Classification And Regression Tree Model Research Articles

Investigation of Freeway Incident Duration Using Classification and Regression Trees Based on Multisource Data

Targeted contingency measures have proven highly effective at reducing the duration and harm caused by incidents. This study utilized the Classification and Regression Trees (CART) data mining technique to predict and quantify the duration of incidents. To achieve this, multisensor data collected from the Hangzhou freeway in China spanning from 2019 to 2021 was utilized to construct a regression tree with eight levels and 14 leaf nodes. By extracting 14 rules from the tree and establishing contingency measures based on these rules, accurate incident assessment and effective implementation of post-incident emergency plans were achieved. In addition, to more accurately apply the research findings to actual incidents, the CART method was compared with XGBoost, Random Forest (RF), and AFT (accelerated failure time) models. The results indicated that the prediction accuracy of the CART model is better than the other three models. Furthermore, the CART method has strong interpretability. Interactions between explanatory variables, up to seven, are captured in the CART method, rather than merely analyzing the effect of individual variables on the incident duration, aligning more closely with actual incidents. This study has important practical implications for advancing the engineering application of machine learning methods and the analysis of sensor data.

Role of letermovir therapeutic drug monitoring for cytomegalovirus prophylaxis in allogeneic hematopoietic stem cell transplantation recipients: a prospective study.

The role of therapeutic drug monitoring (TDM) in allogeneic hematopoietic stem cell transplantation (allo-HSCT) recipients receiving letermovir has not yet been clarified. This study is to explore letermovir trough concentration (Cmin) correlation with its clinical efficacy and adverse events, and factors affecting its plasma concentrations. A prospective, non-interventional study was performed in allo-HSCT recipients receiving letermovir prophylaxis. Plasma concentrations were determined using high-performance liquid chromatography-tandem mass spectrometry. Data analysis was performed using logistic regression, linear regression, and classification and regression tree (CART) models. 701 trough concentrations from 71 recipients were included, uncovering pronounced intra- and inter-individual variability in letermovir Cmin. During 24-week follow-up, CMV infection incidence was 16.4%. A significant correlation was identified between letermovir Cmin and its clinical efficacy, and the CART model showed an increased risk of CMV infection when Cmin ≤ 2731 ng/mL. However, no clear correlation was found between Cmin and adverse events. Gastrointestinal graft-versus-host disease, cyclosporine Cmin, gender, and concomitant medications, including mycophenolate mofetil, ondansetron, caspofungin, and methylprednisolone, may impact letermovir Cmin. Additionally, coadministration with cyclosporine injection significantly decreased median letermovir Cmin compared with cyclosporine capsules (2311 vs. 3386 ng/mL). Moreover, with the extension of time post-transplant, trough concentrations of both cyclosporine and letermovir significantly decreased. TDM for letermovir may be beneficial in allo-HSCT recipients considering the variability in letermovir Cmin and its correlation with clinical efficacy. Moreover, drug interactions and the effects of changes in cyclosporine dosage forms or concentrations require careful monitoring for their effect on letermovir Cmin.

Predictive Factors of Chemotherapy-Induced Peripheral Neuropathy in Breast Cancer: A Decision Tree Model Approach.

Chemotherapy-induced peripheral neuropathy (CIPN) poses a substantial challenge in breast cancer (BC) chemotherapy, affecting the patient's quality of life. Recent studies have focused on exploring predictors and patterns of CIPN occurrence. We aimed to develop a prediction model for CIPN occurrence using a classification and regression tree (CART) algorithm. In this prospective study of 170 patients with BC undergoing chemotherapy, patient-reported adaptation of the Common Terminology Criteria for Adverse Events version 4.0 was used to assess CIPN occurrence. Multivariable analysis using the CART model was tuned using 10-fold cross-validation to identify baseline predictors for CIPN throughout chemotherapy. A receiver operating characteristic curve analysis was conducted for the CART model. A multivariable logistic regression was conducted from the variables included in the CART model to assess the strength and direction of the association. The prevalence of CIPN was 64.7% (n = 110). The most decisive predictor of CIPN occurrence in the CART model was the subject's C-reactive protein (CRP) level. CRP level >3.91 mg/dL, BMI >21.85 kg/m2, and a marital status of unmarried have predicted a probability of 100% in CIPN occurrence. The CART model showed an accuracy of 65.9%, sensitivity of 51.7%, specificity of 73.2%, and an area under the curve of 0.705. A CRP level of >3.91 mg/dL and a neutrophil-to-lymphocyte ratio (NLR) of >2.82 are significantly associated with the occurrence of CIPN (odds ratio [OR], 2.01 [95% CI, 1.01 to 4.01]; P = .046, OR, 2.09 [95%, CI, 1.02 to 4.24]; P = .042, respectively). Baseline CRP, NLR, BMI level, and marital status are significant predictors of CIPN occurrence throughout chemotherapy. Our CART model was better at ruling out individuals who would not experience CIPN. The CART model may provide insight into the future development of individualized patient care and prevention strategies.

