The Utility of Machine Learning-Enhanced Developmental Cascade Models in Prevention Science.

Childhood maltreatment affects posttraumatic stress symptoms, posttraumatic growth, and prosocial behavior in emerging adulthood: A developmental cascade model.

Adolescent social withdrawal, parental psychological control, and parental knowledge across seven years: A developmental cascade model

A developmental cascade model was tested to examine longitudinal associations among firstborn children's aggression, theory of mind (ToM), and antagonism toward their younger sibling during the 1st year of siblinghood. Aggression and ToM were assessed before the birth of a sibling and 4 and 12months after the birth, and antagonism was examined at 4 and 12months in a sample of 208 firstborn children (initial Mage =30months, 56% girls) from primarily European American, middle-class families. Firstborns' aggression consistently predicted high sibling antagonism both directly and through poorer ToM. Results highlight the importance of examining longitudinal influences across behavioral, social-cognitive, and relational factors that are closely intertwined even from the early years of life.

A developmental cascade model tested associations among child maltreatment, internalizing and externalizing psychopathology, social competence, and cannabis abuse and dependence symptoms in a longitudinal cohort (N = 415). Nested structural equation models evaluated continuity and cross-domain influences among broad multi-informant constructs across four developmental periods: age 7 to 9, 10 to 12, 13 to 15, and 15 to 18. Results indicated significant paths from child maltreatment to early externalizing and internalizing problems and social competence, as well as to cannabis abuse and dependence (CAD) symptoms in adolescence. Youth CAD symptoms were primarily related directly to child maltreatment and externalizing problems. Childhood internalizing symptoms contributed to later childhood decreases in social competence, which predicted increases in late adolescent externalizing problems. Using a developmental psychopathology framework, results are discussed in relation to cascade and transactional effects and the interplay between problem behaviors during childhood and development of CAD symptoms during early and late adolescence.

Objectives: Early adolescence is a key period of ecological and physiological change, during which exposure to accumulating risks from various environmental systems can negatively impact mental health. This study aimed to investigate the potential longitudinal relationships among cumulative risk, depression, and psychache in adolescents. Methods: A three-wave longitudinal study spanning one year was conducted with 675 (47.5% girls; Mean age = 14.13, standard deviation [SD] = 0.45) middle school students. The Random Intercept Cross-Lagged Panel Model (RI-CLPM) was used to explore the dynamic reciprocal relationships among these variables. Results: At the within-individual level, cumulative risk, depression, and psychache showed relative stability over time (β ranges from 0.21 to 0.52, p < 0.01). Prior cumulative risk significantly and positively predicted later depression and psychache (β ranges from 0.21 to 0.52, p < 0.01). Prior depression significantly and positively predicted later cumulative risk and psychache (β ranges from 0.15 to 0.17, p < 0.01). Prior psychache significantly and positively predicted later depression (β ranges from 0.25 to 0.26, p < 0.001). Conclusion: A cascading effect of mutual influences existed among cumulative risk, depression, and psychache in early adolescents. These findings highlight the usefulness of screening for both cumulative risk and psychache to identify at-risk individuals. Additionally, including psychache assessment in early intervention strategies could enhance their effectiveness.

Toward analyzing and synthesizing previous research in early prediction of cardiac arrest using machine learning based on a multi-layered integrative framework.

The growing quantity and diversity of available data for sociologists necessitates adopting a novel analytic technique that is more appropriate to this new horizon of empirical reality. As a result, a rapprochement between machine learning (ML) and sociology is taking place. The ML modeling approach differs from traditional statistical methods. In ML modeling, four types of fitting outcomes are derived by juxtaposing training results with validation results: ideal fitting, unknown fitting, underfitting, and overfitting. Sociologists experience challenges with using ML approaches to elucidate the differences between ML-based data analysis and conventional statistical techniques. Fitting results do not guarantee the intrinsic validity of the model. Model refinement and validation, which involve fine-tuning hyperparameters, algorithm cross-checking, and subsectioning, are also crucial parts of ML-based analysis. Although well-fitted algorithms do not provide sociologists with immediate explanations for social mechanisms, the anatomy of the well-fitted algorithms can help debunk hidden social mechanisms.

