Crime Index Research Articles

Parricide and homicide NGRI offenders: How do they differ?

The aim of the present study was to provide a forensic psychiatric characterization of perpetrators of parricide who were found not guilty by reason of insanity (NGRI). We conducted a study involving 52 NGRI patients who had committed homicide or attempted homicide within the Department of Forensic Psychiatry in Thessaloniki, Greece, between January 2015 and 2020. Subjects were categorized into two groups: parricide (n = 21) and a control group (n = 31). Our findings revealed that in the parricide group, the majority of patients were unmarried males in their thirties, with a history of prior contact with mental health services and nonadherence to treatment. Additionally, they had a background of substance abuse and exhibited violent behavior before the index crime. A notable trend observed among parricide offenders was the tendency to seek hospitalization, possibly as a means of distancing themselves from stressful family environments, based on information obtained in the interviews conducted as a part of this research. All instances of parricide involved the use of sharp weapons, and the crimes were consistently committed in private settings. Symptomatology among parricide patients was assessed as moderate to severe, with a significant long-term risk observed following the crime. The primary differences identified between the two groups were the higher pre-crime voluntary admissions and the elevated estimated postcrime risk observed in the parricide group. Early intervention, comprehensive assessment of risk factors, family support, and assistance in resolving conflicts and reintegrating patients into society are emphasized as critical interventions that can potentially prevent future tragedies.

Evaluation of financial monitoring systems effectiveness in its relationship to the country's security indicators

Motivation: The motivation for this research work is its potential to identify critical issues with far-reaching implications for economic security, governance and development, and to contribute to more informed decision-making in the area of countering the financing of terrorism. Aim: The purpose of this research paper is to analyse the impact of the FATF (Financial Action Task Force) standards on crime and anti-corruption efforts and the effective implementation of the legal framework in countries. Results: The article examines the relationship between crime, corruption, terrorism and FATF standards in 54 countries. Based on the regression analysis, the influence of crime, terrorism and perception of corruption on the effectiveness and compliance with FATF standards is investigated. The specific coefficients show that the perception of terrorism and corruption have a statistically significant negative and positive impact on the dependent variable, respectively, while the impact of the crime index is not statistically significant. By examining the impact of crime rates and anti-corruption efforts on FATF standards and the effective implementation of legal frameworks in countries, the study aims to provide information that can inform decision-making. Understanding how these factors interact can help to improve anti-money laundering and counter-terrorist financing strategies at both the national and international levels, including the improvement of financial monitoring systems. Understanding the relationship between crime, corruption and terrorism can have practical implications for various stakeholders, including law enforcement, government officials and international organisations. The findings are important for the implementation of effective measures to combat money laundering and terrorist financing, improve governance, security and overall socio-economic stability.

Models of Valuing Used by Christian Religious Education Teachers to Enable Secondary School Learners Acquire Social, Spiritual and Moral Insights Secondary Schools in Kenya