Association of Cannabis Use Reduction With Improved Functional Outcomes: An Exploratory Aggregated Analysis From Seven Cannabis Use Disorder Treatment Trials to Extract Data-Driven Cannabis Reduction Metrics.

This exploratory analysis sought to determine whether decreases in cannabis use are associated with improvements in cannabis-related problems and functional outcomes, and if so, what percentage decrease is associated with improvement. Data were aggregated from seven cannabis use disorder treatment trials conducted in the United States (N=920; ages 13 years and older; mean age, 25 years; 30% female, 7% Black, 11% Hispanic/Latinx). Outcome measures included the patient-reported Marijuana Problems Scale (MPS), Health-Related Quality of Life scale (HRQOL), and Pittsburgh Sleep Quality Index and the clinician-rated Clinical Global Impressions (CGI) severity and improvement scales (CGI-S and CGI-I). Generalized estimating equations tested the association between changes in 4-week cannabis use and improvements in functional outcomes. Classification and regression tree (CART) models were developed to determine what reductions in cannabis use could be used as classifiers of improvement. Decreases in the amount and frequency of cannabis use were significantly associated with improvements in MPS severity and total scores as well as improvements on the CGI-I and in sleep quality, but not improvements on the HRQOL. CART models performed best for CGI-I scores (72%-75% correct classification), while other outcome measures did not perform as well (40%-62% correct classification). CART models showed improvements on the CGI at 74% reduction in use amounts and 47% reduction in use days. Reductions in cannabis use (∼50% reduction in use days and ∼75% reduction in use amounts) were associated with clinician-assessed improvement, which suggests that cannabis use reduction may yield benefit among individuals with cannabis use disorder. These exploratory results extract a data-driven metric to inform future studies, clinicians, patients, and policy recommendations.

A novel model using leukocytes to differentiating mild autonomous cortisol secretion and non-functioning adrenal adenoma

BackgroundMild autonomous cortisol secretion (MACS) accounts for a significant proportion of adrenal incidentaloma. Current endocrinological screening tests for MACS are complex, particularly in areas with limited medical resources. This study aimed to develop a diagnostic tool based on leukocyte-related parameters to differentiate between MACS and non-functioning adrenal adenoma (NFA).MethodsInthis retrospective case-control study, propensity score-matching was used to select 567 patients from a cohort of 1108 patients (201 MACS, 907 NFA). External validation cohort included 52MACS and 48 NFA from two hospitals, which did not overlap with the modeling cohort patients. Leukocyte-related parameters were evaluated, and the diagnostic efficacy of each parameter was assessed by calculating Youden’s J index (J) and the area under the curve (AUC). The study population was divided into training and testing samples using a 10-fold cross-validation method. Machine learning (ML) and classification and regression tree (CART) model were established.ResultsAfter propensity score matching, 567 patients were enrolled, including 197 MACS and 370 NFA. With the exception of basophil percentage, all other parameters differed significantly between the two groups. Lymphocyte count, lymphocyte percentage, eosinophils count, eosinophils percentage, and basophil percentage were lower in the MACS group compared to the NFA group. Eosinophils percentage demonstrated the highest AUC (0.650), with a sensitivity of 51.3% and specificity of 73.2%. The ML model, based on multiple parameters,exhibited better performance in diagnosing MACS (sensitivity 76%, specificity 77.4%, and AUC 0.818). A clinically usable CART model achieved an AUC of 0.872, with a sensitivity of 95% and a specificity of 75.7%. In the validation cohort, the prediction accuracy of the ML model and the CART model were 0.784 and 0.798, respectively.ConclusionTheCART diagnostic model, constructed based on leukocyte-related parameters, could assist clinicians in distinguishing between MACS and NFA.

