to identify clinical genetic panels indicated for antidepressant prescribing and summarize their genes and variants. Screening ofN = 5793 articles yieldedN = 390 for inclusion, largely comprising adult (≥ 18 years) populations. Top‐studied variants identified in the search were discussed and compared with those represented on theN = 34 clinical genetic panels that were identified. Summarization of articles revealed sources of heterogeneity across studies and low rates of replicability of pharmacogenetic associations. Heterogeneity was present in outcome definitions, treatment regimens, and differential inclusion of mediating variables in analyses. Efficacy outcomes (i.e., response, remission) were studied at greater frequency than adverse‐event outcomes. Studies that used advanced analytical approaches, such as machine learning, to integrate variants with complimentary biological datatypes were fewer in number but achieved higher rates of significant associations with treatment outcomes than candidate variant approaches. As large biological datasets become more prevalent, machine learning will be an increasingly valuable tool for parsing the complexity of antidepressant response. This review provides valuable context and considerations surrounding pharmacogenetic associations in MDD which will help inform future research and translation efforts for guiding antidepressant care. 

Abstract ObjectivesInterpatient variability in bipolar I depression (BP‐D) symptoms challenges the ability to predict pharmacotherapeutic outcomes. A machine learning workflow was developed to predict remission after 8 weeks of pharmacotherapy (total score of ≤8 on the Montgomery Åsberg Depression Rating Scale [MADRS]). MethodsSupervised machine learning models were trained on data from BP‐D patients treated with olanzapine (N = 168) and were externally validated on patients treated with olanzapine/fluoxetine combination (OFC;N = 131) and lamotrigine (LTG;N = 126). Top predictors were used to develop a prognosis rule informing how many symptoms should change and by how much within 4 weeks to increase the odds of achieving remission. ResultsAn AUC of 0.76 (NIR:0.59;p = 0.17) was established to predict remission in olanzapine‐treated subjects. These trained models achieved AUCs of 0.70 with OFC (NIR:0.52;p < 0.03) and 0.73 with LTG (NIR:0.52;p < 0.003), demonstrating external replication of prediction performance. Week‐4 changes in four MADRS symptoms (reported sadness, reduced sleep, reduced appetite, and concentration difficulties) were top predictors of remission. Across all pharmacotherapies, three or more of these symptoms needed to improve by ≥2 points at Week‐4 to have a 65% chance of achieving remission at 8 weeks (OR: 3.74, 95% CI: 2.45–5.76;p < 9.3E‐11). ConclusionMachine learning strategies achieved cross‐trial and cross‐drug replication in predicting remission after 8 weeks of pharmacotherapy for BP‐D. Interpretable prognoses rules required only a limited number of depressive symptoms, providing a promising foundation for developing simple quantitative decision aids that may, in the future, serve as companions to clinical judgment at the point of care. 

Abstract PurposeTo examine graduating medical student reports of burnout by sex, race and ethnicity, and sexual orientation and explore trends within intersectional demographic groups from 2019–2021 in a national sample. MethodThe authors obtained medical student responses to the 2019–2021 Association of American Medical Colleges (AAMC) Graduation Questionnaires (GQs) linked to data from other AAMC sources. The dataset included year of GQ completion, responses to a modified Oldenburg Burnout Inventory (exhaustion subscale range: 0–24; disengagement subscale range: 0–15), and demographics previously shown to relate to the risk of burnout in medical students, residents, or physicians. Multivariable linear regression analysis was performed to evaluate independent associations between demographics and burnout. ResultsOverall response rate was 80.7%. After controlling for other factors, mean exhaustion scores were higher among Asian (parameter estimate [PE] 0.38, 95% confidence interval [CI] 0.21, 0.54), bisexual (PE 0.97, 95% CI 0.76, 1.17), and gay or lesbian (PE 0.55, 95% CI 0.35, 0.75) students than those who did not identify with each of those respective groups. Mean disengagement scores were lower among female (PE −0.47, 95% CI −0.52, −0.42), Hispanic (PE −0.11, 95% CI −0.22, −0.01), and White (PE −0.10, 95% CI −0.19, 0.00) students and higher among Asian (PE 0.17, 95% CI 0.07, 0.27), Black or African American (PE 0.31, 95% CI 0.18, 0.44), bisexual (PE 0.54, 95% CI 0.41, 0.66), and gay or lesbian (PE 0.23, 95% CI 0.11, 0.35) students than those who did not identify with each of those respective groups. From 2019–2021, mean exhaustion and disengagement scores were relatively stable or improved across nearly all intersectional groups. ConclusionsMale, Asian, Black or African American, and sexual minority students had a higher risk of burnout, while female, Hispanic, White, and heterosexual or straight students had a lower risk of burnout. 

