Conventional Statistics Research Articles

Classification of Traffic Violations Using the Naïve Bayes Algorithm at Padang City Police

Traffic violations have been increasing each year. According to data from the Padang City Police from 2018 to 2023, there were 128,913 traffic violation cases. This is not a small number, and it is time for the police to start utilizing machine learning (ML) technology to evaluate traffic violation cases, as ML can identify hidden patterns or information that cannot be detected manually by conventional statistics or by traffic officers. This research aims to classify traffic violations using the Naïve Bayes algorithm at the Padang City Police by conducting evaluations and comparisons using different dataset ratios. The best algorithm obtained from the comparison will then be analyzed, and the research findings are expected to serve as a reference for the relevant authorities. This research is quantitative in nature, using an experimental method. The data sources or information were obtained from traffic ticket documentation at the Padang City Police and questionnaires distributed to traffic officers of the Padang City Police. The research results show that the Naïve Bayes (NB) algorithm can be used to classify traffic violations at the Padang City Police. The performance test results of the Naïve Bayes (NB) algorithm using all comparison algorithms with different training and testing dataset ratios resulted in 100% accuracy. However, during cross-validation, the Naïve Bayes algorithm achieved the highest accuracy only with training and testing dataset ratios of 80%:20% and 90%:10%. This is due to the large dataset size in this research, which is more than 100,000 entries. The evaluation results of the Naïve Bayes algorithm show that the best model is achieved with the Naïve Bayes algorithm using an 80% training and 20% testing dataset split. Although the performance is similarly high with a 90%:10% training and testing ratio, the researcher chose the 80%:20% training and testing ratio as the best algorithm for reasons of efficiency during training. The argument is that even with just 80%, it is able to predict/classify 20%, which is more efficient than training 90% to predict/classify 10%. Another finding from this implementation is that with a large dataset of 100,000 entries or more, high and stable performance can be achieved, so this research also suggests that to achieve good results from traffic violation classification, the dataset should be above 100,000 entries.

Enhancing Preoperative Outcome Prediction: A Comparative Retrospective Case-Control Study on Machine Learning versus the International Esodata Study Group Risk Model for Predicting 90-Day Mortality in Oncologic Esophagectomy.

Risk prediction prior to oncologic esophagectomy is crucial for assisting surgeons and patients in their joint informed decision making. Recently, a new risk prediction model for 90-day mortality after esophagectomy using the International Esodata Study Group (IESG) database was proposed, allowing for the preoperative assignment of patients into different risk categories. However, given the non-linear dependencies between patient- and tumor-related risk factors contributing to cumulative surgical risk, machine learning (ML) may evolve as a novel and more integrated approach for mortality prediction. We evaluated the IESG risk model and compared its performance to ML models. Multiple classifiers were trained and validated on 552 patients from two independent centers undergoing oncologic esophagectomies. The discrimination performance of each model was assessed utilizing the area under the receiver operating characteristics curve (AUROC), the area under the precision-recall curve (AUPRC), and the Matthews correlation coefficient (MCC). The 90-day mortality rate was 5.8%. We found that IESG categorization allowed for adequate group-based risk prediction. However, ML models provided better discrimination performance, reaching superior AUROCs (0.64 [0.63-0.65] vs. 0.44 [0.32-0.56]), AUPRCs (0.25 [0.24-0.27] vs. 0.11 [0.05-0.21]), and MCCs (0.27 ([0.25-0.28] vs. 0.15 [0.03-0.27]). Conclusively, ML shows promising potential to identify patients at risk prior to surgery, surpassing conventional statistics. Still, larger datasets are needed to achieve higher discrimination performances for large-scale clinical implementation in the future.

Monson’s sphere in Chinese young adult females with individual normal occlusion: a preliminary study using digital models

