Predicting crime during or after psychiatric care: Evaluating machine learning for risk assessment using the Danish patient registries.

BACKGROUND: Structural changes in psychiatric systems have altered treatment opportunities for patients in need of mental healthcare. These changes are possibly associated with an increase in post-discharge crime, reported in the increase of forensic psychiatric populations. As current risk-assessment tools are time-consuming to administer and offer limited accuracy, this study aims to develop a predictive model designed to identify psychiatric patients at risk of committing crime leading to a future forensic psychiatric treatment course. METHOD: We utilized the longitudinal quality of the Danish patient registries, identifying the 45.720 adult patients who had contact with the psychiatric system in 2014, of which 474 committed crime leading to a forensic psychiatric treatment course after discharge. Four machine learning models (Logistic Regression, Random Forest, XGBoost and LightGBM) were applied over a range of sociodemographic, judicial, and psychiatric variables. RESULTS: This study achieves a F1-macro score of 76%, with precision = 57% and recall = 47% reported by the LightGBM algorithm. Our model was therefore able to identify 47% of future forensic psychiatric patients, while making correct predictions in 57% of cases. CONCLUSION: The study demonstrates how a clinically useful initial risk-assessment can be achieved using machine learning on data from patient registries. The proposed approach offers the opportunity to flag potential future forensic psychiatric patients, while in contact with the general psychiatric system, hereby allowing early-intervention initiatives to be activated.

Artificial intelligence framework for predictive cardiovascular and stroke risk assessment models: A narrative review of integrated approaches using carotid ultrasound.

RECENT FINDINGS: Cardiovascular disease (CVD) is the leading cause of mortality and poses challenges for healthcare providers globally. Risk-based approaches for the management of CVD are becoming popular for recommending treatment plans for asymptomatic individuals. Several conventional predictive CVD risk models based do not provide an accurate CVD risk assessment for patients with different baseline risk profiles. Artificial intelligence (AI) algorithms have changed the landscape of CVD risk assessment and demonstrated a better performance when compared against conventional models, mainly due to its ability to handle the input nonlinear variations. Further, it has the flexibility to add risk factors derived from medical imaging modalities that image the morphology of the plaque. The integration of noninvasive carotid ultrasound image-based phenotypes with conventional risk factors in the AI framework has further provided stronger power for CVD risk prediction, so-called "integrated predictive CVD risk models." PURPOSE: of the review: The objective of this review is (i) to understand several aspects in the development of predictive CVD risk models, (ii) to explore current conventional predictive risk models and their successes and challenges, and (iii) to refine the search for predictive CVD risk models using noninvasive carotid ultrasound as an exemplar in the artificial intelligence-based framework. CONCLUSION: Conventional predictive CVD risk models are suboptimal and could be improved. This review examines the potential to include more noninvasive image-based phenotypes in the CVD risk assessment using powerful AI-based strategies.

Cardiovascular/stroke risk predictive calculators: a comparison between statistical and machine learning models.

BACKGROUND: Statistically derived cardiovascular risk calculators (CVRC) that use conventional risk factors, generally underestimate or overestimate the risk of cardiovascular disease (CVD) or stroke events primarily due to lack of integration of plaque burden. This study investigates the role of machine learning (ML)-based CVD/stroke risk calculators (CVRCML) and compares against statistically derived CVRC (CVRCStat) based on (I) conventional factors or (II) combined conventional with plaque burden (integrated factors). METHODS: The proposed study is divided into 3 parts: (I) statistical calculator: initially, the 10-year CVD/stroke risk was computed using 13 types of CVRCStat (without and with plaque burden) and binary risk stratification of the patients was performed using the predefined thresholds and risk classes; (II) ML calculator: using the same risk factors (without and with plaque burden), as adopted in 13 different CVRCStat, the patients were again risk-stratified using CVRCML based on support vector machine (SVM) and finally; (III) both types of calculators were evaluated using AUC based on ROC analysis, which was computed using combination of predicted class and endpoint equivalent to CVD/stroke events. RESULTS: An Institutional Review Board approved 202 patients (156 males and 46 females) of Japanese ethnicity were recruited for this study with a mean age of 69±11 years. The AUC for 13 different types of CVRCStat calculators were: AECRS2.0 (AUC 0.83, P<0.001), QRISK3 (AUC 0.72, P<0.001), WHO (AUC 0.70, P<0.001), ASCVD (AUC 0.67, P<0.001), FRScardio (AUC 0.67, P<0.01), FRSstroke (AUC 0.64, P<0.001), MSRC (AUC 0.63, P=0.03), UKPDS56 (AUC 0.63, P<0.001), NIPPON (AUC 0.63, P<0.001), PROCAM (AUC 0.59, P<0.001), RRS (AUC 0.57, P<0.001), UKPDS60 (AUC 0.53, P<0.001), and SCORE (AUC 0.45, P<0.001), while the AUC for the CVRCML with integrated risk factors (AUC 0.88, P<0.001), a 42% increase in performance. The overall risk-stratification accuracy for the CVRCML with integrated risk factors was 92.52% which was higher compared all the other CVRCStat. CONCLUSIONS: ML-based CVD/stroke risk calculator provided a higher predictive ability of 10-year CVD/stroke compared to the 13 different types of statistically derived risk calculators including integrated model AECRS 2.0.

