Machine learning for detection of heterogeneous effects of Medicaid coverage on depression.

In 2008, Oregon expanded its Medicaid program using a lottery, creating a rare opportunity to study the effects of Medicaid coverage using a randomized controlled design (Oregon Health Insurance Experiment). Analysis showed that Medicaid coverage lowered the risk of depression. However, this effect may vary between individuals, and the identification of individuals likely to benefit the most has the potential to improve the effectiveness and efficiency of the Medicaid program. By applying the machine learning causal forest to data from this experiment, we found substantial heterogeneity in the effect of Medicaid coverage on depression; individuals with high predicted benefit were older and had more physical or mental health conditions at baseline. Expanding coverage to individuals with high predicted benefit generated greater reduction in depression prevalence than expanding to all eligible individuals (21.5 vs 8.8 percentage-point reduction; adjusted difference = +12.7 [95% CI, +4.6 to +20.8]; P = 0.003), at substantially lower cost per case prevented ($16 627 vs $36 048; adjusted difference = -$18 598 [95% CI, -156 953 to -3120]; P = 0.04). Medicaid coverage reduces depression substantially more in a subset of the population than others, in ways that are predictable in advance. Targeting coverage on those most likely to benefit could improve the effectiveness and efficiency of insurance expansion. This article is part of a Special Collection on Mental Health.

Characterizing the limitations of using diagnosis codes in the context of machine learning for healthcare.

BACKGROUND: Diagnostic codes are commonly used as inputs for clinical prediction models, to create labels for prediction tasks, and to identify cohorts for multicenter network studies. However, the coverage rates of diagnostic codes and their variability across institutions are underexplored. The primary objective was to describe lab- and diagnosis-based labels for 7 selected outcomes at three institutions. Secondary objectives were to describe agreement, sensitivity, and specificity of diagnosis-based labels against lab-based labels. METHODS: This study included three cohorts: SickKids from The Hospital for Sick Children, and StanfordPeds and StanfordAdults from Stanford Medicine. We included seven clinical outcomes with lab-based definitions: acute kidney injury, hyperkalemia, hypoglycemia, hyponatremia, anemia, neutropenia and thrombocytopenia. For each outcome, we created four lab-based labels (abnormal, mild, moderate and severe) based on test result and one diagnosis-based label. Proportion of admissions with a positive label were presented for each outcome stratified by cohort. Using lab-based labels as the gold standard, agreement using Cohen's Kappa, sensitivity and specificity were calculated for each lab-based severity level. RESULTS: The number of admissions included were: SickKids (n = 59,298), StanfordPeds (n = 24,639) and StanfordAdults (n = 159,985). The proportion of admissions with a positive diagnosis-based label was significantly higher for StanfordPeds compared to SickKids across all outcomes, with odds ratio (99.9% confidence interval) for abnormal diagnosis-based label ranging from 2.2 (1.7-2.7) for neutropenia to 18.4 (10.1-33.4) for hyperkalemia. Lab-based labels were more similar by institution. When using lab-based labels as the gold standard, Cohen's Kappa and sensitivity were lower at SickKids for all severity levels compared to StanfordPeds. CONCLUSIONS: Across multiple outcomes, diagnosis codes were consistently different between the two pediatric institutions. This difference was not explained by differences in test results. These results may have implications for machine learning model development and deployment.

Detecting Developmental Delay and Autism Through Machine Learning Models Using Home Videos of Bangladeshi Children: Development and Validation Study.