This investigation was motivated by the extant evidence which indicates that social, economic and political vices are on the rise in Kenya. For example the Kenya police report indicates that nationally crime among the youths stood at 22% between the years 2004 and 2006 from 08% in the period 1998 to 2003. Kisumu East was among the most hit areas with the crime index at 38% in 2006. In addition to this school dropout stood at 31% whereas HIV and AIDS prevalence stood at 12.5% in the same period. This scenario created a need to examine the mechanisms put in place by the Kenyan society to enhance moral growth of the learner more so in Kisumu East district. The study sought to determine the valuing methods used by the Christian Religious Education (C.R.E) teachers in secondary schools with the view of establishing whether or not, the methods equipped the learners with the ability to use valuing models in societal context. The design of the study was descriptive survey and it was conducted in Kisumu East District of Nyanza Province in the Republic of Kenya. The study population consisted of forty seven schools, forty eight teachers and three thousand two hundred and twenty five form two students. Using stratified sampling technique, fifteen mixed secondary schools, five from each of the three administrative units in the district were randomly selected for the study. A population of three hundred and forty three students determined by use of the Fischer formula and then simple randomly sampled formed the sample. Added to the above sixteen C.R.E teachers within the study schools were sampled purposively for the study. Data was collected as follows: the teachers were observed using a rating scale as they taught C.R.E. Secondly, the learners were given a test to ascertain their affective achievements with regards to value identification in societal context and an in-depth interview was conducted with the teachers. Data was also generated through documents analysis in which the teacher's schemes of work, the syllabus and curriculum guides were scrutinized to determine their adequacy in addressing the learners' value needs. To ensure the usefulness of the instruments in collecting data, they were piloted to ascertain their reliability. They were also critiqued and corrected by the experts from the faculty of Education to determine their face validity. Quantitative data was analyzed by use of descriptive statistics such as frequency counts, means and percentages then presented in form of tables. Information from the interviews and documents was analyzed qualitatively by transcription and organization into categories as per the emergent themes then reported and presented in narrative form. The research revealed that the teachers were not acquainted with the valuing models that are supposed to be used in teaching morals to enable learners to acquire social and spiritual insights in societal context. The research concluded that moral decadence experienced in Kisumu East district is due to teachers' inability to use the right valuing models of teaching values using C.R.E. Due to this, there is an urgent need to review the C.R.E. teaching curriculum guide to emphasize on valuing skills. The findings of this study are useful to the designers of curriculum at Kenya Institute of Curriculum Development, the Quality Assurance and Standards Officers in the Ministry of Education as well as the C.R.E teachers in a secondary school classroom since it contributes to the theory and practice of value education.

Save A Leg – Exploring Disparities in Community Characteristics Between Regions of High and Low Leg Amputation Rates

ObjectiveTo explore the disparities in community characteristics between the regions with the highest and lowest leg amputation rates. ApproachThis study used an exploratory method to describe the disparities between community characteristics of these two regions. The study team used several data sources: 1) We used the Dartmouth Atlas Healthcare Map to identify the highest and lowest leg amputation areas. This data was based on leg amputations per 1,000 Medicare enrollees by Hospital referral regions (HRRs) in 2015. 2) We used population estimates and income data from The Census Bureau. 3) We gathered climate, crime index, walk score, bike lanes, and park data from numerous websites. ResultsFlorence, SC has the highest leg amputation rate and Bridgeport, CT has the lowest across the nation. Florence also shows higher cardiovascular disease and diabetes discharge rates. Florence’s population has a slightly higher percentage of persons 65 years and over, a higher percentage of bachelor’s degrees, a higher per capita income, and a lower poverty rate. Florence also has fewer parks, is less walkable or bikeable, and has worse crime. It is worth noting that Bridgeport is close to Yale New Haven Hospital, which has a Limb Preservation Program that could contribute to the region’s extremely low leg amputation rate. ConclusionsThere are disparities in community characteristics between the regions with the highest and lowest leg amputation rates. ImplicationsFuture work needs to investigate the association between community characteristics and leg amputation rates and assess the impact of the Limb Preservation Program.

Neighborhood Deprivation and Crime on Asthma Exacerbations and Utilization in Mild Adult Asthma

Social determinants of health (SDOH) have a significant impact on asthma outcomes, with factors such as income level and neighborhood environment playing crucial roles. This study aimed to assess the impact of Neighborhood Deprivation Index (NDI) and Total Crime Index (TCI) on acute asthma exacerbation (AAE) and asthma-related Emergency Department and urgent care (ED/UC) visits in adults with mild asthma. This retrospective cohort study utilized administrative data from Kaiser Permanente Southern California among 198,873 mild adult asthma patients between January 1, 2013, and December 31, 2018. Robust Poisson regression models, adjusted for age and sex, were employed to investigate the associations of NDI and TCI with AAE and asthma-related ED/UC visits. Data analysis included subgroup assessments by race and ethnicity and BMI categories to explore potential disparities in asthma outcomes. Among the cohort, 12,906 patients (6.5%) experienced AAE in one year, with Black patients having the highest AAE percentage (7.1%). Higher NDI quintiles were associated with increased AAE risk (aRRs: 1.11-1.27), with similar trends across BMI categories and race or ethnicity, except for Black patients. TCI showed weaker associations with AAE. Regarding ED/UC visits, 5.0% had such visits within one year. Higher NDI quintiles were associated with higher ED/UC visit risk (aRRs: 1.23-1.75), while TCI associations were weaker. Addressing socioeconomic disparities, as indicated by NDI, may be crucial in mitigating asthma exacerbations and reducing healthcare utilization, highlighting the importance of incorporating social determinants into asthma management strategies even in patients with mild asthma.