Patient flow analysis can be studied from a clinical and or operational perspective using simulation. Traditional statistical methods such as stochastic distribution methods have been used to construct patient flow simulation submodels such as patient inflow, Length of Stay (LoS), Cost of Treatment (CoT) and Clinical Pathway (CP) models. However, patient inflow demonstrates seasonality, trend and variation over time. LoS, CoT and CP are significantly determined by attributes of patients and clinical and laboratory test results. For this reason, patient flow simulation models constructed using traditional statistical methods are criticized for ignoring heterogeneity and their contribution to personalized and value based healthcare. On the other hand, machine learning methods have proven to be efficient to study and predict admission rate, LoS, CoT, and CP. This paper, hence, describes why coupling machine learning with patient flow simulation is important and proposes a conceptual architecture that shows how to integrate machine learning with patient flow simulation.

Background While recreational drugs use is known to be a strong risk factor of acute cardiovascular events, there is no available prediction tool to detect it in patients admitted to intensive cardiac care units (ICCU), and urinary testing is not routinely performed. Machine learning (ML) methods could provide an accurate model for detection of recreational drugs use. Purpose To assess the feasibility of recreational drugs use detection in patients admitted to ICCU using a ML model with clinical, biological, ECG, and echocardiographic data. Methods From 7 to 22 April 2021, a systematic screening for all traditional recreational drugs (cannabis, opioids, cocaine, amphetamines, 3,4-methylenedioxymethamphetamine [MDMA]) was performed by urinary testing prospectively in all consecutive patients admitted to ICCU in 39 French centres. We compared several ML algorithms to detect recreational drugs use from clinical, biological, ECG and echocardiographic data. The study population was divided in an internal (31 centres, 80% of the population) and an external (8 centres, 20% of the population) cohorts. The internal cohort was divided in a training (70% of the cohort) and a testing (30% of the cohort) dataset. XGBoost algorithm was used for feature selection to avoid overfitting, and gain interpretability. Final performance of the algorithms were evaluated on the external validation cohort and compared against a standard logistic regression model, using receiver operating characteristics (ROC) and precision-recall (PR) curves and area-under-the curves (AUC). Results Of 1,499 consecutive included in the cohort (63±15 years, 70% male), 161 (11%) had a positive test for recreational drugs (cannabis: 9.1%, opioids: 2.1%, cocaine: 1.7%, amphetamines: 0.7%, MDMA: 0.6%, Figure 1). Of the patients with a positive test, only 57% reported using recreational drugs. Out of 165 clinical, biological, ECG, and echocardiographic features, 9 variables were selected as being the most important in detecting drugs use: age, systolic pulmonary artery pressure, body mass index, hemoglobin, NT-pro BNP, temperature, active smoker status, heart rate, and mean blood pressure. The random forest model showed the best performance compared with the other ML models (AUROC=0.82; and PR-AUC=0.62, Figure 2), and with a traditional model using logistic regression (AUROC 0.82 vs. 0.80, and PR-AUC 0.62 vs 0.46; both p&amp;lt;0.001) to detect recreational drugs use. The random forest model also exhibited a good performance for detecting recreational drugs use in the external validation cohort (AUROC=0.76 and PR-AUC=0.44). Conclusions In a large ICCU registry, our ML algorithm including clinical, biological, ECG and echocardiographic data exhibited a higher performance to detect recreational drugs use than traditional statistical methods. Knowing the high rate of underreporting in this study, it is crucial to validate the performance of this ML tool in further larger studies.Model developmentModel performances