BACKGROUND: Autism spectrum disorder (ASD) is currently diagnosed using qualitative methods that measure between 20-100 behaviors, can span multiple appointments with trained clinicians, and take several hours to complete. In our previous work, we demonstrated the efficacy of machine learning classifiers to accelerate the process by collecting home videos of US-based children, identifying a reduced subset of behavioral features that are scored by untrained raters using a machine learning classifier to determine children's "risk scores" for autism. We achieved an accuracy of 92% (95% CI 88%-97%) on US videos using a classifier built on five features. OBJECTIVE: Using videos of Bangladeshi children collected from Dhaka Shishu Children's Hospital, we aim to scale our pipeline to another culture and other developmental delays, including speech and language conditions. METHODS: Although our previously published and validated pipeline and set of classifiers perform reasonably well on Bangladeshi videos (75% accuracy, 95% CI 71%-78%), this work improves on that accuracy through the development and application of a powerful new technique for adaptive aggregation of crowdsourced labels. We enhance both the utility and performance of our model by building two classification layers: The first layer distinguishes between typical and atypical behavior, and the second layer distinguishes between ASD and non-ASD. In each of the layers, we use a unique rater weighting scheme to aggregate classification scores from different raters based on their expertise. We also determine Shapley values for the most important features in the classifier to understand how the classifiers' process aligns with clinical intuition. RESULTS: Using these techniques, we achieved an accuracy (area under the curve [AUC]) of 76% (SD 3%) and sensitivity of 76% (SD 4%) for identifying atypical children from among developmentally delayed children, and an accuracy (AUC) of 85% (SD 5%) and sensitivity of 76% (SD 6%) for identifying children with ASD from those predicted to have other developmental delays. CONCLUSIONS: These results show promise for using a mobile video-based and machine learning-directed approach for early and remote detection of autism in Bangladeshi children. This strategy could provide important resources for developmental health in developing countries with few clinical resources for diagnosis, helping children get access to care at an early age. Future research aimed at extending the application of this approach to identify a range of other conditions and determine the population-level burden of developmental disabilities and impairments will be of high value.

Aspiration Thrombectomy versus Conventional Catheter-Directed Thrombolysis as First-Line Treatment for Noniatrogenic Acute Lower Limb Ischemia.

PURPOSE: To examine the efficacy, safety, and procedural costs of percutaneous aspiration thrombectomy (PAT) as a first-line treatment for noniatrogenic acute lower limb ischemia (ALI) compared with conventional catheter-directed thrombolysis (CDT). MATERIALS AND METHODS: All patients who underwent endovascular intervention for ALI from January 2015 to August 2017 were included. Fifteen patients were treated with the use of primary PAT and 27 patients were treated with the use of primary CDT. The primary end point was complete thrombus clearance with improvement in Thrombolysis in Myocardial Infarction (TIMI) score. Adjunctive treatment for thrombus removal was considered to indicate technical failure. Treatment of underlying chronic disease was not considered to indicate technical failure. Procedural costs for each patient were calculated by itemizing all disposable equipment, facility overheads, and staff costs. RESULTS: Of the 15 primary PAT patients, technical success was achieved in 8 (53%); the remaining 7 (47%) required adjunctive CDT. Of the 27 primary CDT patients, technical success was achieved in 25 (89%); the remaining 2 (11%) required adjunctive PAT. There were 4 complications in the primary PAT group: 2 were procedure related and of a minor grade. There were 8 complications in the primary CDT group: All were procedure-related, including 2 major groin/retroperitoneal hemorrhage and 1 death from intracranial hemorrhage. Limb salvage was attained in all patients. There were no significant differences in average procedural costs per patient between the 2 groups. CONCLUSIONS: First-line use of PAT for endovascular treatment of ALI can reduce the need for CDT, with no significant cost difference.

Design of nanostructures based on aromatic peptide amphiphiles.

