Merging machine learning and patient preference: a novel tool for risk prediction of percutaneous coronary interventions.

BACKGROUND AND AIMS: Predicting personalized risk for adverse events following percutaneous coronary intervention (PCI) remains critical in weighing treatment options, employing risk mitigation strategies, and enhancing shared decision-making. This study aimed to employ machine learning models using pre-procedural variables to accurately predict common post-PCI complications. METHODS: A group of 66 adults underwent a semiquantitative survey assessing a preferred list of outcomes and model display. The machine learning cohort included 107 793 patients undergoing PCI procedures performed at 48 hospitals in Michigan between 1 April 2018 and 31 December 2021 in the Blue Cross Blue Shield of Michigan Cardiovascular Consortium (BMC2) registry separated into training and validation cohorts. External validation was conducted in the Cardiac Care Outcomes Assessment Program database of 56 583 procedures in 33 hospitals in Washington. RESULTS: Overall rate of in-hospital mortality was 1.85% (n = 1999), acute kidney injury 2.51% (n = 2519), new-onset dialysis 0.44% (n = 462), stroke 0.41% (n = 447), major bleeding 0.89% (n = 942), and transfusion 2.41% (n = 2592). The model demonstrated robust discrimination and calibration for mortality {area under the receiver-operating characteristic curve [AUC]: 0.930 [95% confidence interval (CI) 0.920-0.940]}, acute kidney injury [AUC: 0.893 (95% CI 0.883-0.903)], dialysis [AUC: 0.951 (95% CI 0.939-0.964)], stroke [AUC: 0.751 (95%CI 0.714-0.787)], transfusion [AUC: 0.917 (95% CI 0.907-0.925)], and major bleeding [AUC: 0.887 (95% CI 0.870-0.905)]. Similar discrimination was noted in the external validation population. Survey subjects preferred a comprehensive list of individually reported post-procedure outcomes. CONCLUSIONS: Using common pre-procedural risk factors, the BMC2 machine learning models accurately predict post-PCI outcomes. Utilizing patient feedback, the BMC2 models employ a patient-centred tool to clearly display risks to patients and providers (https://shiny.bmc2.org/pci-prediction/). Enhanced risk prediction prior to PCI could help inform treatment selection and shared decision-making discussions.

Learning Experimental Design through Targeted Student-Centric Journal Club with Screencasting.

Knowledge and application of experimental design principles are essential components of scientific methodology, and experience with these skills is fundamental for participating in scientific research. However, undergraduates often enter the research laboratory with little training in designing and interpreting their own experiments. In the context of a research university laboratory, we designed a journal club training exercise to address this need. Students were instructed on methods for interpreting scientific literature using a screencast, a digital recording of a slide presentation narrated by an instructor. Students subsequently examined a series of research publications with a focus on the experimental designs and data interpretation in a two-session group discussion journal club format. We have found this approach to be an efficient and productive method for engaging students in learning about principles of experimental design and further preparing them for success in laboratory research.

Testing the functional assessment of mentation: A mobile application based assessment of mental status.

BACKGROUND: Altered mental status is a significant predictor of mortality in hospitalized patients and a prerequisite component to the diagnosis of delirium. However, the detection of altered mental status is often incomplete, inaccurate, and resource intensive. OBJECTIVE: To identify the clinical utility and feasibility of the Functional Assessment of Mentation (FAM(TM) ), a mobile application for evaluating attention and recall. DESIGN: Prospective observational pilot study. SETTING: Tertiary care medical center. PARTICIPANTS: Nine hundred thirty-one adult subjects (612 nonhospitalized and 319 hospitalized). MEASUREMENTS: Score distribution and time to FAM(TM) completion were compared between nonhospitalized and hospitalized subjects (as well as between hospitalized subjects discharged home and those not discharged home). Additionally, in the hospitalized subgroup, FAM(TM) was compared to the Glasgow Coma Scale (GCS), using the Short Portable Mental Status Questionnaire (SPMSQ) as our criterion standard for altered mental status assessment. RESULTS: Median time to completion of FAM(TM) was 55 seconds (interquartile range [IQR], 45-67 seconds). Our data identified a graded reduction in score comparing nonhospitalized subjects to hospitalized subjects discharged home and not discharged home (median 5 [IQR 4-7] vs 5 [IQR 3-6] vs 3 [IQR 1-5]; P < 0.001). In the hospitalized subset, FAM(TM) scores were more highly correlated to SPMSQ (Spearman ρ = 0.27, P < 0.001) compared to GCS (Spearman ρ = 0.05, P = 0.40). CONCLUSIONS: FAM(TM) is a rapid and clinically feasible tool that can identify minor alterations in mental status often missed by GCS. Journal of Hospital Medicine 2016;11:463-466. 2016 Society of Hospital Medicine.