BackgroundThis study investigated the characteristics of Monson’s sphere in Chinese young adult females with individual normal occlusion to provide a reference for oral rehabilitation in prosthodontic and orthodontic treatments.MethodsPoints at the dental cusps and incisal edges were selected from 51 digital mandibular dental models of Chinese young adult females (aged 18–22 years) with individual normal occlusion. Monson’s spheres were fitted to the selected points based on the least-squares principle and the radii were calculated. The deviation of each selected point from its relative spherical surface was also calculated. The radii and deviations of these points were examined using conventional descriptive statistics and distributions of the most deviated points inside and outside the spheres were analyzed.ResultsThe mean radius of Monson’s sphere in Chinese young adult females was 79.60 ± 14.13 mm. The deviation of each selected point from its relative sphere surface was 0.38 ± 0.30 mm. The maximum deviations inside and outside the sphere were 0.93 ± 0.25 mm and 0.95 ± 0.30 mm, respectively. The most deviated points outside the spheres were mainly distributed at the distolingual cusps of the mandibular second permanent molars (31.37%), while those inside the spheres were mainly distributed at the mesiolingual cusps of the mandibular first permanent molars (45.10%).ConclusionsThe radius of Monson’s sphere in Chinese young adult females was smaller than the classic four-inch value suggested by Monson. Deviation was observed from all selected points to their Monson’s sphere surface, with the most deviated points distributed primarily in the molar region.

Combining artificial intelligence and conventional statistics to predict bronchopulmonary dysplasia in very preterm infants using routinely collected clinical variables.

Prematurity is the strongest predictor of bronchopulmonary dysplasia (BPD). Most previous studies investigated additional risk factors by conventional statistics, while the few studies applying artificial intelligence, and specifically machine learning (ML), for this purpose were mainly targeted to the predictive ability of specific interventions. This study aimed to apply ML to identify, among routinely collected data, variables predictive of BPD, and to compare these variables with those identified through conventional statistics. Very preterm infants were recruited; antenatal, perinatal, and postnatal clinical data were collected. A BPD prediction model was built using conventional statistics, and nine supervised ML algorithms were applied for the same purpose: the results of the best-performing model were described and compared with those of conventional statistics. Both conventional statistics and ML identified the degree of immaturity (low gestational age and/or birth weight), need for mechanical ventilation, and absent or reversed end diastolic flow (AREDF) in the umbilical arteries as risk factors for BPD. Each of the two approaches also identified additional potentially predictive clinical variables. ML algorithms might be useful to integrate conventional statistics in identifying novel risk factors, in addition to prematurity, for the development of BPD in very preterm infants. Specifically, the identification of AREDF status as an independent risk factor for BPD by both conventional statistics and ML highlights the opportunity to include detailed antenatal information in clinical predictive models for neonatal diseases.

Machine Learning Models Can Define Clinically Relevant Bone Density Subgroups based on Patient Specific Calibrated CT Scans in Patients Undergoing Reverse Shoulder Arthroplasty

Reduced bone density is recognized as a predictor for potential complications in reverse shoulder arthroplasty (RSA). While humeral and glenoid planning based on preoperative computed tomography (CT) scans assist in implant selection and position, reproducible methods for quantifying the patients' bone density are currently not available. The purpose of this study was to perform bone density analyses including patient specific calibration in an RSA cohort based on preoperative CT imaging. It was hypothesized that preoperative CT bone density measures would provide objective quantification of the patients' humeral bone quality. This study consisted of three parts, (1) analysis of a patient-specific calibration method in cadaveric CT scans, (2) retrospective application in a clinical RSA cohort, and (3) clustering and classification with machine learning models. Forty cadaveric shoulders were scanned in a clinical CT and compared regarding calibration with density phantoms, air muscle, and fat (patient-specific) or standard Hounsfield unit. Post-scan patient-specific calibration was used to improve the extraction of three-dimensional regions of interest for retrospective bone density analysis in a clinical RSA cohort (n=345). Machine learning models were used to improve the clustering (Hierarchical Ward) and classification (Support Vector Machine (SVM)) of low bone densities in the respective patients. The patient-specific calibration method demonstrated improved accuracy with excellent intraclass correlation coefficients (ICC) for cylindrical cancellous bone densities (ICC>0.75). Clustering partitioned the training data set into a high-density subgroup consisting of 96 patients and a low-density subgroup consisting of 146 patients, showing significant differences between these groups. The SVM showed optimized prediction accuracy of low and high bone densities compared to conventional statistics in the training (accuracy=91.2%; AUC=0.967) and testing (accuracy=90.5 %; AUC=0.958) data set. Preoperative CT scans can be used to quantify the proximal humeral bone quality in patients undergoing RSA. The use of machine learning models and patient-specific calibration on bone mineral density demonstrated that multiple 3D bone density scores improved the accuracy of objective preoperative bone quality assessment. The trained model could provide preoperative information to surgeons treating patients with potentially poor bone quality.

The Artificial Intelligence-Powered New Era in Pharmaceutical Research and Development: A Review.