Machine learning (ML) is a sub-field of artificial intelligence that uses computer algorithms to extract patterns from raw data, acquire knowledge without human input, and apply this knowledge for various tasks. Traditional statistical methods that classify or regress data have limited capacity to handle large datasets that have a low signal-to-noise ratio. In contrast to traditional models, ML relies on fewer assumptions, can handle larger and more complex datasets, and does not require predictors or interactions to be pre-specified, allowing for novel relationships to be detected. In this review, we discuss the rationale for the use and applications of ML in heart failure, including disease classification, early diagnosis, early detection of decompensation, risk stratification, optimal titration of medical therapy, effective patient selection for devices, and clinical trial recruitment. We discuss how ML can be used to expedite implementation and close healthcare gaps in learning healthcare systems. We review the limitations of ML, including opaque logic and unreliable model performance in the setting of data errors or data shift. Whilst ML has great potential to improve clinical care and research in HF, the applications must be externally validated in prospective studies for broad uptake to occur.

Background Patients with atrial fibrillation (AF) after successful transcatheter aortic valve implantation (TAVI) are at heightened risk of ischaemic stroke (IS) and bleeding. However, risk scores, such as CHA2DS2-VA and HAS-BLED, provide modest prediction of IS and bleeding. Although traditional statistical methods (e.g., Cox regression) allow for identifying patients at higher risk for these events, a machine learning (ML) approach may enhance risk prediction by capturing complex non-linear associations. Purpose To develop and evaluate ML models predicting clinical events in patients with AF after TAVI with established risk scores for IS and bleeding. Methods Patient-level data from the ENVISAGE-TAVI AF trial were used to develop ML models for the prediction of IS, major gastrointestinal bleeding (MGIB), all clinically relevant bleeding (major or clinically relevant nonmajor bleeding), and net adverse clinical events (NACE; composite of death from any cause, myocardial infarction, IS, systemic thromboembolic event, valve thrombosis, or major bleeding). For each outcome, 10 ML algorithms were trained, optimised, and ranked by performance using nested cross-validation. The model with the highest F1 score (harmonic mean of precision and recall) for each outcome was selected and validated on a separate hold-out set (25%). SHAP (SHapley Additive exPlanations) values were calculated to determine the average magnitude of feature contributions. Using F1 scores, the best model of each outcome was compared with logistic regression models trained exclusively on CHA2DS2-VA (IS) and HAS-BLED (bleeding) scores. Results Of 1377 patients on treatment, 41 had IS, 83 had MGIB, 375 had clinically relevant bleeding, and 255 had NACE. The predictive abilities of a linear discriminant analysis algorithm for IS (F1 score=0.08) and CHA2DS2-VA (F1 score=0.09) were similarly low and numerically better than HAS-BLED (F1 score=0.05; Figure 1). Prediction of MGIB was similarly low for a logistic-lasso algorithm (F1 score=0.11), CHA2DS2-VA (F1 score=0.09), and HAS-BLED (F1 score=0.12). For all clinically relevant bleeding, the predictive performance of a naïve-Bayes algorithm (F1 score=0.39) was similar to that of CHA2DS2-VA (F1 score=0.38) and HAS-BLED (F1 score=0.41). The predictive ability of a logistic regression algorithm for NACE (F1 score=0.33) was numerically better than CHA2DS2-VA (F1 score=0.22) or HAS-BLED (F1 score=0.27). Low event rates were generally observed to limit the predictive power of ML models and scores. All 4 algorithms identified novel predictors of events (Figure 2). Conclusion ML models allow for risk assessment for IS, MGIB, all clinically relevant bleeding, and NACE, and were comparable to traditional risk scores. While further development and validation in larger datasets will be required, these initial models reveal potential new predictors of IS and bleeding events that may be important to consider in future studies.

