Critically reading machine learning literature in neurosurgery: a reader's guide and checklist for appraising prediction models.

OBJECTIVE: Machine learning (ML) has become an increasingly popular tool for use in neurosurgical research. The number of publications and interest in the field have recently seen significant expansion in both quantity and complexity. However, this also places a commensurate burden on the general neurosurgical readership to appraise this literature and decide if these algorithms can be effectively translated into practice. To this end, the authors sought to review the burgeoning neurosurgical ML literature and to develop a checklist to help readers critically review and digest this work. METHODS: The authors performed a literature search of recent ML papers in the PubMed database with the terms "neurosurgery" AND "machine learning," with additional modifiers "trauma," "cancer," "pediatric," and "spine" also used to ensure a diverse selection of relevant papers within the field. Papers were reviewed for their ML methodology, including the formulation of the clinical problem, data acquisition, data preprocessing, model development, model validation, model performance, and model deployment. RESULTS: The resulting checklist consists of 14 key questions for critically appraising ML models and development techniques; these are organized according to their timing along the standard ML workflow. In addition, the authors provide an overview of the ML development process, as well as a review of key terms, models, and concepts referenced in the literature. CONCLUSIONS: ML is poised to become an increasingly important part of neurosurgical research and clinical care. The authors hope that dissemination of education on ML techniques will help neurosurgeons to critically review new research better and more effectively integrate this technology into their practices.

Risk of suicide among stroke survivors in the United States.

BACKGROUND: Stroke is the largest cause of disability and the 5th leading cause of death in the United States. Suicide is the 12th leading cause of death in the United States. However, little is known about the risk of suicide among people with a prior stroke. OBJECTIVES: Using Multiple Cause of Death data (1999-2020) from the Centers for Disease Control and Prevention WONDER database, we examined via cross-sectional analysis the risk of suicide among survivors of stroke as compared to the general U.S. population and among subgroups within the United States. METHODS: We assessed disparities in suicide rate among patients with stroke stratified by sex, race, urbanization levels, and census regions using the CDC WONDER multiple cause of death database. Standardized mortality rates were calculated to compare the suicide rate of stroke patients with the rates among demographic-matched cohorts and the general United States population. RESULTS: As compared to the general population, stroke survivors had an elevated risk of suicide. Black stroke survivors had a lower rate of suicide as compared to the general population, while White stroke survivors and those in nonmetropolitan areas had an elevated risk compared to the general population. CONCLUSION: There was a slightly elevated risk of suicide among people with a prior stroke in the United States. This risk may be elevated among White people and among people living in nonmetropolitan areas.

The invisible scars: Unseen financial complications worsen every aspect of long-term health in trauma survivors.

BACKGROUND: Trauma survivors are susceptible to experiencing financial toxicity (FT). Studies have shown the negative impact of FT on chronic illness outcomes. However, there is a notable lack of data on FT in the context of trauma. We aimed to better understand prevalence, risk factors, and impact of FT on trauma long-term outcomes. METHODS: Adult trauma patients with an Injury Severity Score (ISS) ≥9 treated at Level I trauma centers were interviewed 6 months to 14 months after discharge. Financial toxicity was considered positive if patients reported any of the following due to the injury: income loss, lack of care, newly applied/qualified for governmental assistance, new financial problems, or work loss. The Impact of FT on Patient Reported Outcome Measure Index System (PROMIS) health domains was investigated. RESULTS: Of 577 total patients, 44% (254/567) suffered some form of FT. In the adjusted model, older age (odds ratio [OR], 0.4; 95% confidence interval [95% CI], 0.2-0.81) and stronger social support networks (OR, 0.44; 95% CI, 0.26-0.74) were protective against FT. In contrast, having two or more comorbidities (OR, 1.81; 95% CI, 1.01-3.28), lower education levels (OR, 1.95; 95% CI, 95%, 1.26-3.03), and injury mechanisms, including road accidents (OR, 2.69; 95% CI, 1.51-4.77) and intentional injuries (OR, 4.31; 95% CI, 1.44-12.86) were associated with higher toxicity. No significant relationship was found with ISS, sex, or single-family household. Patients with FT had worse outcomes across all domains of health. There was a negative linear relationship between the severity of FT and worse mental and physical health scores. CONCLUSION: Financial toxicity is associated with long-term outcomes. Incorporating FT risk assessment into recovery care planning may help to identify patients most in need of mitigative interventions across the trauma care continuum to improve trauma recovery. Further investigations to better understand, define, and address FT in trauma care are warranted. LEVEL OF EVIDENCE: Prognostic and Epidemiological; Level III.