Currently, artificial intelligence (AI), machine learning (ML), and deep learning (DL) are gaining increased interest in many fields, particularly in pharmaceutical research and development, where they assist in decision-making in complex situations. Numerous research studies and advancements have demonstrated how these computational technologies are used in various pharmaceutical research and development aspects, including drug discovery, personalized medicine, drug formulation, optimization, predictions, drug interactions, pharmacokinetics/ pharmacodynamics, quality control/quality assurance, and manufacturing processes. Using advanced modeling techniques, these computational technologies can enhance efficiency and accuracy, handle complex data, and facilitate novel discoveries within minutes. Furthermore, these technologies offer several advantages over conventional statistics. They allow for pattern recognition from complex datasets, and the models, typically developed from data-driven algorithms, can predict a given outcome (model output) from a set of features (model inputs). Additionally, this review discusses emerging trends and provides perspectives on the application of AI with quality by design (QbD) and the future role of AI in this field. Ethical and regulatory considerations associated with integrating AI into pharmaceutical technology were also examined. This review aims to offer insights to researchers, professionals, and others on the current state of AI applications in pharmaceutical research and development and their potential role in the future of research and the era of pharmaceutical Industry 4.0 and 5.0.

Family history of cancer and lung cancer: Utility of big data and artificial intelligence for exploring the role of genetic risk

ObjectivesLung Cancer (LC) is a multifactorial disease for which the role of genetic susceptibility has become increasingly relevant. Our aim was to use artificial intelligence (AI) to analyze differences between patients with LC based on family history of cancer (FHC). Materials and methodsFrom August 2016 to June 2020 clinical information was obtained from Thoracic Tumors Registry (TTR), a nationwide database sponsored by the Spanish Lung Cancer Group. In addition to descriptive statistical analysis, an AI-assisted analysis was performed. The German Technical Information Library supported the merging of data from the electronic medical records and database of the TTR. The results of the AI-assisted analysis were reported using Knowledge Graph, Unified Schema and descriptive and predictive analyses. ResultsAnalyses were performed in two phases: first, conventional statistical analysis including 11,684 patients of those 5,806 had FHC. Median overall survival (OS) for the global population was 23 months (CI 95 %: 21.39–24.61) in patients with FHC versus 21 months (CI 95 %: 19.53–22.48) in patients without FHC (NFHC), p < 0.001. The second AI-assisted analysis included 5,788 patients of those 939 had FHC. 58.48 % of women with FHC had LC. 9.53 % of patients had an EGFR or HER2 mutation or ALK translocation and at least one relative with cancer. A family history of LC was associated with an increased risk of smoking-related LC. Non-smokers with a family history of LC were more likely to have an EGFR mutation in NSCLC. In Bayesian network analysis, 55 % of patients with a family history of LC and never-smokers had an EGFR mutation. ConclusionIn our population, the incidence of LC in patients with a FHC is higher in women and younger patients. FHC is a risk factor and predictor of LC development, especially in people ≤ 50 years. These results were confirmed by conventional statistics and AI-assisted analysis.

Measuring repeatability of dynamic contrast-enhanced MRI biomarkers improves evaluation of biological response to radiotherapy in lung cancer.

To measure dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) biomarker repeatability in patients with non-small cell lung cancer (NSCLC). To use these statistics to identify which individual target lesions show early biological response. A single-centre, prospective DCE-MRI study was performed between September 2015 and April 2017. Patients with NSCLC were scanned before standard-of-care radiotherapy to evaluate biomarker repeatability and two weeks into therapy to evaluate biological response. Volume transfer constant (Ktrans), extravascular extracellular space volume fraction (ve) and plasma volume fraction (vp) were measured at each timepoint along with tumour volume. Repeatability was assessed using a within-subject coefficient of variation (wCV) and repeatability coefficient (RC). Cohort treatment effects on biomarkers were estimated using mixed-effects models. RC limits of agreement revealed which individual target lesions changed beyond that expected with biomarker daily variation. Fourteen patients (mean age, 67 years +/- 12, 8 men) had 22 evaluable lesions (12 primary tumours, 8 nodal metastases, 2 distant metastases). The wCV (in 8/14 patients) was between 9.16% to 17.02% for all biomarkers except for vp, which was 42.44%. Cohort-level changes were significant for Ktrans and ve (p < 0.001) and tumour volume (p = 0.002). Ktrans and tumour volume consistently showed the greatest number of individual lesions showing biological response. In distinction, no individual lesions had a real change in ve despite the cohort-level change. Identifying individual early biological responders provided additional information to that derived from conventional cohort cohort-level statistics, helping to prioritise which parameters would be best taken forward into future studies. Dynamic contrast-enhanced magnetic resonance imaging biomarkers Ktrans and tumour volume are repeatable and detect early treatment-induced changes at both cohort and individual lesion levels, supporting their use in further evaluation of radiotherapy and targeted therapeutics. Few literature studies report quantitative imaging biomarker precision, by measuring repeatability or reproducibility. Several DCE-MRI biomarkers of lung cancer tumour microenvironment were highly repeatable. Repeatability coefficient measurements enabled lesion-specific evaluation of early biological response to therapy, improving conventional assessment.