The Road to Crime: An Unintended Consequence of the Interstate Highway System

Abstract The necessity to overhaul national infrastructure has become one of the key issues of US domestic policy in recent years. While the benefits of infrastructure spending are often straightforward, its unintended consequences are less well understood. This paper studies the impact of transportation infrastructure on local crime, focusing on the construction of the Interstate Highway System (IHS), the largest public works project in US history. Using a staggered difference-in-differences design and a county-by-year panel dataset spanning all US counties between 1960 and 1993, we find that a highway opening in a county led to an 8% rise in total index crime. This effect is driven by property crime (burglary, larceny, and motor vehicle theft), although some evidence suggests an increase in violent crime as well. Exploring potential mechanisms, we show that the positive effect of highways on crime is concentrated in counties with low pre-existing stock of police resources where increased connectivity may have raised the returns to crime. Moreover, we find that highway construction induced higher local employment, average firm size, and the local population size, thus increasing the returns to criminal activity, and ultimately the risk of victimisation in the newly-connected counties.

The Trend of Unemployment and Crime Index during COVID-19 Pandemic in Malaysia

The COVID-19 pandemic has caused the number of unemployed to increase in Malaysia and the issue of unemployment has become a social problem that has always been positively linked to criminal activity. However, the crime index in Malaysia showed a decrease over the period of the Movement Control Order (MCO). This study aims to explore the issue using secondary data taken from various sources such as journals, books, proceedings, and press reports. The results of the study found that the crime index decreased even though the number of unemployed increased because it was in line with the theory of crime opportunity. As the community needs to stay at home during the MCO period, the chances of committing index crime are low because the home as well as property are monitored as well as individuals are not exposed to violent crime. However, the domino effect is non -index crime is reported to increase due to the stress of life that makes the individual is motivated to commit non-index crime. The results of the analysis of this study are expected to help the government, especially the Department of Social Welfare to be more efficient by helping and supporting the victims of non-index crime. The results of this study are also expected to provide an explanation to the community on the question of why the unemployment rate is negatively related to index crime as well as remove the negative impression of the report given by the Royal Malaysian Police (RMP). However, the results of this study are only a preliminary analysis and it is suggested that empirical studies can be conducted to support the results of this analysis.

Are crimes against women in India converging? Some empirical observations

ABSTRACT Using the Indian state-level panel data on crimes against women for the period 2000–2019, we examined whether various rates of crime against women were converging. The second-generation unit-root test proposed by Pesaran (2007) was employed to check for absolute β-convergence after conforming to cross-sectional dependence in our panel analysis. The results showed no convergence for various rates of crime against women at the aggregate level, barring dowry deaths. The disaggregated zone-wise results revealed convergence in Eastern and North Eastern states for the Composite Crime Index (CI). The rate of rape was convergent in the west zone, while dowry deaths and cruelty by husbands were convergent only in the Eastern zone. Note that there was a weak convergence in dowry deaths in the North zone. In short, our study fails to find robust evidence of strong convergence in various categories of crime against women in India. The system-GMM results of conditional β-convergence broadly supported the no-convergence results of Pesaran’s unit-root test, as divergence was found in most crime categories. The prominent sources of divergence are women’s employment, female foeticide rate, number of pending cases, rate of arrest, and the proportion of Schedule Castes (SCs) people in the total population.