Suicide Risk Among Patients With Heart Disease and Heart Failure.

Heart disease is the leading cause of death in the United States (US). Suicide is the 12th leading cause of death. However, little is known about the risk of suicide in patients with heart disease and heart failure. Using Multiple Cause of Death data from the Centers for Disease Control and Prevention (CDC) Wide-ranging ONline Data for Epidemiologic Research (WONDER) database, we used a cross-sectional analysis to examine the risk of suicide in patients with heart disease and heart failure as compared with the general US population and in subgroups within the US. We assessed suicide rate in patients with heart disease and heart failure in the US population as a whole and stratified by race, time, urbanization levels, and census regions using the CDC WONDER Multiple Cause of Death database. Standardized mortality rates were calculated as observed deaths divided by expected deaths. As compared with the general population, patients with heart disease and heart failure had an elevated risk of suicide. This was true across racial and geographic subgroups. There was an elevated risk of suicide in patients with heart disease and heart failure in the United States. For heart disease, there were particular elevations in the Western US, and there was a particular elevation in Black Americans compared with the age-matched population.

Suicide among Cancer Patients: Current Knowledge and Directions for Observational Research.

Cancer is a major public health concern associated with an increased risk of psychosocial distress and suicide. The reasons for this increased risk are still being characterized. The purpose of this study is to highlight existing observational studies on cancer-related suicides in the United States and identify gaps for future research. This work helps inform clinical and policy decision-making on suicide prevention interventions and ongoing research on the detection and quantification of suicide risk among cancer patients. We identified 73 peer-reviewed studies (2010-2022) that examined the intersection of cancer and suicide using searches of PubMed and Embase. Overall, the reviewed studies showed that cancer patients have an elevated risk of suicide when compared to the general population. In general, the risk was higher among White, male, and older cancer patients, as well as among patients living in rural areas and with lower socioeconomic status. Future studies should further investigate the psychosocial aspects of receiving a diagnosis of cancer on patients' mental health as well as the impact of new treatments and their availability on suicide risk and disparities among cancer patients to better inform policies.

Body Position and Orthostatic Hypotension in Hypertensive Adults: Results from the Syst-Eur Trial.

BACKGROUND: We recently demonstrated that more intensive blood pressure (BP) treatment lowered risk of orthostatic hypotension (OH) measured with a seated-to-standing protocol. However, seated-to-standing OH assessments are less sensitive than supine-to-standing and could miss clinically relevant OH. OBJECTIVES: Using data from the Syst-Eur trial (Systolic Hypertension in Europe), we examined the effect of hypertension treatment on incidence of OH based on the difference in BP from 3 body positions. METHODS: Syst-Eur was a multi-center, randomized trial that enrolled adults with isolated systolic hypertension to investigate whether active hypertension treatment could reduce cardiovascular events. Participants underwent BP measurement in supine, seated, and standing positions. Using differences in BP between the 3 body positions (seated minus supine, standing minus seated, and standing minus supine), we defined OH as a drop in systolic BP ≥20 mm Hg or diastolic BP ≥10 mm Hg. We included measurements from baseline and follow-up visits. RESULTS: Among 4695 participants (mean age, 70.2±6.7 years; 66.9% female) with 42 636 BP measurements, OH was present in 4.9% of measures with supine-to-seated, 7.9% with seated-to-standing, and 11.4% with supine-to-standing protocols, respectively. Compared with placebo, BP treatment did not increase OH with any set of maneuvers, OR, 0.79 (95% CI, 0.65-0.95) with seated-to standing, 1.03 (95% CI, 0.86-1.24) with supine-to-seated, and 0.99 (95% CI, 0.86-1.15) with supine-to-standing. CONCLUSIONS: Regardless of protocol, active hypertension treatment did not increase the risk of OH, reinforcing evidence that OH should not be viewed as a complication of hypertension treatment. REGISTRATION: URL: https://www. CLINICALTRIALS: gov; Unique identifier: NCT02088450.

Rationale and Design of the Groceries for Black Residents of Boston to Stop Hypertension Among Adults Without Treated Hypertension (GoFresh) Trial.