Machine learning models identify micronutrient intake as predictors of undiagnosed hypertension among rural community-dwelling older adults in Thailand: a cross-sectional study.

To develop a predictive model for undiagnosed hypertension (UHTN) in older adults based on five modifiable factors [eating behaviors, emotion, exercise, stopping smoking, and stopping drinking alcohol (3E2S) using machine learning (ML) algorithms. The supervised ML models [random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGB)] with SHapley Additive exPlanations (SHAP) prioritization and conventional statistics (χ2 and binary logistic regression) were employed to predict UHTN from 5,288 health records of older adults from ten primary care hospitals in Thailand. The χ2 analyses showed that age and eating behavior were the predicting features of UHTN occurrence. The binary logistic regression revealed that taking food supplements/vitamins, using seasoning powder, and eating bean products were related to normotensive and hypertensive classifications. The RF, XGB, and SVM accuracy were 0.90, 0.89, and 0.57, respectively. The SHAP identified the importance of salt intake and food/vitamin supplements. Vitamin B6, B12, and selenium in the UHTN were lower than in the normotensive group. ML indicates that salt intake, soybean consumption, and food/vitamin supplements are primary factors for UHTN classification in older adults.

Sequential Behavior of Broiler Chickens in Enriched Environments under Varying Thermal Conditions Using the Generalized Sequential Pattern Algorithm: A Proof of Concept.

Behavior analysis is a widely used non-invasive tool in the practical production routine, as the animal acts as a biosensor capable of reflecting its degree of adaptation and discomfort to some environmental challenge. Conventional statistics use occurrence data for behavioral evaluation and well-being estimation, disregarding the temporal sequence of events. The Generalized Sequential Pattern (GSP) algorithm is a data mining method that identifies recurrent sequences that exceed a user-specified support threshold, the potential of which has not yet been investigated for broiler chickens in enriched environments. Enrichment aims to increase environmental complexity with promising effects on animal welfare, stimulating priority behaviors and potentially reducing the deleterious effects of heat stress. The objective here was to validate the application of the GSP algorithm to identify temporal correlations between heat stress and the behavior of broiler chickens in enriched environments through a proof of concept. Video image collection was carried out automatically for 48 continuous hours, analyzing a continuous period of seven hours, from 12:00 PM to 6:00 PM, during two consecutive days of tests for chickens housed in enriched and non-enriched environments under comfort and stress temperatures. Chickens at the comfort temperature showed high motivation to perform the behaviors of preening (P), foraging (F), lying down (Ld), eating (E), and walking (W); the sequences <{Ld,P}>; <{Ld,F}>; <{P,F,P}>; <{Ld,P,F}>; and <{E,W,F}> were the only ones observed in both treatments. All other sequential patterns (comfort and stress) were distinct, suggesting that environmental enrichment alters the behavioral pattern of broiler chickens. Heat stress drastically reduced the sequential patterns found at the 20% threshold level in the tested environments. The behavior of lying laterally "Ll" is a strong indicator of heat stress in broilers and was only frequent in the non-enriched environment, which may suggest that environmental enrichment provides the animal with better opportunities to adapt to stress-inducing challenges, such as heat.