Unraveling Relapse in Male Forensic Psychiatric Patients with Substance Use Disorders—The Impact of Social, Psychiatric, and Personality Factors Post Long-Term Remission

AbstractSubstance use disorder, labelled a chronic relapse condition by the WHO, remains challenging to address with limited progress in effective relapse prevention measures. Scientific evaluation is hindered by cost, but an opportunity arises in the German forensic psychiatric setting governed by § 64 of the German criminal code. Here, patients undergo two-year multi-modal therapy followed by up to five years of supervised oversight post-release. This retrospective study analyzed legal and medical records, revealing key determinants of relapse, including emotional stress, social activities, personality disorder diagnosis, inpatient treatment relapse, age at first conviction, and loss of motivation. Surprisingly, social factors like family and work status, living situation at discharge, and dialectical behavioral therapy during admission showed no impact, nor did index crime type. Polysubstance use, except for cannabinoids and psychostimulants other than cocaine, increased relapse probability. Multiple inpatient pretreatments were insignificant predictors. A generalized linear model highlighted substance use during inpatient treatment, personality disorder, and previous convictions as most central predictors of post-discharge relapse, challenging conventional notions and informing effective substance use disorder management.

Drugs, guns, and violent crime in California

BackgroundThere is evidence linking use of controlled substances with perpetration of interpersonal violence. While the United States constitution protects the right to own a firearm, federal law prohibits firearm purchase and possession by persons believed to be at high risk for violence, including those who use controlled substances unlawfully. MethodsWe report here the results of a 13-year prospective observational study on the risk of violent crime associated with a history of criminal drug charges in a cohort of 79,678 legal purchasers of handguns in California in 2001. The main outcomes were post-purchase charges for any violent crime, violent Crime Index crimes (murder, rape, robbery, aggravated assault), and firearm-related violent crimes. The main exposure of interest was a history of pre-purchase charge(s) for drug-related offenses; we examined as a secondary exposure a history of marijuana-related charges. We estimated adjusted hazard ratios (aHR) with 95 % confidence intervals (CI) using Cox proportional hazards multiple events models. ResultsWe found that legal handgun purchasers in California with a history of drug-related charges, even those with marijuana charges only, had triple the risk of a post-purchase violent crime charge compared to purchasers with no criminal charges (drug charges only: aHR=2.9, 95 % CI 2.2–3.8; marijuana charges only: aHR=3.3, 95 % CI 1.8–6.0). In addition, a criminal history of drug charges only vs. no criminal history was associated with increased risk of one or more violent crime charges after the first post-purchase arrest event (aHR=1.6, 95 % CI 1.2–2.3). ConclusionIt is incumbent on researchers and policy makers to understand the nature and causes of this risk in order to take effective steps towards mitigation.

Vaping Behaviors and Criminal Activity among a Nationally Representative Sample of U.S. Adults

Background: Prior research has discovered an association between vaping activities and increased delinquent behaviors. However, this relationship has been exclusively studied among adolescents and has not been examined among an adult sample. Methods: The current study uses a nationally representative sample of approximately 45,000 adults from the 2021 National Survey on Drug Use and Health. Logistic regression and negative binomial regression are employed to assess the association between three types of vaping (marijuana, nicotine, flavor) and five crime measures (arrest, sold drugs, stole >$50, attack, crime index), net of covariates. A vaping index is also examined to determine whether the number of substances vaped is related to criminal outcomes. Results: Results indicate that past year and past month marijuana and nicotine vaping are associated with higher odds of almost all crime measures, but flavor vaping was not significantly associated with the crime outcomes. Additionally, the vaping index suggests that the number of substances vaped is associated with the likelihood of engaging in certain crimes. Conclusions: The findings of the current study indicate the need for more awareness of the negative social consequences associated with vaping, particularly marijuana vaping. Additionally, the crime patterns among adults in this study are different from previous studies using adolescent samples. Specifically, flavor vaping is not associated with criminal behavior among the adult only sample. Thus, vaping studies that use adolescent samples may not generalize to adults.