Aromatic peptide amphiphiles are gaining popularity as building blocks for the bottom-up fabrication of nanomaterials, including gels. These materials combine the simplicity of small molecules with the versatility of peptides, with a range of applications proposed in biomedicine, nanotechnology, food science, cosmetics, etc. Despite their simplicity, a wide range of self-assembly behaviours have been described. Due to varying conditions and protocols used, care should be taken when attempting to directly compare results from the literature. In this review, we rationalise the structural features which govern the self-assembly of aromatic peptide amphiphiles by focusing on four segments, (i) the N-terminal aromatic component, (ii) linker segment, (iii) peptide sequence, and (iv) C-terminus. It is clear that the molecular structure of these components significantly influences the self-assembly process and resultant supramolecular architectures. A number of modes of assembly have been proposed, including parallel, antiparallel, and interlocked antiparallel stacking conformations. In addition, the co-assembly arrangements of aromatic peptide amphiphiles are reviewed. Overall, this review elucidates the structural trends and design rules that underpin the field of aromatic peptide amphiphile assembly, paving the way to a more rational design of nanomaterials based on aromatic peptide amphiphiles.

Differential self-assembly and tunable emission of aromatic peptide bola-amphiphiles containing perylene bisimide in polar solvents including water.

We demonstrate the self-assembly of bola-amphiphile-type conjugates of dipeptides and perylene bisimide (PBI) in water and other polar solvents. Depending on the nature of the peptide used (glycine-tyrosine, GY, or glycine-aspartic acid, GD), the balance between H-bonding and aromatic stacking can be tailored. In aqueous buffer, PBI-[GY]2 forms chiral nanofibers, resulting in the formation of a hydrogel, while for PBI-[GD]2 achiral spherical aggregates are formed, demonstrating that the peptide sequence has a profound effect on the structure formed. In water and a range of other polar solvents, self-assembly of these two PBI-peptides conjugates results in different nanostructures with highly tunable fluorescence performance depending on the peptide sequence employed, e.g., fluorescent emission and quantum yield. Organogels are formed for the PBI-[GD]2 derivative in DMF and DMSO while PBI-[GY]2 gels in DMF. To the best of our knowledge, this is the first successful strategy for using short peptides, specifically, their sequence/structure relationships, to manipulate the PBI nanostructure and consequent optical properties. The combination of controlled self-assembly, varied optical properties, and formation of aqueous and organic gel-phase materials may facilitate the design of devices for various applications related to light harvesting and sensing.

Insights into the coassembly of hydrogelators and surfactants based on aromatic peptide amphiphiles.

The coassembly of small molecules is a useful means of increasing the complexity and functionality of their resultant supramolecular constructs in a modular fashion. In this study, we explore the assembly and coassembly of serine surfactants and tyrosine-leucine hydrogelators, capped at the N-termini with either fluorenyl-9-methoxycarbonyl (Fmoc) or pyrene. These systems all exhibit self-assembly behavior, which is influenced by aromatic stacking interactions, while the hydrogelators also exhibit ß-sheet-type arrangements, which reinforce their supramolecular structures. We provide evidence for three distinct supramolecular coassembly models; cooperative, disruptive, and orthogonal. The coassembly mode adopted depends on whether the individual constituents (I) are sufficiently different, such that effective segregation and orthogonal assembly occurs; (II) adhere to a communal mode of self-assembly; or (III) act to compromise the assembly of one another via incorporation and disruption. We find that a greater scope for controllable coassembly exists within orthogonal systems; which show minimal relative changes in the native gelator's supramolecular structure by Fourier transform infrared spectroscopy (FTIR), circular dichroism (CD), and fluorescence spectroscopy. This is indicative of the segregation of orthogonal coassembly constituents into distinct domains, where surfactant chemical functionality is presented at the surface of the gelator's supramolecular fibers. Overall, this work provides new insights into the design of modular coassembly systems, which have the potential to augment the chemical and physical properties of existing gelator systems.

The effect of shear stress on the size, structure, and function of human von Willebrand factor.