Factors Militating Against Family Caregivers on Cancer Patients Health in Selected Teaching Hospitals in Ogbomoso Area, Oyo State, Nigeria

Introduction: Cancer is gradually becoming a chronic disease, which brings important needs and difficulties to both patients and caregivers. Objective: The study examines factors militating against family caregivers on cancer patients health in selected teaching hospitals in Ogbomoso area, Oyo State, Nigeria. Materials and Methods: Both questionnaire and interviewed techniques were used for data collection from 120 respondents chosen through stratified sampling techniques. In analyzing the data, logit regression model was employed in addition to conventional descriptive statistics such as tables, frequency distribution and percentages. Results: The result of regression model has coefficient of five (5) variables that were statistically significant at 1%, and 5% probability levels. The results revealed that variables with positive signs indicate that the chances of factors militating against family caregivers on cancer patients health increase with education (2.15), social support (2.76), communication, (2.67), and financial support (4.92) whereas, variables with negative sign indicates that the chances of factor militating against family caregivers on cancer patients health decreases with socio-cultural beliefs (-2.64). Conclusion: It identified that factors militating against family caregivers on cancer patients health strongly influenced by gender, age, education, marital status and religion. Hence, recommendation was made that regular systemic assessment of effects of caregiving and shared care responsibility among family members to provide a respite for a particular caregiver.

Current Status of Machine Learning for Precision Rheumatology: Are We There Yet?

Autoimmune rheumatic diseases are often characterised by heterogeneity in presentation. The traditional approach to diseases guided by their phenotype may be suboptimal with the advent of precision medicine. Precision medicine is the integration and application of multiomics to predict the best-performing drug and its toxicity profile to derive optimal benefits. With novel drug discoveries and an expanding therapeutic armamentarium, it potentially aids in clinical and therapeutic decision-making, while saving time and averting adverse events. However, multiomics comes with ‘big data’, and owing to the costs, the sample size is usually small. Machine learning (ML) plays an important role in these scenarios where conventional statistics fall short. So, by integrating clinical data with the data from -omics, ML models can be built, which can accurately predict the clinical factors or even novel biomarkers that predict response. This approach has a potential for great benefit as valuable time or the ‘therapeutic window of opportunity’ would be saved, with fewer adverse events, eventually translating to lower damage accrual and better outcomes. Most of the evidence for the use of ML in precision rheumatology comes from rheumatoid arthritis and the factors predicting response to various drugs, including tumour necrosis factor inhibitors. This approach also has its limitations such as the lack of generalizability and the current scarcity of longitudinal data. These models must be tested in larger cohorts and population-based studies for validation, failing which there is a risk of apparent identification of multiple ‘novel’ biomarkers that may or may not be mechanistic.

Novel Proteome Targets Marking Insulin Resistance in Metabolic Syndrome.

In order to better understand which metabolic differences are related to insulin resistance in metabolic syndrome (MetSyn), we used hyperinsulinemic-euglycemic (HE) clamps in individuals with MetSyn and related peripheral insulin resistance to circulating biomarkers. In this cross-sectional study, HE-clamps were performed in treatment-naive men (n = 97) with MetSyn. Subjects were defined as insulin-resistant based on the rate of disappearance (Rd). Machine learning models and conventional statistics were used to identify biomarkers of insulin resistance. Findings were replicated in a cohort with n = 282 obese men and women with (n = 156) and without (n = 126) MetSyn. In addition to this, the relation between biomarkers and adipose tissue was assessed by nuclear magnetic resonance imaging. Peripheral insulin resistance is marked by changes in proteins related to inflammatory processes such as IL-1 and TNF-receptor and superfamily members. These proteins can distinguish between insulin-resistant and insulin-sensitive individuals (AUC = 0.72 ± 0.10) with MetSyn. These proteins were also associated with IFG, liver fat (rho 0.36, p = 1.79 × 10-9) and visceral adipose tissue (rho = 0.35, p = 6.80 × 10-9). Interestingly, these proteins had the strongest association in the MetSyn subgroup compared to individuals without MetSyn. MetSyn associated with insulin resistance is characterized by protein changes related to body fat content, insulin signaling and pro-inflammatory processes. These findings provide novel targets for intervention studies and should be the focus of future in vitro and in vivo studies.

P.119 NIRS regional oxygen saturation based cerebrovascular reactivity in the recovery from moderate/severe TBI

Background: Near-infrared spectroscopy (NIRS) regional cerebral oxygen saturation (rSO2) based cerebrovascular reactivity (CVR) indicies have enable the entirely non-invasive continuous monitoring. This study aims to compare CVR in those recovering from moderate/severe TBI to a health control group. Methods: In this prospective cohort study the cerebral oxygen CVR index, COx_a (using rSO2 and arterial blood pressure), was measured in subjects with moderate/severe TBI at follow-up. COx_a was also measured in a group of healthy controls. CVR was compared within and between these groups using conventional statistics. Results: A total of 101 heathy subject were recruited for this study along with 29 TBI patients. In the health cohort COx_a was not statistically different between males and females or in the dominate and non-dominate hemisphere. The TBI cohort, COx_a was not statistically different between first and last available follow up. Surprisingly, CVR as measured by COx_a was statistically better in those recovering from TBI than in the healthy cohort. Conclusions: In the prospective cohort study, CVR as measured by NIRS based methods, was found to be more active in those recovering from TBI than in a healthy cohort. This study may indicate that, in those that survive TBI, CVR may be enhanced as a neuroprotective measure.