BACKGROUND: Poor diet quality significantly contributes to hypertension disparities affecting Black adults. While the Dietary Approaches to Stop Hypertension (DASH) eating pattern lowers blood pressure (BP), access to DASH-patterned groceries is a major barrier for residents of urban food deserts. METHODS: The Groceries for Black Residents of Boston to Stop Hypertension among Adults without Treated Hypertension (GoFresh) study is one of five projects in the RESTORE Network, an AHA-funded initiative focused on hypertension prevention. GoFresh is testing whether online, dietitian-assisted, home-delivered, DASH-patterned groceries lowers BP among Black adults with elevated BP. This individual-level, parallel-arm trial will enroll up to 176 Black adults with SBP (systolic blood pressure) between 120 and <150 mm Hg residing in Boston-area communities with reduced grocery store access. Following randomization, half of the participants will be assigned to weekly sessions with a dietitian who will assist participants in ordering DASH-patterned groceries online for home delivery; the remainder will receive a $500 monthly stipend. Both interventions will last 3 months, followed by a 9-month maintenance phase. RESULTS: The primary outcome is the difference in SBP after 3 months. Secondary outcomes include a change in 24-hour ambulatory BP, body mass index, 24-hour urine sodium and potassium, hemoglobin A1C, lipids, fruit and vegetable intake, and saturated fat intake. Qualitative interviews with 45 participants 6 months after baseline assessments will determine barriers and facilitators to long-term maintenance of DASH-patterned grocery shopping. DISCUSSION: Findings from this study will inform ongoing work on scalable interventions to prevent hypertension among Black adults with implications for public and healthcare-based food supplementation programs. TRIAL REGISTRATION: NCT05121337. Registered on 16 November 2021, at ClinicalTrials.gov: https://clinicaltrials.gov/ct2/show/NCT05121337.

First tobacco product tried among adolescents based on race/ethnicity and socioeconomic status.

In recent years, the tobacco use landscape among youth has changed greatly, underscoring a need to understand current tobacco product initiation patterns. This study aimed to examine if adolescents' first tobacco product tried differs by race/ethnicity and socioeconomic status (SES). Cross-sectional survey data were collected from 6 Connecticut high schools in Spring 2019 (N = 4875). The analytic sample comprised ever users of tobacco products who reported on the first tobacco product they tried (N = 2530; 53.6% female). Of ever tobacco product users, 64.6% reported that their first tobacco product tried was an e-cigarette, 24.4% reported blunts, 6.5% reported another tobacco product, and 4.5% reported cigarettes. A multinomial logistic regression model examined race/ethnicity and SES as predictors of the first tobacco product tried with cigarettes as the reference group. Compared to Non-Hispanic (NH) White students, NH Black students (OR = 0.38, 95%CI = 0.17-0.82), Hispanic students (OR = 0.44, 95%CI = 0.27-0.71), and students of other NH races (OR = 0.30, 95%CI = 0.18-0.52) were less likely to report initiating tobacco product use with e-cigarettes. Additionally, compared to NH White students, NH Black students were more likely to report using blunts as their first tobacco product (OR = 3.01, 95%CI = 1.38-6.56). Compared to low SES, middle SES (OR = 1.62, 95%CI = 1.04-2.52) was associated with greater odds of reporting e-cigarettes as the first tobacco product. These findings suggest that youth of different backgrounds initiate tobacco use with different tobacco products and tailored prevention strategies are needed.

Recent findings in the pharmacology of inhaled nicotine: Preclinical and clinical in vivo studies.

INTRODUCTION: The rise of vaping in adolescents, the recent entrance of new inhaled nicotine products such as iQOS on the market and e-cigarette or vaping product use-associated lung injury cases has created concern for the use of inhaled non-combustible nicotine products. This narrative review discusses recent experimental in vivo studies that utilize human, rat and mouse models to understand the pharmacological impact of nicotine from non-combustible products. METHODS: The search engine PubMed was utilized with the following search terms: inhaled nicotine, nicotine e-cigarette, heated tobacco products, iQOS, electronic cigarette, nicotine inhaler, nicotine vaping. This review highlights recent primary in vivo studies of inhaled nicotine administration experimental paradigms that occurred in laboratory settings using human and rodent (rats and mice) models that have been published from January 2017-December 2019. RESULTS: The pharmacokinetics of nicotine via e-cigarettes is influenced by the PG/VG and flavor constituents in e-liquids, the presence of nicotine salts in e-liquids, puff topography of nicotine and tobacco product users and the power of the e-cigarette device. The pharmacodynamic impact of inhaled nicotine has cardiovascular, pulmonary and central nervous system implications. CONCLUSION: The articles reviewed here highlight the importance of both animal and human models to fully understand the impact of inhaled nicotine pharmacology There is a need for more rodent pharmacokinetic inhaled nicotine studies to understand the influences of factors such as flavor and nicotine salts. Additionally, consensus on nicotine measurement in both human and rodent studies is greatly needed.