Clinical outcomes from ventricular assist devices (VADs) have improved significantly during recent decades, but bleeding episodes remain a common complication of long-term VAD usage. Greater understanding of the effect of the shear stress in the VAD on platelet aggregation, which is influenced by the functional activity of high molecular weight (HMW) von Willebrand factor (vWF), could provide insight into these bleeding complications. However, because VAD shear rates are difficult to assess, there is a need for a model that enables controlled shear rates to first establish the relationship between shear rates and vWF damage. Secondly, if such a dependency exists, then it is relevant to establish a rapid and quantitative assay that can be used routinely for the safety assessment of new VADs in development. Therefore, the purpose of this study was to exert vWF to controlled levels of shear using a rheometer, and flow cytometry was used to investigate the shear-dependent effect on the functional activity of vWF. Human platelet-poor plasma (PPP) was subjected to different shear rate levels ranging from 0 to 8000/s for a period of 6 h using a rheometer. A simple and rapid flow cytometric assay was used to determine platelet aggregation in the presence of ristocetin cofactor as a readout for vWF activity. Platelet aggregates were visualized by confocal microscopy. Multimers of vWF were detected using gel electrophoresis and immunoblotting. The longer PPP was exposed to high shear, the greater the loss of HMW vWF multimers, and the lower the functional activity of vWF for platelet aggregation. Confocal microscopy revealed for the first time that platelet aggregates were smaller and more dispersed in postsheared PPP compared with nonsheared PPP. The loss of HMW vWF in postsheared PPP was demonstrated by immunoblotting. Smaller vWF platelet aggregates formed in response to shear stress might be a cause of bleeding in patients implanted with VADs. The methodological approaches used herein could be useful in the design of safer VADs and other blood handling devices. In particular, we have demonstrated a correlation between the loss of HMW vWF, analyzed by immunoblotting, with platelet aggregation, assessed by flow cytometry. This suggests that flow cytometry could replace conventional immunoblotting as a simple and rapid routine test for HMW vWF loss during in vitro testing of devices.

Clinfo.ai: An Open-Source Retrieval-Augmented Large Language Model System for Answering Medical Questions using Scientific Literature.

The quickly-expanding nature of published medical literature makes it challenging for clinicians and researchers to keep up with and summarize recent, relevant findings in a timely manner. While several closed-source summarization tools based on large language models (LLMs) now exist, rigorous and systematic evaluations of their outputs are lacking. Furthermore, there is a paucity of high-quality datasets and appropriate benchmark tasks with which to evaluate these tools. We address these issues with four contributions: we release Clinfo.ai, an open-source WebApp that answers clinical questions based on dynamically retrieved scientific literature; we specify an information retrieval and abstractive summarization task to evaluate the performance of such retrieval-augmented LLM systems; we release a dataset of 200 questions and corresponding answers derived from published systematic reviews, which we name PubMed Retrieval and Synthesis (PubMedRS-200); and report benchmark results for Clinfo.ai and other publicly available OpenQA systems on PubMedRS-200.

A multi-center study on the adaptability of a shared foundation model for electronic health records.

Foundation models are transforming artificial intelligence (AI) in healthcare by providing modular components adaptable for various downstream tasks, making AI development more scalable and cost-effective. Foundation models for structured electronic health records (EHR), trained on coded medical records from millions of patients, demonstrated benefits including increased performance with fewer training labels, and improved robustness to distribution shifts. However, questions remain on the feasibility of sharing these models across hospitals and their performance in local tasks. This multi-center study examined the adaptability of a publicly accessible structured EHR foundation model (FMSM), trained on 2.57 M patient records from Stanford Medicine. Experiments used EHR data from The Hospital for Sick Children (SickKids) and Medical Information Mart for Intensive Care (MIMIC-IV). We assessed both adaptability via continued pretraining on local data, and task adaptability compared to baselines of locally training models from scratch, including a local foundation model. Evaluations on 8 clinical prediction tasks showed that adapting the off-the-shelf FMSM matched the performance of gradient boosting machines (GBM) locally trained on all data while providing a 13% improvement in settings with few task-specific training labels. Continued pretraining on local data showed FMSM required fewer than 1% of training examples to match the fully trained GBM's performance, and was 60 to 90% more sample-efficient than training local foundation models from scratch. Our findings demonstrate that adapting EHR foundation models across hospitals provides improved prediction performance at less cost, underscoring the utility of base foundation models as modular components to streamline the development of healthcare AI.

