Lateral hypothalamic glutamatergic inputs to VTA glutamatergic neurons mediate prioritization of innate defensive behavior over feeding.

The lateral hypothalamus (LH) is involved in feeding behavior and defense responses by interacting with different brain structures, including the Ventral Tegmental Area (VTA). Emerging evidence indicates that LH-glutamatergic neurons infrequently synapse on VTA-dopamine neurons but preferentially establish multiple synapses on VTA-glutamatergic neurons. Here, we demonstrated that LH-glutamatergic inputs to VTA promoted active avoidance, long-term aversion, and escape attempts. By testing feeding in the presence of a predator, we observed that ongoing feeding was decreased, and that this predator-induced decrease in feeding was abolished by photoinhibition of the LH-glutamatergic inputs to VTA. By VTA specific neuronal ablation, we established that predator-induced decreases in feeding were mediated by VTA-glutamatergic neurons but not by dopamine or GABA neurons. Thus, we provided evidence for an unanticipated neuronal circuitry between LH-glutamatergic inputs to VTA-glutamatergic neurons that plays a role in prioritizing escape, and in the switch from feeding to escape in mice.

A framework for integrating artificial intelligence for clinical care with continuous therapeutic monitoring.

The complex relationships between continuously monitored health signals and therapeutic regimens can be modelled via machine learning. However, the clinical implementation of the models will require changes to clinical workflows. Here we outline ClinAIOps ('clinical artificial-intelligence operations'), a framework that integrates continuous therapeutic monitoring and the development of artificial intelligence (AI) for clinical care. ClinAIOps leverages three feedback loops to enable the patient to make treatment adjustments using AI outputs, the clinician to oversee patient progress with AI assistance, and the AI developer to receive continuous feedback from both the patient and the clinician. We lay out the central challenges and opportunities in the deployment of ClinAIOps by means of examples of its application in the management of blood pressure, diabetes and Parkinson's disease. By enabling more frequent and accurate measurements of a patient's health and more timely adjustments to their treatment, ClinAIOps may substantially improve patient outcomes.

Irving Kirsch opens a window on antidepressant medications.

When it comes to antidepressant medications - popular, backbone drugs of modern psychiatry - even learned scholars and savvy clinicians find it difficult to separate honest, rigorous research from that which thrives on hidden agendas and ulterior motives. Fortunately, a mounting corpus of data-based studies, mostly meta-analyses, casts new and critical light on the clinical efficacy, side effects, and therapeutic outcomes of antidepressants. Spearheading these efforts over the past few decades, Irving Kirsch and colleagues have challenged the hegemonic view of antidepressants as an effective therapeutic intervention. Notably, Kirsch illuminates the small difference between antidepressants and placebos in mitigating depression-a difference that may be statistically significant yet fails to reach clinical significance. This piece sketches the important contributions Kirsch has made to the scientific understanding of antidepressant medications.

Complex identities, intersectionality and research approaches in millennial family caregivers in the United States.

AIMS: A discussion of the personal and social contexts for Millennial family caregivers and the value of including complex identity and intersectionality in Millennial family caregiving research with practical application. DESIGN: Discussion paper. DATA SOURCES: This discussion paper is based on our own experiences and supported by literature and theory. IMPLICATIONS FOR NURSING: Millennial family caregivers have distinct generational, historical and developmental experiences that contribute to the care they provide as well as their own well-being. Complex identity, the integration of multiple identities, and intersectionality, systems and structures that disempower and oppress individuals with multiple identities, need to be addressed in nursing research so intervention tailoring and health equity can be better supported in this population. From research conceptualization and design to data analysis, data must be used intentionally to promote equity and reduce bias. The inclusion of diverse Millennial caregivers throughout all stages of the research process and having a diverse nursing research workforce will support these efforts. CONCLUSION: Millennial family caregivers comprise one-quarter of the family caregiving population in the United States, and they are more diverse than previous family caregiving generational cohorts. Their needs will be more fully supported by nursing scientists with the adoption of methods and techniques that address complex identity and intersectionality. IMPACT: Nursing researchers can use the following research approaches to address complex identity and intersectionality in Millennial caregivers: inclusion of qualitative demographic data collection (participants can self-describe); data disaggregation; data visualization techniques to augment or replace frequencies and descriptive statistics for demographic reporting; use of researcher reflexivity throughout the research process; advanced statistical modelling techniques that can handle complex demographic data and test for interactions and differential effects of health outcomes; and qualitative approaches such as phenomenology that centre the stories and experiences of individuals within the population of interest.

AI in health and medicine.

Artificial intelligence (AI) is poised to broadly reshape medicine, potentially improving the experiences of both clinicians and patients. We discuss key findings from a 2-year weekly effort to track and share key developments in medical AI. We cover prospective studies and advances in medical image analysis, which have reduced the gap between research and deployment. We also address several promising avenues for novel medical AI research, including non-image data sources, unconventional problem formulations and human-AI collaboration. Finally, we consider serious technical and ethical challenges in issues spanning from data scarcity to racial bias. As these challenges are addressed, AI's potential may be realized, making healthcare more accurate, efficient and accessible for patients worldwide.

Improving hospital readmission prediction using individualized utility analysis.

OBJECTIVE: Machine learning (ML) models for allocating readmission-mitigating interventions are typically selected according to their discriminative ability, which may not necessarily translate into utility in allocation of resources. Our objective was to determine whether ML models for allocating readmission-mitigating interventions have different usefulness based on their overall utility and discriminative ability. MATERIALS AND METHODS: We conducted a retrospective utility analysis of ML models using claims data acquired from the Optum Clinformatics Data Mart, including 513,495 commercially-insured inpatients (mean [SD] age 69 [19] years; 294,895 [57%] Female) over the period January 2016 through January 2017 from all 50 states with mean 90 day cost of $11,552. Utility analysis estimates the cost, in dollars, of allocating interventions for lowering readmission risk based on the reduction in the 90-day cost. RESULTS: Allocating readmission-mitigating interventions based on a GBDT model trained to predict readmissions achieved an estimated utility gain of $104 per patient, and an AUC of 0.76 (95% CI 0.76, 0.77); allocating interventions based on a model trained to predict cost as a proxy achieved a higher utility of $175.94 per patient, and an AUC of 0.62 (95% CI 0.61, 0.62). A hybrid model combining both intervention strategies is comparable with the best models on either metric. Estimated utility varies by intervention cost and efficacy, with each model performing the best under different intervention settings. CONCLUSION: We demonstrate that machine learning models may be ranked differently based on overall utility and discriminative ability. Machine learning models for allocation of limited health resources should consider directly optimizing for utility.