A lifestyle physical activity intervention for women in alcohol treatment: A pilot randomized controlled trial

IntroductionCompared to men, women with alcohol use disorder (AUD) are more likely to drink to manage stress and negative affect. Given women's risk for poor drinking outcomes, it is critical to develop and test interventions that target these affective factors. Physical activity improves negative affect and has emerged as a promising adjunct to AUD treatment and, thus, may be especially valuable for women. MethodsFifty women with AUD (49.9 ± 12.0 years of age) participated in either a 12-week telephone-delivered lifestyle physical activity plus Fitbit (LPA + Fitbit) or a health education contact (HEC) control intervention following a partial hospital addictions treatment program. The study examined changes in drinking behaviors, mental health outcomes, and physical activity engagement post-intervention using both conventional test statistics and standard effect sizes. ResultsHigher rates of continuous abstinence during the 12-week period were observed in the LPA + Fitbit condition (55.6 %) than in the HEC condition (33.6 %); odds ratio = 2.97. However, among women who drank any alcohol during the 12-weeks, slightly higher rates of heavy drinking and drinks/day were observed among women in the LPA + Fitbit condition. Significant differences for improved mental health outcomes (including depression, anxiety, negative affect, positive affect, perceived stress, and behavioral activation) and increased self-reported physical activity were consistently observed among participants in the LPA + Fitbit condition, relative to HEC. ConclusionsThe LPA + Fitbit program had a positive impact on alcohol abstinence, mental health, and physical activity in adult women receiving treatment for AUD. Future research should continue to investigate the optimal implementation strategies, duration, and intensity of LPA interventions in the context of a fully-powered RCT.

Heterogeneity, Bayesian thinking, and phenotyping in critical care: A primer.

To familiarize clinicians with the emerging concepts in critical care research of Bayesian thinking and personalized medicine through phenotyping and explain their clinical relevance by highlighting how they address the issues of frequent negative trials and heterogeneity of treatment effect. The past decades have seen many negative (effect-neutral) critical care trials of promising interventions, culminating in calls to improve the field's research through adopting Bayesian thinking and increasing personalization of critical care medicine through phenotyping. Bayesian analyses add interpretive power for clinicians as they summarize treatment effects based on probabilities of benefit or harm, contrasting with conventional frequentist statistics that either affirm or reject a null hypothesis. Critical care trials are beginning to include prospective Bayesian analyses, and many trials have undergone reanalysis with Bayesian methods. Phenotyping seeks to identify treatable traits to target interventions to patients expected to derive benefit. Phenotyping and subphenotyping have gained prominence in the most syndromic and heterogenous critical care disease states, acute respiratory distress syndrome and sepsis. Grouping of patients has been informative across a spectrum of clinically observable physiological parameters, biomarkers, and genomic data. Bayesian thinking and phenotyping are emerging as elements of adaptive clinical trials and predictive enrichment, paving the way for a new era of high-quality evidence. These concepts share a common goal, sifting through the noise of heterogeneity in critical care to increase the value of existing and future research. The future of critical care medicine will inevitably involve modification of statistical methods through Bayesian analyses and targeted therapeutics via phenotyping. Clinicians must be familiar with these systems that support recommendations to improve decision-making in the gray areas of critical care practice.

Predictive Modeling for Spinal Metastatic Disease.