Study DesignRetrospective cohort study.ObjectivesProlonged ICU stay is a driver of higher costs and inferior outcomes in Adult Spinal Deformity (ASD) patients. Machine learning (ML) models have recently been seen as a viable method of predicting pre-operative risk but are often ‘black boxes’ that do not fully explain the decision-making process. This study aims to demonstrate ML can achieve similar or greater predictive power as traditional statistical methods and follows traditional clinical decision-making processes.MethodsFive ML models (Decision Tree, Random Forest, Support Vector Classifier, GradBoost, and a CNN) were trained on data collected from a large urban academic center to predict whether prolonged ICU stay would be required post-operatively. 535 patients who underwent posterior fusion or combined fusion for treatment of ASD were included in each model with a 70-20-10 train-test-validation split. Further analysis was performed using Shapley Additive Explanation (SHAP) values to provide insight into each model’s decision-making process.ResultsThe model’s Area Under the Receiver Operating Curve (AUROC) ranged from 0.67 to 0.83. The Random Forest model achieved the highest score. The model considered length of surgery, complications, and estimated blood loss to be the greatest predictors of prolonged ICU stay based on SHAP values.ConclusionsWe developed a ML model that was able to predict whether prolonged ICU stay was required in ASD patients. Further SHAP analysis demonstrated our model aligned with traditional clinical thinking. Thus, ML models have strong potential to assist with risk stratification and more effective and cost-efficient care.

Machine learning (ML) techniques can help harness insights from data that complement and extend those that can be attained by traditional statistical methods. The current article introduces clinicians to concepts underlying ML and explores how it can be applied within the domain of neuropsychology. Specifically, we illustrate an application of ML to a dataset that includes a battery of standardized measures designed to provide diagnostic support for concussions, including standardized neurocognitive (CPT 3) and neurobehavioral (BESS, NIH 4 meter gait) measures, gait sensor data, and a CDC concussion symptom checklist. These variables were used to predict the decision-making of a pediatric neurologist evaluating a group of child/adolescent patients. With a sample of 111 cases, ML (using a general linear model and deep learning as illustrations) achieved accuracies of 91% and 84.8% and AUCs of 1.0 and .947, respectively, when predicting the neurologist's binomial decision-making (safe/remove). In presenting the data and various considerations for interpretation, we attempt to balance both the promise and perils of ML.

For accurate prediction of any physical parameter including ambient temperature by taking inputs from sensors, machine learning (ML) techniques are often preferred. In this paper, prediction and analysis of environmental real time temperature has been done using two ML models viz. Recurrent Neural Network (RNN) and Long Short Term Memory (LSTM). For analysis of collected data, traditional statistical methods such as Regression Analysis have been used. With the real time temperature sensor, data is collected periodically each day and then is used to train the ML models. During model development, various trails have been undertaken and the LSTM model has been found to be the most suitable. Various parameters of the model such as epochs, batch size have been further analyzed and with increase in the accuracy of the model, the predicted value is observed and a generalized performance is noted for real time use of the system. Further, the work involves the design of an internet of thing (IoT) set up as part of which the ML model works. Together the set-up becomes an intelligent IoT system which is used for remote monitoring through an android application. From experimental results the system has been found to be accurate.

Predicting phenotypes from genomic mutations remains a major genetic challenge. Traditional statistical methods (such as GBLUP and BayesR) have limitations, including reliance on artificial prior assumptions, and hard to capture epistatic effects. Machine learning (ML) has emerged as a powerful alternative for genomic prediction; however, it often struggles with interpretability because of its black-box nature. Here, we evaluate 12 ML models alongside GBLUP and BayesR to identify key factors influencing genomic prediction performance across traits with different genetic architectures in multiple agricultural species, including pigs, chickens, horses, and maize, and we use a series of simulated data sets to assess the impacts of various parameters. Trait genetic architecture and feature selection are the primary determinants of predictive performance. Boosting algorithms outperform the other ML methods and can be further improved by refining biological feature engineering and optimizing the hyperparameters. We demonstrate how gene-related biometrics influence target traits and how accounting for interaction effects enhances prediction accuracy. In addition, we apply Shapley additive explanations (SHAP) to quantify the SNP additive and epistatic effects. To bridge the gap between algorithmic advancements and biological interpretability, we have developed artificial intelligence genomic prediction (AIGP), an open-source end-to-end toolkit for genomic prediction research. Our findings highlight the potential of ML for genomic prediction and emphasize the importance of explainable ML approaches, integration of prior information, and parameter optimization. The AIGP toolkit enables automated model optimization and interpretability, making ML-driven genomic selection more accessible and providing new tools to support genomic research.