BackgroundThe occupational burnout epidemic is a growing issue, and in the United States, up to 60% of medical students, residents, physicians, and registered nurses experience symptoms. Wearable technologies may provide an opportunity to predict the onset of burnout and other forms of distress using physiological markers. ObjectiveThis study aims to identify physiological biomarkers of burnout, and establish what gaps are currently present in the use of wearable technologies for burnout prediction among health care professionals (HCPs). MethodsA comprehensive search of several databases was performed on June 7, 2022. No date limits were set for the search. The databases were Ovid: MEDLINE(R), Embase, Healthstar, APA PsycInfo, Cochrane Central Register of Controlled Trials, Cochrane Database of Systematic Reviews, Web of Science Core Collection via Clarivate Analytics, Scopus via Elsevier, EBSCOhost: Academic Search Premier, CINAHL with Full Text, and Business Source Premier. Studies observing anxiety, burnout, stress, and depression using a wearable device worn by an HCP were included, with HCP defined as medical students, residents, physicians, and nurses. Bias was assessed using the Newcastle Ottawa Quality Assessment Form for Cohort Studies. ResultsThe initial search yielded 505 papers, from which 10 (1.95%) studies were included in this review. The majority (n=9) used wrist-worn biosensors and described observational cohort studies (n=8), with a low risk of bias. While no physiological measures were reliably associated with burnout or anxiety, step count and time in bed were associated with depressive symptoms, and heart rate and heart rate variability were associated with acute stress. Studies were limited with long-term observations (eg, ≥12 months) and large sample sizes, with limited integration of wearable data with system-level information (eg, acuity) to predict burnout. Reporting standards were also insufficient, particularly in device adherence and sampling frequency used for physiological measurements. ConclusionsWith wearables offering promise for digital health assessments of human functioning, it is possible to see wearables as a frontier for predicting burnout. Future digital health studies exploring the utility of wearable technologies for burnout prediction should address the limitations of data standardization and strategies to improve adherence and inclusivity in study participation. 

Abstract Pharmacogenomic (PGx) biomarkers integrated using machine learning can be embedded within the electronic health record (EHR) to provide clinicians with individualized predictions of drug treatment outcomes. Currently, however, drug alerts in the EHR are largely generic (not patient‐specific) and contribute to increased clinician stress and burnout. Improving the usability of PGx alerts is an urgent need. Therefore, this work aimed to identify principles for optimal PGx alert design through a health‐system‐wide, mixed‐methods study. Clinicians representing multiple practices and care settings (N = 1062) in urban, rural, and underserved regions were invited to complete an electronic survey comparing the usability of three drug alerts for citalopram, as a case study. Alert 1 contained a generic warning of pharmacogenomic effects on citalopram metabolism. Alerts 2 and 3 provided patient‐specific predictions of citalopram efficacy with varying depth of information. Primary outcomes included the System's Usability Scale score (0–100 points) of each alert, the perceived impact of each alert on stress and decision‐making, and clinicians' suggestions for alert improvement. Secondary outcomes included the assessment of alert preference by clinician age, practice type, and geographic setting. Qualitative information was captured to provide context to quantitative information. The final cohort comprised 305 geographically and clinically diverse clinicians. A simplified, individualized alert (Alert 2) was perceived as beneficial for decision‐making and stress compared with a more detailed version (Alert 3) and the generic alert (Alert 1) regardless of age, practice type, or geographic setting. Findings emphasize the need for clinician‐guided design of PGx alerts in the era of digital medicine. 

BackgroundThe treatment of depression in children and adolescents is a substantial public health challenge. This study examined artificial intelligence tools for the prediction of early outcomes in depressed children and adolescents treated with fluoxetine, duloxetine, or placebo. MethodsThe study samples included training datasets (N = 271) from patients with major depressive disorder (MDD) treated with fluoxetine and testing datasets from patients with MDD treated with duloxetine (N = 255) or placebo (N = 265). Treatment trajectories were generated using probabilistic graphical models (PGMs). Unsupervised machine learning identified specific depressive symptom profiles and related thresholds of improvement during acute treatment. ResultsVariation in six depressive symptoms (difficulty having fun, social withdrawal, excessive fatigue, irritability, low self‐esteem, and depressed feelings) assessed with the Children’s Depression Rating Scale‐Revised at 4–6 weeks predicted treatment outcomes with fluoxetine at 10–12 weeks with an average accuracy of 73% in the training dataset. The same six symptoms predicted 10–12 week outcomes at 4–6 weeks in (a) duloxetine testing datasets with an average accuracy of 76% and (b) placebo‐treated patients with accuracies of 67%. In placebo‐treated patients, the accuracies of predicting response and remission were similar to antidepressants. Accuracies for predicting nonresponse to placebo treatment were significantly lower than antidepressants. ConclusionsPGMs provided clinically meaningful predictions in samples of depressed children and adolescents treated with fluoxetine or duloxetine. Future work should augment PGMs with biological data for refined predictions to guide the selection of pharmacological and psychotherapeutic treatment in children and adolescents with depression. 

Background & Aims Metabolomic and lipidomic analyses provide an opportunity for novel biological insights. Cholangiocarcinoma (CCA) remains a highly lethal cancer with limited response to systemic, targeted, and immunotherapeutic approaches. Using a global metabolomics and lipidomics platform, this study aimed to discover and characterize metabolomic variations and associated pathway derangements in patients with CCA. Methods Leveraging a biospecimen collection, including samples from patients with digestive diseases and normal controls, global serum metabolomic and lipidomic profiling was performed on 213 patients with CCA and 98 healthy controls. The CCA cohort of patients included representation of intrahepatic, perihilar, and distal CCA tumours. Metabolome-wide association studies utilizing multivariable linear regression were used to perform case–control comparisons, followed by pathway enrichment analysis, CCA subtype analysis, and disease stage analysis. The impact of biliary obstruction was evaluated by repeating analyses in subsets of patients only with normal bilirubin levels. Results Of the 420 metabolites that discriminated patients with CCA from controls, decreased abundance of cysteine-glutathione disulfide was most closely associated with CCA. Additional conjugated bile acid species were found in increased abundance even in the absence of clinically relevant biliary obstruction denoted by elevated serum bilirubin levels. Pathway enrichment analysis also revealed alterations in caffeine metabolism and mitochondrial redox-associated pathways in the serum of patients with CCA. Conclusions The presented metabolomic and lipidomic profiling demonstrated multiple alterations in the serum of patients with CCA. These exploratory data highlight novel metabolic pathways in CCA and support future work in therapeutic targeting of these pathways and the development of a precision biomarker panel for diagnosis.