Basal microRNA expression patterns in reward circuitry of selectively bred high-responder and low-responder rats vary by brain region and genotype.

Mental health disorders involving altered reward, emotionality, and anxiety are thought to result from the interaction of individual predisposition (genetic factors) and personal experience (environmental factors), although the mechanisms that contribute to an individual's vulnerability to these disorders remain poorly understood. We used an animal model of individual variation [inbred high-responder/low-responder (bHR-bLR) rodents] known to vary in reward, anxiety, and emotional processing to examine neuroanatomical expression patterns of microRNAs (miRNAs). Laser capture microdissection was used to dissect the prelimbic cortex and the nucleus accumbens core and shell prior to analysis of basal miRNA expression in bHR and bLR male rats. These studies identified 187 miRNAs differentially expressed by genotype in at least one brain region, 10 of which were validated by qPCR. Four of these 10 qPCR-validated miRNAs demonstrated differential expression across multiple brain regions, and all miRNAs with validated differential expression between genotypes had lower expression in bHR animals compared with bLR animals. microRNA (miR)-484 and miR-128a expression differences between the prelimbic cortex of bHR and bLR animals were validated by semiquantitative in situ hybridization. miRNA expression analysis independent of genotype identified 101 miRNAs differentially expressed by brain region, seven of which validated by qPCR. Dnmt3a mRNA, a validated target of miR-29b, varied in a direction opposite that of miR-29b's differential expression between bHR and bLR animals. These data provide evidence that basal central nervous system miRNA expression varies in the bHR-bLR model, implicating microRNAs as potential epigenetic regulators of key neural circuits and individual differences associated with mental health disorders.

Acute and chronic glucocorticoid treatments regulate astrocyte-enriched mRNAs in multiple brain regions in vivo.

Previous studies have primarily interpreted gene expression regulation by glucocorticoids in the brain in terms of impact on neurons; however, less is known about the corresponding impact of glucocorticoids on glia and specifically astrocytes in vivo. Recent microarray experiments have identified glucocorticoid-sensitive mRNAs in primary astrocyte cell culture, including a number of mRNAs that have reported astrocyte-enriched expression patterns relative to other brain cell types. Here, we have tested whether elevations of glucocorticoids regulate a subset of these mRNAs in vivo following acute and chronic corticosterone exposure in adult mice. Acute corticosterone exposure was achieved by a single injection of 10 mg/kg corticosterone, and tissue samples were harvested 2 h post-injection. Chronic corticosterone exposure was achieved by administering 10 mg/mL corticosterone via drinking water for 2 weeks. Gene expression was then assessed in two brain regions associated with glucocorticoid action (prefrontal cortex and hippocampus) by qPCR and by in situ hybridization. The majority of measured mRNAs regulated by glucocorticoids in astrocytes in vitro were similarly regulated by acute and/or chronic glucocorticoid exposure in vivo. In addition, the expression levels for mRNAs regulated in at least one corticosterone exposure condition (acute/chronic) demonstrated moderate positive correlation between the two conditions by brain region. In situ hybridization analyses suggest that select mRNAs are regulated by chronic corticosterone exposure specifically in astroctyes based on (1) similar general expression patterns between corticosterone-treated and vehicle-treated animals and (2) similar expression patterns to the pan-astrocyte marker Aldh1l1. Our findings demonstrate that glucocorticoids regulate astrocyte-enriched mRNAs in vivo and suggest that glucocorticoids regulate gene expression in the brain in a cell type-dependent fashion.