시민들의 경찰역할인식이 범죄두려움에 미치는 영향

This study aims to investigate whether fear of crime varies according to citizens’ perception of the police role. And to explore it underlying causes. Citizens’ perception of police role can be influence by personal, societal, and psychological factors, with this study particularly focusing on the macroscopic perspective of the local community environment to analyze variations in citizens' perceptions. The analysis utilizes self-collected data from the “Citizens' Perception Survey on Police Organizations and Crime” and the Ministry of Public Administration and Security's “2022 Nationwide Local Safety Index Publication.” The findings are as follows: First, citizens tend to perceive the police role as closer to crime response in areas with higher crime indices, indicating greater vulnerability to crime. Second, it was found that differences in citizens' perception of the police role based on the crime index of their residential districts have varied impacts on fear of crime. Specifically, residents in the Dongbuk-gwon, where the crime index is the lowest, showed no significant impact of crime fear even when perceiving police role as crime response. However, in the Seobuk-gwon with the highest crime index, the perception of police role as crime response corresponded to increased fear of crime, demonstrating the strongest significance. Based on these results, several preventative measures emphasizing the proactive aspects of police activities are proposed.

A Hybrid Machine Learning and Regression Approach for Validating a Multi-Dimensional Crime Index in the Context of Crime against Women

A Hybrid Machine Learning and Regression Approach for Validating a Multi-Dimensional Crime Index in the Context of Crime against Women

Investigative Capabilities of Crime Investigators in Handling Eight Focus Crimes

This study examined the investigative capabilities of crime investigators and the problems encountered in handling eight focus crimes in CALABARZON using the descriptive method of research. The instrument was distributed conveniently to 365 criminal investigator-respondents with a turnout of 325 or 89.04% questionnaire retrieval rate. Basic and inferential statistical tools were used to analyze and interpret the data gathered. The maximum number of cases filed by investigators is 500, and the minimum is zero or none. Physical injury is the case with most convictions; however, it is the most dismissed case due to noncooperation of the victim/complainant. It was also revealed that the criminal investigators are very highly capable as to their skills, attitude, and knowledge in the conduct of their duties and responsibilities. However, even though they are highly capable in handling the eight focus crimes, they still encountered serious problems in investigating the index crimes. In light of the study’s findings, the Philippine National Police can devise incentive programs to encourage criminal investigators to improve themselves and become more effective in the performance of their duties.

Assessing the impact of socioeconomic status on incidental lung nodules at an urban safety net hospital

IntroductionLower socioeconomic status has been identified as an emerging risk factor for health disparities, including lung cancer outcomes. Most research investigating these outcomes includes patients from formal lung cancer screening programs. There is a paucity of studies assessing the relationship between socioeconomic status and incidental lung nodules. This study aimed to investigate the association between socioeconomic status and the size of incidental lung nodules on initial presentation at an urban safety net hospital, which did not have a formal lung cancer screening program or incidental lung nodule program.MethodsA retrospective chart review was conducted on patients with incidental lung nodules on CT chest imaging who were referred from primary care to a pulmonology clinic at a safety net hospital. Patients with incomplete nodule characteristics information were excluded. Data on demographics, comorbidities, smoking history, insurance type, immigration status, and geographical factors were collected. Less commonly studied determinants such as crime index, cost of living, and air quality index were also assessed. Logistic regression analysis was performed to assess relationships between nodule size and socioeconomic determinants.ResultsOut of 3,490 patients with chest CT scans, 268 patients with ILNs were included in the study. 84.7% of patients represented racial or ethnic minorities, and most patients (67.8%) had federal insurance. Patients with non-commercial insurance were more likely to have larger, inherently higher-risk nodules (> 8 mm) compared to those with commercial insurance (OR 2.18, p 0.01). Patients from areas with higher unemployment rates were also less likely (OR 0.75, p 0.04) to have smaller nodules (< 6 mm). Patients representing racial or ethnic minorities were also more likely to have nodules > 8 mm (OR 1.6, p 0.24), and less likely to have nodules < 6 mm (OR 0.6, p 0.32), however, these relationships were not statistically significant.ConclusionThis study found that lower socioeconomic status, indicated by having non-commercial insurance, was associated with larger incidental lung nodule size on initial presentation. While it is established that socioeconomic status is associated with disparities in lung cancer screening, these findings suggest that inequalities may also be present in those with incidental lung nodules. Further research is needed to understand the underlying mechanisms and develop interventions to address these disparities in incidental lung nodule evaluation and improve outcomes.

