Optimised Multi-Channel Transcranial Direct Current Stimulation (MtDCS) Reveals Differential Involvement of the Right-Ventrolateral Prefrontal Cortex (rVLPFC) and Insular Complex in those Predisposed to Aberrant Experiences.

Research has shown a prominent role for cortical hyperexcitability underlying aberrant perceptions, hallucinations, and distortions in human conscious experience - even in neurotypical groups. The rVLPFC has been identified as an important structure in mediating cognitive affective states / feeling conscious states. The current study examined the involvement of the rVLPFC in mediating cognitive affective states in those predisposed to aberrant experiences in the neurotypical population. Participants completed two trait-based measures: (i) the Cortical Hyperexcitability Index_II (CHi_II, a proxy measure of cortical hyperexcitability) and (ii) two factors from the Cambridge Depersonalisation Scale (CDS). An optimised 7-channel MtDCS montage for stimulation conditions (Anodal, Cathodal and Sham) was created targeting the rVLPFC in a single-blind study. At the end of each stimulation session, participants completed a body-threat task (BTAB) while skin conductance responses (SCRs) and psychological responses were recorded. Participants with signs of increasing cortical hyperexcitability showed significant suppression of SCRs in the Cathodal stimulation relative to the Anodal and sSham conditions. Those high on the trait-based measures of depersonalisation-like experiences failed to show reliable effects. Collectively, the findings suggest that baseline brain states can mediate the effects of neurostimulation which would be missed via sample level averaging and without appropriate measures for stratifying individual differences.

Prevalence and incidence measures for schizophrenia among commercial health insurance and medicaid enrollees.

Given the chronic nature of schizophrenia, it is important to examine age-specific prevalence and incidence to understand the scope of the burden of schizophrenia across the lifespan. Estimates of lifetime prevalence of schizophrenia have varied widely and have often relied upon community-based data estimates from over two decades ago, while more recent studies have shown considerable promise by leveraging pooled datasets. However, the validity of measures of schizophrenia, particularly new onset schizophrenia, has not been well studied in these large health databases. The current study examines prevalence and validity of incidence measures of new diagnoses of schizophrenia in 2019 using two U.S. administrative health databases: MarketScan, a national database of individuals receiving employer-sponsored commercial insurance (N = 16,365,997), and NYS Medicaid, a large state public insurance program (N = 4,414,153). Our results indicate that the prevalence of schizophrenia is over 10-fold higher, and the incidence two-fold higher, in the NYS Medicaid population compared to the MarketScan database. In addition, prevalence increased over the lifespan in the Medicaid population, but decreased in the employment based MarketScan database beginning in early adulthood. Incident measures of new diagnoses of schizophrenia had excellent validity, with positive predictive values and specificity exceeding 95%, but required a longer lookback period for Medicaid compared to MarketScan. Further work is needed to leverage these findings to develop robust clinical outcome predictors for new onset of schizophrenia within large administrative health data systems.

A normative framework for artificial intelligence as a sociotechnical system in healthcare.

Artificial intelligence (AI) tools are of great interest to healthcare organizations for their potential to improve patient care, yet their translation into clinical settings remains inconsistent. One of the reasons for this gap is that good technical performance does not inevitably result in patient benefit. We advocate for a conceptual shift wherein AI tools are seen as components of an intervention ensemble. The intervention ensemble describes the constellation of practices that, together, bring about benefit to patients or health systems. Shifting from a narrow focus on the tool itself toward the intervention ensemble prioritizes a "sociotechnical" vision for translation of AI that values all components of use that support beneficial patient outcomes. The intervention ensemble approach can be used for regulation, institutional oversight, and for AI adopters to responsibly and ethically appraise, evaluate, and use AI tools.

Making machine learning matter to clinicians: model actionability in medical decision-making.