Pickering stabilized peptide gel particles as tunable microenvironments for biocatalysis.

We demonstrate the preparation of peptide gel microparticles that are emulsified and stabilized by SiO2 nanoparticles. The gels are composed of aromatic peptide amphiphiles 9-fluorenylmethoxycarbonyldiphenylalanine (Fmoc-FF) coassembled with Fmoc-amino acids with different functional groups (S: serine; D: aspartic acid; K: lysine; and Y: tyrosine). The gel phase provides a highly hydrated matrix, and peptide self-assembly endows the matrix with tunable chemical environments which may be exploited to support and stabilize proteins. The use of Pickering emulsion to stabilize these gel particles is advantageous through avoidance of surfactants that may denature proteins. The performance of enzyme lipase B immobilized in pickering/gel microparticles with different chemical functionalities is investigated by studying transesterification in heptane. We show that the use of Pickering particles enhances the performance of the enzyme, which is further improved in gel-phase systems, with hydrophilic environment provided by Fmoc-FF/S giving rise to the best catalytic performance. The combination of a tunable chemical environment in gel phase and Pickering stabilization described here is expected to prove useful for areas where proteins are to be exploited in technological contexts such as biocatalysis and also in other areas where protein performance and activity are important, such as biosensors and bioinspired solar fuel devices.

Assessing the utility of infrared spectroscopy as a structural diagnostic tool for ß-sheets in self-assembling aromatic peptide amphiphiles.

ß-Sheets are a commonly found structural motif in self-assembling aromatic peptide amphiphiles, and their characteristic "amide I" infrared (IR) absorption bands are routinely used to support the formation of supramolecular structure. In this paper, we assess the utility of IR spectroscopy as a structural diagnostic tool for this class of self-assembling systems. Using 9-fluorene-methyloxycarbonyl dialanine (Fmoc-AA) and the analogous 9-fluorene-methylcarbonyl dialanine (Fmc-AA) as examples, we show that the origin of the band around 1680-1695 cm(-1) in Fourier transform infrared (FTIR) spectra, which was previously assigned to an antiparallel ß-sheet conformation, is in fact absorption of the stacked carbamate group in Fmoc-peptides. IR spectra from (13)C-labeled samples support our conclusions. In addition, DFT frequency calculations on small stacks of aromatic peptides help to rationalize these results in terms of the individual vibrational modes.

EHR foundation models improve robustness in the presence of temporal distribution shift.

Temporal distribution shift negatively impacts the performance of clinical prediction models over time. Pretraining foundation models using self-supervised learning on electronic health records (EHR) may be effective in acquiring informative global patterns that can improve the robustness of task-specific models. The objective was to evaluate the utility of EHR foundation models in improving the in-distribution (ID) and out-of-distribution (OOD) performance of clinical prediction models. Transformer- and gated recurrent unit-based foundation models were pretrained on EHR of up to 1.8 M patients (382 M coded events) collected within pre-determined year groups (e.g., 2009-2012) and were subsequently used to construct patient representations for patients admitted to inpatient units. These representations were used to train logistic regression models to predict hospital mortality, long length of stay, 30-day readmission, and ICU admission. We compared our EHR foundation models with baseline logistic regression models learned on count-based representations (count-LR) in ID and OOD year groups. Performance was measured using area-under-the-receiver-operating-characteristic curve (AUROC), area-under-the-precision-recall curve, and absolute calibration error. Both transformer and recurrent-based foundation models generally showed better ID and OOD discrimination relative to count-LR and often exhibited less decay in tasks where there is observable degradation of discrimination performance (average AUROC decay of 3% for transformer-based foundation model vs. 7% for count-LR after 5-9 years). In addition, the performance and robustness of transformer-based foundation models continued to improve as pretraining set size increased. These results suggest that pretraining EHR foundation models at scale is a useful approach for developing clinical prediction models that perform well in the presence of temporal distribution shift.