Mutation Clusters from Cancer Exome.

We apply our statistically deterministic machine learning/clustering algorithm *K-means (recently developed in https://ssrn.com/abstract=2908286) to 10,656 published exome samples for 32 cancer types. A majority of cancer types exhibit a mutation clustering structure. Our results are in-sample stable. They are also out-of-sample stable when applied to 1389 published genome samples across 14 cancer types. In contrast, we find in- and out-of-sample instabilities in cancer signatures extracted from exome samples via nonnegative matrix factorization (NMF), a computationally-costly and non-deterministic method. Extracting stable mutation structures from exome data could have important implications for speed and cost, which are critical for early-stage cancer diagnostics, such as novel blood-test methods currently in development.

Risk assessment of radioisotope contamination for aquatic living resources in and around Japan.

Food contamination caused by radioisotopes released from the Fukushima Dai-ichi nuclear power plant is of great public concern. The contamination risk for food items should be estimated depending on the characteristics and geographic environments of each item. However, evaluating current and future risk for food items is generally difficult because of small sample sizes, high detection limits, and insufficient survey periods. We evaluated the risk for aquatic food items exceeding a threshold of the radioactive cesium in each species and location using a statistical model. Here we show that the overall contamination risk for aquatic food items is very low. Some freshwater biota, however, are still highly contaminated, particularly in Fukushima. Highly contaminated fish generally tend to have large body size and high trophic levels.

Heart rate dynamics preceding hemorrhage in the intensive care unit.

Occult hemorrhage in surgical/trauma intensive care unit (STICU) patients is common and may lead to circulatory collapse. Continuous electrocardiography (ECG) monitoring may allow for early identification and treatment, and could improve outcomes. We studied 4,259 consecutive admissions to the STICU at the University of Virginia Health System. We collected ECG waveform data captured by bedside monitors and calculated linear and non-linear measures of the RR interbeat intervals. We tested the hypothesis that a transfusion requirement of 3 or more PRBC transfusions in a 24 hour period is preceded by dynamical changes in these heart rate measures and performed logistic regression modeling. We identified 308 hemorrhage events. A multivariate model including heart rate, standard deviation of the RR intervals, detrended fluctuation analysis, and local dynamics density had a C-statistic of 0.62. Earlier detection of hemorrhage might improve outcomes by allowing earlier resuscitation in STICU patients.

Factors that affect the decision to undergo amniocentesis in women with normal Down syndrome screening results: it is all about the age.

BACKGROUND: Risk for foetal Down syndrome (DS) increases as maternal age increases. Non-invasive screening (maternal serum triple test) for DS is routinely offered to pregnant women to provide risk estimates and suggest invasive amniocentesis for definitive pre-natal diagnosis to high-risk women. OBJECTIVE: We examined women's decision process with regard to pre-natal screening, and specifically, the degree to which they take into account triple serum screening results when considering whether or not to undergo amniocentesis. DESIGN: Semi-structured phone interviews were conducted to assess recall of DS screening results, understanding of risk estimates and their effect on women's decision whether to undergo amniocentesis. The study included 60 pregnant Israeli women (half younger than 35 and half advanced maternal age - AMA), with normal DS screening results and no known ultrasound abnormalities. RESULTS: Age appeared to determine the decision process. The vast majority of AMA women had amniocentesis, many of them before receiving their DS screening results. Most AMA participants knew that their risk estimate was 'normal', but still considered themselves at high risk due to their age. Procedure-related risk (miscarriage) and other factors only had a minor effect on their decision. A minority of younger women had amniocentesis. Younger women mentioned procedure-related risk and having normal screening results as the main factors affecting their decision not to have amniocentesis. CONCLUSION: Age 35 is an anchor for the pre-determination regarding performing or avoiding amniocentesis. AMA women mention 'age' as their main reason to have amniocentesis and considered it an independent risk factor.

Bayesian model selection for group studies - revisited.

In this paper, we revisit the problem of Bayesian model selection (BMS) at the group level. We originally addressed this issue in Stephan et al. (2009), where models are treated as random effects that could differ between subjects, with an unknown population distribution. Here, we extend this work, by (i) introducing the Bayesian omnibus risk (BOR) as a measure of the statistical risk incurred when performing group BMS, (ii) highlighting the difference between random effects BMS and classical random effects analyses of parameter estimates, and (iii) addressing the problem of between group or condition model comparisons. We address the first issue by quantifying the chance likelihood of apparent differences in model frequencies. This leads to the notion of protected exceedance probabilities. The second issue arises when people want to ask "whether a model parameter is zero or not" at the group level. Here, we provide guidance as to whether to use a classical second-level analysis of parameter estimates, or random effects BMS. The third issue rests on the evidence for a difference in model labels or frequencies across groups or conditions. Overall, we hope that the material presented in this paper finesses the problems of group-level BMS in the analysis of neuroimaging and behavioural data.