Spinal metastasis is exceedingly common in patients with cancer and its prevalence is expected to increase. Surgical management of symptomatic spinal metastasis is indicated for pain relief, preservation or restoration of neurologic function, and mechanical stability. The overall prognosis is a major driver of treatment decisions; however, clinicians' ability to accurately predict survival is limited. In this narrative review, we first discuss the NOMS decision framework used to guide decision making in the treatment of patients with spinal metastasis. Given that decision making hinges on prognosis, multiple scoring systems have been developed over the last three decades to predict survival in patients with spinal metastasis; these systems have largely been developed using expert opinions or regression modeling. Although these tools have provided significant advances in our ability to predict prognosis, their utility is limited by the relative lack of patient-specific survival probability. Machine learning models have been developed in recent years to close this gap. Employing a greater number of features compared to models developed with conventional statistics, machine learning algorithms have been reported to predict 30-day, 6-week, 90-day, and 1-year mortality in spinal metastatic disease with excellent discrimination. These models are well calibrated and have been externally validated with domestic and international independent cohorts. Despite hypothesized and realized limitations, the role of machine learning methodology in predicting outcomes in spinal metastatic disease is likely to grow.

A Minkowski functional analysis of the Cosmic Microwave Background weak lensing convergence

Minkowski functionals are summary statistics that capture the geometric and morphological properties of fields. They are sensitive to all higher order correlations of the fields and can be used to complement more conventional statistics, such as the power spectrum of the field. We develop a Minkowski functional-based approach for a full likelihood analysis of mildly non-Gaussian sky maps with partial sky coverage. Applying this to the inference of cosmological parameters from the Planck mission's map of the Cosmic Microwave Background's lensing convergence, we find an excellent agreement with results from the power spectrum-based lensing likelihood. While the non-Gaussianity of current CMB lensing maps is dominated by reconstruction noise, a Minkowski functional-based analysis may be able to extract cosmological information from the non-Gaussianity of future lensing maps and thus go beyond what is accessible with a power spectrum-based analysis. We make the numerical code for the calculation of a map's Minkowski functionals, skewness and kurtosis parameters available for download from https://github.com/Kang-Yuqi/MF_lensing.

Identifying the top predictors of student well-being across cultures using machine learning and conventional statistics

Alongside academic learning, there is increasing recognition that educational systems must also cater to students’ well-being. This study examines the key factors that predict adolescent students’ subjective well-being, indexed by life satisfaction, positive affect, and negative affect. Data from 522,836 secondary school students from 71 countries/regions across eight different cultural contexts were analyzed. Underpinned by Bronfenbrenner’s bioecological theory, both machine learning (i.e., light gradient-boosting machine) and conventional statistics (i.e., hierarchical linear modeling) were used to examine the roles of person, process, and context factors. Among the multiple predictors examined, school belonging and sense of meaning emerged as the common predictors of the various well-being dimensions. Different well-being dimensions also had distinct predictors. Life satisfaction was best predicted by a sense of meaning, school belonging, parental support, fear of failure, and GDP per capita. Positive affect was most strongly predicted by resilience, sense of meaning, school belonging, parental support, and GDP per capita. Negative affect was most strongly predicted by fear of failure, gender, being bullied, school belonging, and sense of meaning. There was a remarkable level of cross-cultural similarity in terms of the top predictors of well-being across the globe. Theoretical and practical implications are discussed.

Artificial Intelligence, Lymphoid Neoplasms, and Prediction of MYC, BCL2, and BCL6 Gene Expression Using a Pan-Cancer Panel in Diffuse Large B-Cell Lymphoma

Background: Artificial intelligence in medicine is a field that is rapidly evolving. Machine learning and deep learning are used to improve disease identification and diagnosis, personalize disease treatment, analyze medical images, evaluate clinical trials, and speed drug development. Methods: First, relevant aspects of AI are revised in a comprehensive manner, including the classification of hematopoietic neoplasms, types of AI, applications in medicine and hematological neoplasia, generative pre-trained transformers (GPTs), and the architecture and interpretation of feedforward neural net-works (multilayer perceptron). Second, a series of 233 diffuse large B-cell lymphoma (DLBCL) patients treated with rituximab-CHOP from the Lymphoma/Leukemia Molecular Profiling Project (LLMPP) was analyzed. Results: Using conventional statistics, the high expression of MYC and BCL2 was associated with poor survival, but high BCL6 was associated with a favorable overall survival of the patients. Then, a neural network predicted MYC, BCL2, and BCL6 with high accuracy using a pan-cancer panel of 758 genes of immuno-oncology and translational research that includes clinically relevant actionable genes and pathways. A comparable analysis was performed using gene set enrichment analysis (GSEA). Conclusions: The mathematical way in which neural networks reach conclusions has been considered a black box, but a careful understanding and evaluation of the architectural design allows us to interpret the results logically. In diffuse large B-cell lymphoma, neural networks are a plausible data analysis approach.