Evaluation of Feature Selection Methods for Preserving Machine Learning Performance in the Presence of Temporal Dataset Shift in Clinical Medicine.

BACKGROUND: Temporal dataset shift can cause degradation in model performance as discrepancies between training and deployment data grow over time. The primary objective was to determine whether parsimonious models produced by specific feature selection methods are more robust to temporal dataset shift as measured by out-of-distribution (OOD) performance, while maintaining in-distribution (ID) performance. METHODS: Our dataset consisted of intensive care unit patients from MIMIC-IV categorized by year groups (2008-2010, 2011-2013, 2014-2016, and 2017-2019). We trained baseline models using L2-regularized logistic regression on 2008-2010 to predict in-hospital mortality, long length of stay (LOS), sepsis, and invasive ventilation in all year groups. We evaluated three feature selection methods: L1-regularized logistic regression (L1), Remove and Retrain (ROAR), and causal feature selection. We assessed whether a feature selection method could maintain ID performance (2008-2010) and improve OOD performance (2017-2019). We also assessed whether parsimonious models retrained on OOD data performed as well as oracle models trained on all features in the OOD year group. RESULTS: The baseline model showed significantly worse OOD performance with the long LOS and sepsis tasks when compared with the ID performance. L1 and ROAR retained 3.7 to 12.6% of all features, whereas causal feature selection generally retained fewer features. Models produced by L1 and ROAR exhibited similar ID and OOD performance as the baseline models. The retraining of these models on 2017-2019 data using features selected from training on 2008-2010 data generally reached parity with oracle models trained directly on 2017-2019 data using all available features. Causal feature selection led to heterogeneous results with the superset maintaining ID performance while improving OOD calibration only on the long LOS task. CONCLUSIONS: While model retraining can mitigate the impact of temporal dataset shift on parsimonious models produced by L1 and ROAR, new methods are required to proactively improve temporal robustness.

The shaky foundations of large language models and foundation models for electronic health records.

The success of foundation models such as ChatGPT and AlphaFold has spurred significant interest in building similar models for electronic medical records (EMRs) to improve patient care and hospital operations. However, recent hype has obscured critical gaps in our understanding of these models' capabilities. In this narrative review, we examine 84 foundation models trained on non-imaging EMR data (i.e., clinical text and/or structured data) and create a taxonomy delineating their architectures, training data, and potential use cases. We find that most models are trained on small, narrowly-scoped clinical datasets (e.g., MIMIC-III) or broad, public biomedical corpora (e.g., PubMed) and are evaluated on tasks that do not provide meaningful insights on their usefulness to health systems. Considering these findings, we propose an improved evaluation framework for measuring the benefits of clinical foundation models that is more closely grounded to metrics that matter in healthcare.

Self-supervised machine learning using adult inpatient data produces effective models for pediatric clinical prediction tasks.