Subjective and objective indicators of neighbourhood safety and physical activity among UK adolescents.

The health benefits of regular physical activity in adolescence are well-documented and many health-related behaviours are established in adolescence. The neighbourhood environment is a key setting for physical activity for adolescents and feeling unsafe in their neighbourhood may be a potential barrier to physical activity. This study aimed to examine associations between neighbourhood safety and physical activity using objective and subjective measures for both. Participants (n=10,913) came from the Millennium Cohort Study, a nationally representative UK longitudinal birth cohort. Linear regression and Zero Inflated Poisson models were used to examine associations between subjective and objective indicators of safety (self-reported safety, Index of Multiple Deprivation crime, Reported Crime Incidence) and physical activity (self-reported weekly and device-measured physical activity). Adolescents who feel unsafe in their neighbourhood, or who live in areas with high IMD crime or violent crime rates report 0.29 (95% CI -0.49, -0.09) 0.32 (95% CI -0.47, -0.16) and 0.20 (95% CI -0.39, -0.20) fewer days of physical activity, respectively. No associations were found between Reported Crime Incidence and either objective or subjective measures of physical activity. This study demonstrates varying associations between subjective safety and objective crime with physical activity levels in adolescence, highlighting the complexities around subjective and objective measurements and their associations with health outcomes.

The Effect of Land Cover Protection on Preventing Crime: The Case Study of the State of New York, USA

The settlements’ traditional character and architectural texture will strengthen people’s sense of belonging and prevent migration, while local urban identity will be the most significant impediment to crime. The study investigates the relationship between the environmental and criminal conditions in New York, the world’s most diverse demographic. In New York, not every county has the same settlement or vegetation homogeneity level. To avoid the immigrant factor, the location where the offenders committed the crime was considered; crime data were statistically analyzed to assess the vegetation-crime relationship. With an interdisciplinary approach, the research also draws attention to the mean-world syndrome regarding crime and urbanization in the current cultural environment in the context of the media-violence relationship. Under the crime index category, the crimes committed were divided into major groups, and statistical analyses were performed on all the groups. The study also touches on proactive policing used in the United States. According to our findings, the keyword of sustainable development, equity, has been successfully realized in the United States. As a result, the classic scenario of income distribution disparities in the state driving citizens to crime does not apply to New York.

The role of prenatal violence exposure in the development of disparities in children's adiposity from birth to middle childhood.

This study examined whether women's exposure to multiple types of violence during childhood and pregnancy was associated with children's BMI trajectories and whether parenting quality moderated those associations. A cohort of 1288 women who gave birth between 2006 and 2011 self-reported their exposure to childhood traumatic events, intimate partner violence (IPV), and residential address (linked to geocoded index of violent crime) during pregnancy. Children's length/height and weight at birth and at age 1, 2, 3, 4 to 6, and 8 years were converted to BMI z scores. Observed mother-child interactions were behaviorally coded during a dyadic teaching task. Covariate-adjusted growth mixture models identified three trajectories of children's BMI from birth to 8 years old: Low-Stable (17%), Moderate-Stable (59%), and High-Rising (22%). Children whose mothers experienced more types of IPV during pregnancy were more likely to be in the High-Rising than the Low-Stable (odds ratio [OR] = 2.62; 95% CI: 1.27-5.41) trajectory. Children whose mothers lived in higher crime neighborhoods were more likely to be in the High-Rising than the Low-Stable (OR = 1.11; 95% CI:1.03-1.17) or Moderate-Stable trajectories (OR = 1.08; CI: 1.03-1.13). Main effects of childhood traumatic events and moderation by parenting were not detected. Maternal experiences of violence during pregnancy increase children's risk for developing overweight, highlighting intergenerational transmission of social adversity in children's health.