Machine learning (ML) has the potential to transform patient care and outcomes. However, there are important differences between measuring the performance of ML models in silico and usefulness at the point of care. One lens to use to evaluate models during early development is actionability, which is currently undervalued. We propose a metric for actionability intended to be used before the evaluation of calibration and ultimately decision curve analysis and calculation of net benefit. Our metric should be viewed as part of an overarching effort to increase the number of pragmatic tools that identify a model's possible clinical impacts.

Probabilistic Machine Learning for Healthcare.

Machine learning can be used to make sense of healthcare data. Probabilistic machine learning models help provide a complete picture of observed data in healthcare. In this review, we examine how probabilistic machine learning can advance healthcare. We consider challenges in the predictive model building pipeline where probabilistic models can be beneficial, including calibration and missing data. Beyond predictive models, we also investigate the utility of probabilistic machine learning models in phenotyping, in generative models for clinical use cases, and in reinforcement learning.

Ethical Machine Learning in Healthcare.

The use of machine learning (ML) in healthcare raises numerous ethical concerns, especially as models can amplify existing health inequities. Here, we outline ethical considerations for equitable ML in the advancement of healthcare. Specifically, we frame ethics of ML in healthcare through the lens of social justice. We describe ongoing efforts and outline challenges in a proposed pipeline of ethical ML in health, ranging from problem selection to postdeployment considerations. We close by summarizing recommendations to address these challenges.

Short-Term Immobilization Promotes a Rapid Loss of Motor Evoked Potentials and Strength That Is Not Rescued by rTMS Treatment.

Short-term limb immobilization results in skeletal muscle decline, but the underlying mechanisms are incompletely understood. This study aimed to determine the neurophysiologic basis of immobilization-induced skeletal muscle decline, and whether repetitive Transcranial Magnetic Stimulation (rTMS) could prevent any decline. Twenty-four healthy young males (20 ± 0.5 years) underwent unilateral limb immobilization for 72 h. Subjects were randomized between daily rTMS (n = 12) using six 20 Hz pulse trains of 1.5 s duration with a 60 s inter-train-interval delivered at 90% resting Motor Threshold (rMT), or Sham rTMS (n = 12) throughout immobilization. Maximal grip strength, EMG activity, arm volume, and composition were determined at 0 and 72 h. Motor Evoked Potentials (MEPs) were determined daily throughout immobilization to index motor excitability. Immobilization induced a significant reduction in motor excitability across time (-30% at 72 h; p < 0.05). The rTMS intervention increased motor excitability at 0 h (+13%, p < 0.05). Despite daily rTMS treatment, there was still a significant reduction in motor excitability (-33% at 72 h, p < 0.05), loss in EMG activity (-23.5% at 72 h; p < 0.05), and a loss of maximal grip strength (-22%, p < 0.001) after immobilization. Interestingly, the increase in biceps (Sham vs. rTMS) (+0.8 vs. +0.1 mm, p < 0.01) and posterior forearm (+0.3 vs. +0.0 mm, p < 0.05) skinfold thickness with immobilization in Sham treatment was not observed following rTMS treatment. Reduced MEPs drive the loss of strength with immobilization. Repetitive Transcranial Magnetic Stimulation cannot prevent this loss of strength but further investigation and optimization of neuroplasticity protocols may have therapeutic benefit.

Patient safety and quality improvement: Ethical principles for a regulatory approach to bias in healthcare machine learning.

Accumulating evidence demonstrates the impact of bias that reflects social inequality on the performance of machine learning (ML) models in health care. Given their intended placement within healthcare decision making more broadly, ML tools require attention to adequately quantify the impact of bias and reduce its potential to exacerbate inequalities. We suggest that taking a patient safety and quality improvement approach to bias can support the quantification of bias-related effects on ML. Drawing from the ethical principles underpinning these approaches, we argue that patient safety and quality improvement lenses support the quantification of relevant performance metrics, in order to minimize harm while promoting accountability, justice, and transparency. We identify specific methods for operationalizing these principles with the goal of attending to bias to support better decision making in light of controllable and uncontrollable factors.