OBJECTIVE: Development of electronic health records (EHR)-based machine learning models for pediatric inpatients is challenged by limited training data. Self-supervised learning using adult data may be a promising approach to creating robust pediatric prediction models. The primary objective was to determine whether a self-supervised model trained in adult inpatients was noninferior to logistic regression models trained in pediatric inpatients, for pediatric inpatient clinical prediction tasks. MATERIALS AND METHODS: This retrospective cohort study used EHR data and included patients with at least one admission to an inpatient unit. One admission per patient was randomly selected. Adult inpatients were 18 years or older while pediatric inpatients were more than 28 days and less than 18 years. Admissions were temporally split into training (January 1, 2008 to December 31, 2019), validation (January 1, 2020 to December 31, 2020), and test (January 1, 2021 to August 1, 2022) sets. Primary comparison was a self-supervised model trained in adult inpatients versus count-based logistic regression models trained in pediatric inpatients. Primary outcome was mean area-under-the-receiver-operating-characteristic-curve (AUROC) for 11 distinct clinical outcomes. Models were evaluated in pediatric inpatients. RESULTS: When evaluated in pediatric inpatients, mean AUROC of self-supervised model trained in adult inpatients (0.902) was noninferior to count-based logistic regression models trained in pediatric inpatients (0.868) (mean difference = 0.034, 95% CI=0.014-0.057; P < .001 for noninferiority and P = .006 for superiority). CONCLUSIONS: Self-supervised learning in adult inpatients was noninferior to logistic regression models trained in pediatric inpatients. This finding suggests transferability of self-supervised models trained in adult patients to pediatric patients, without requiring costly model retraining.

Intrinsic Connectivity and Family Dynamics: Striatolimbic Markers of Risk and Resilience in Youth at Familial Risk for Mood Disorders.

BACKGROUND: Few studies to date have characterized functional connectivity (FC) within emotion and reward networks in relation to family dynamics in youth at high familial risk for bipolar disorder (HR-BD) and major depressive disorder (HR-MDD) relative to low-risk youth (LR). Such characterization may advance our understanding of the neural underpinnings of mood disorders and lead to more effective interventions. METHODS: A total of 139 youth (43 HR-BD, 46 HR-MDD, and 50 LR) aged 12.9 ± 2.7 years were longitudinally followed for 4.5 ± 2.4 years. We characterized differences in striatolimbic FC that distinguished between HR-BD, HR-MDD, and LR and between resilience and conversion to psychopathology. We then examined whether risk status moderated FC-family dynamic associations. Finally, we examined whether baseline between-group FC differences predicted resilence versus conversion to psychopathology. RESULTS: HR-BD had greater amygdala-middle frontal gyrus and dorsal striatum-middle frontal gyrus FC relative to HR-MDD and LR, and HR-MDD had lower amygdala-fusiform gyrus and dorsal striatum-precentral gyrus FC relative to HR-BD and LR (voxel-level p < .001, cluster-level false discovery rate-corrected p < .05). Resilient youth had greater amygdala-orbitofrontal cortex and ventral striatum-dorsal anterior cingulate cortex FC relative to youth with conversion to psychopathology (voxel-level p < .001, cluster-level false discovery rate-corrected p < .05). Greater family rigidity was inversely associated with amygdala-fusiform gyrus FC across all groups (false discovery rate-corrected p = .017), with a moderating effect of bipolar risk status (HR-BD vs. HR-MDD p < .001; HR-BD vs. LR p = .005). Baseline FC differences did not predict resilence versus conversion to psychopathology. CONCLUSIONS: Findings represent neural signatures of risk and resilience in emotion and reward processing networks in youth at familial risk for mood disorders that may be targets for novel interventions tailored to the family context.

Perspective Toward Machine Learning Implementation in Pediatric Medicine: Mixed Methods Study.

BACKGROUND: Given the costs of machine learning implementation, a systematic approach to prioritizing which models to implement into clinical practice may be valuable. OBJECTIVE: The primary objective was to determine the health care attributes respondents at 2 pediatric institutions rate as important when prioritizing machine learning model implementation. The secondary objective was to describe their perspectives on implementation using a qualitative approach. METHODS: In this mixed methods study, we distributed a survey to health system leaders, physicians, and data scientists at 2 pediatric institutions. We asked respondents to rank the following 5 attributes in terms of implementation usefulness: the clinical problem was common, the clinical problem caused substantial morbidity and mortality, risk stratification led to different actions that could reasonably improve patient outcomes, reducing physician workload, and saving money. Important attributes were those ranked as first or second most important. Individual qualitative interviews were conducted with a subsample of respondents. RESULTS: Among 613 eligible respondents, 275 (44.9%) responded. Qualitative interviews were conducted with 17 respondents. The most common important attributes were risk stratification leading to different actions (205/275, 74.5%) and clinical problem causing substantial morbidity or mortality (177/275, 64.4%). The attributes considered least important were reducing physician workload and saving money. Qualitative interviews consistently prioritized implementations that improved patient outcomes. CONCLUSIONS: Respondents prioritized machine learning model implementation where risk stratification would lead to different actions and clinical problems that caused substantial morbidity and mortality. Implementations that improved patient outcomes were prioritized. These results can help provide a framework for machine learning model implementation.