Social Determinants of Health and Racial Disparities in Cardiac Events in Breast Cancer.

Racial disparities have been reported for breast cancer and cardiovascular disease (CVD) outcomes. The determinants of racial disparities in CVD outcomes are not yet fully understood. We aimed to examine the impact of individual and neighborhood-level social determinants of health (SDOH) on the racial disparities in major adverse cardiovascular events (MACE; consisting of heart failure, acute coronary syndrome, atrial fibrillation, and ischemic stroke) among female patients with breast cancer. This 10-year longitudinal retrospective study was based on a cancer informatics platform with electronic medical record supplementation. We included women aged ≥18 years diagnosed with breast cancer. SDOH were obtained from LexisNexis, and consisted of the domains of social and community context, neighborhood and built environment, education access and quality, and economic stability. Race-agnostic (overall data with race as a feature) and race-specific machine learning models were developed to account for and rank the SDOH impact in 2-year MACE. We included 4,309 patients (765 non-Hispanic Black [NHB]; 3,321 non-Hispanic white). In the race-agnostic model (C-index, 0.79; 95% CI, 0.78-0.80), the 5 most important adverse SDOH variables were neighborhood median household income (SHapley Additive exPlanations [SHAP] score [SS], 0.07), neighborhood crime index (SS = 0.06), number of transportation properties in the household (SS = 0.05), neighborhood burglary index (SS = 0.04), and neighborhood median home values (SS = 0.03). Race was not significantly associated with MACE when adverse SDOH were included as covariates (adjusted subdistribution hazard ratio, 1.22; 95% CI, 0.91-1.64). NHB patients were more likely to have unfavorable SDOH conditions for 8 of the 10 most important SDOH variables for the MACE prediction. Neighborhood and built environment variables are the most important SDOH predictors for 2-year MACE, and NHB patients were more likely to have unfavorable SDOH conditions. This finding reinforces that race is a social construct.

Thirty-Day Unplanned Hospital Readmissions in Patients With Cancer and the Impact of Social Determinants of Health: A Machine Learning Approach.

Develop a cancer-specific machine learning (ML) model that accurately predicts 30-day unplanned readmissions in patients with solid tumors. The initial cohort included patients 18 years or older diagnosed with a solid tumor. Two distinct cohorts were generated: one with and one without detailed social determinants of health (SDOHs) data. For each cohort, data were temporally partitioned in 70% (training), 20% (validation), and 10% (testing). Tree-based ML models were developed and validated on each cohort. The metrics used to evaluate the model's performance were receiver operating characteristic curve (ROC), area under the ROC curve, precision, recall (R), accuracy, and area under the precision-recall curve. We included 13,717 patients in this study in two cohorts (5,059 without SDOH data and 8,658 with SDOH data). Unplanned 30-day readmission occurred in 21.3% of the cases overall. The five main non-SDOH factors most highly associated with an unplanned 30-day readmission (R, 0.74; IQR, 0.58-0.76) were: number of previous unplanned readmissions; higher Charlson comorbidity score; nonelective index admission; discharge to anywhere other than home, hospice, or nursing facility; and higher anion gap during the admission. Neighborhood crime index, neighborhood median home values, annual income, neighborhood median household income, and wealth index were the main five SDOH factors important for predicting a high risk for an unplanned hospital readmission (R, 0.66; IQR, 0.56-0.72). The models were not directly comparable. Key drivers of unplanned readmissions in patients with cancer are complex and involve both clinical factors and SDOH. We developed a cancer-specific ML model that with reasonable accuracy identified patients with cancer at high risk for an unplanned hospital readmission.