Performance of a Commonly Used Pressure Injury Risk Model Under Changing Incidence.

BACKGROUND: Hospital-acquired pressure injuries (HAPIs) cause patient harm and increase health care costs. We sought to evaluate the performance of the Braden QD Scale-associated changes in HAPI incidence. METHODS: Using electronic health records data from a quaternary children's hospital, we evaluated the association between Braden QD scores and patient risk of HAPI. We analyzed how this relationship changed during a hospitalwide quality HAPI reduction initiative. RESULTS: Of 23,532 unique patients, 108 (0.46%, 95% confidence interval [CI] = 0.38%-0.55%) experienced a HAPI. Every 1-point increase in the Braden QD score was associated with a 41% increase in the patient's odds of developing a HAPI (odds ratio [OR] = 1.41, 95% CI = 1.36-1.46, p < 0.001). HAPI incidence declined significantly following implementation of a HAPI-reduction initiative (ß = -0.09, 95% CI = -0.11 - -0.07, p < 0.001), as did Braden QD positive predictive value (ß = -0.29, 95% CI = -0.44 - -0.14, p < 0.001) and specificity (ß = -0.28, 95% CI = -0.43 - -0.14, p < 0.001), while sensitivity (ß = 0.93, 95% CI = 0.30-1.75, p = 0.01) and the concordance statistic (ß = 0.18, 95% CI = 0.15-0.21, p < 0.001) increased significantly. CONCLUSION: Decreases in HAPI incidence following a quality improvement initiative were associated with (1) significant deterioration in threshold-dependent performance measures such as specificity and precision and (2) significant improvements in threshold-independent performance measures such as the concordance statistic. The performance of the Braden QD Scale is more stable as a tool that continuously measures risk than as a prediction tool.

Mapping Neural Circuit Biotypes to Symptoms and Behavioral Dimensions of Depression and Anxiety.

BACKGROUND: Despite tremendous advances in characterizing human neural circuits that govern emotional and cognitive functions impaired in depression and anxiety, we lack a circuit-based taxonomy for depression and anxiety that captures transdiagnostic heterogeneity and informs clinical decision making. METHODS: We developed and tested a novel system for quantifying 6 brain circuits reproducibly and at the individual patient level. We implemented standardized circuit definitions relative to a healthy reference sample and algorithms to generate circuit clinical scores for the overall circuit and its constituent regions. RESULTS: In new data from primary and generalizability samples of depression and anxiety (N = 250), we demonstrated that overall disconnections within task-free salience and default mode circuits map onto symptoms of anxious avoidance, loss of pleasure, threat dysregulation, and negative emotional biases-core characteristics that transcend diagnoses-and poorer daily function. Regional dysfunctions within task-evoked cognitive control and affective circuits may implicate symptoms of cognitive and valence-congruent emotional functions. Circuit dysfunction scores also distinguished response to antidepressant and behavioral intervention treatments in an independent sample (n = 205). CONCLUSIONS: Our findings articulate circuit dimensions that relate to transdiagnostic symptoms across mood and anxiety disorders. Our novel system offers a foundation for deploying standardized circuit assessments across research groups, trials, and clinics to advance more precise classifications and treatment targets for psychiatry.