Impact of the fibrosis-4 index in patients with ST-elevated myocardial infarction.

The fibrosis-4 (FIB4) index, a simple, noninvasive marker used for hepatic diseases, represents adverse outcomes. The aim of the present study was to evaluate whether the FIB4 index can predict adverse outcomes in patients with ST-elevation myocardial infarction (STEMI). We investigated patients with STEMI who underwent primary percutaneous coronary intervention (PCI) and were alive at discharge. The cut-off FIB4 index at discharge was investigated using the survival classification and regression tree (CART) model to predict adverse outcomes. The primary outcome was all-cause mortality. Between January 2006 and December 2018, 1354 patients with STEMI (median age, 68 years; men, 76.1%) were investigated. The median value of the FIB4 index was 1.21 (0.84-1.78). The CART model divided the study population into low (FIB4 index <0.945; n = 435), intermediate (0.945 ≤ FIB4 index < 2.185; n = 692), and high (FIB4 index ≥2.185; n = 227) groups based on the significant predictive values for all-cause death. During a median follow-up period of 4.3 years, all-cause death occurred in 208 patients (15.4%). The Kaplan-Meier analysis showed a significant increase in mortality with higher FIB4 index values (log-rank, P < 0.001). The multivariate Cox regression model revealed that the FIB4 index was an independent risk predictor for all-cause death in patients with STEMI [low group as reference vs. intermediate group, hazard ratio: 1.975; 95% confidence interval (CI): 1.166-3.346; P = 0.011 and vs. high group, hazard ratio: 4.633; 95% CI: 2.549-8.418; P < 0.001]. The FIB4 index was associated with the risk of all-cause mortality in patients with STEMI who underwent primary PCI.

Quantification of Color Variation of Various Esthetic Restorative Materials in Pediatric Dentistry.

The goal of this paper is to find an association between the staining capacity of dental restorations used in pediatric patients and food items and to develop an optimum model to predict the most informative factor that causes the highest amount of color change through machine learning algorithms. Color changes in restorative materials occur as a result of intrinsic and extrinsic factors, such as the type of restorative material, food items used, polished status of the material, and time interval. This was an "in vitro study" conducted at Aligarh Muslim University, Aligarh, Uttar Pradesh, India. The study included 200 specimens, that is, 40 in each group A (orange juice), group B (Amul Kool Café), group C (Pepsi), group D (Amul Kesar Milk), and group E (artificial saliva). The materials were glass ionomer cement (GIC), resin-modified glass ionomer cement (RMGIC), microhybrid composite resin, and nanohybrid composite resin. These were further divided into polished and unpolished groups. The optimum modeling of the prediction of color change in materials by different effective factors was done by machine learning decision tree. We applied two algorithms: Chi-square automatic interaction detector (CHAID) and classification and regression tree (CART). In prediction modeling in the decision tree by CHAID and CART, color change is taken as the dependent variable, and group (type of restorative material), food items, time interval, and polished status are taken as independent variables. The various beverages caused significant color variation due to different pigmentation agents. The agent that caused the highest color change was Kool Café. The Kesar Milk had the lowest pigmentation capacity. The greatest color variation was found on Glasionomer FX-II submerged in Pepsi and the least on Ivoclar Te-Econom Plus in Kesar Milk. The mean absolute error for the training dataset in the CART model and CHAID model is 0.379 and 0.332, and for the testing data set, it is 0.398 and 0.333, respectively. Therefore, the prediction of color change by the CHAID model is optimum, and we found that the restorative materials have a maximum predictor importance of 0.86 (86%), time interval 0.07 (7%), food items 0.04 (4%), and polished status has the least importance, that is, 0.03 (3%). The staining capacity of restorative material highly depends on the material itself, the initial time interval, and least on the food items used. The clinical performance of dental restorations could be affected by various beverages consumed by children. This study thus provides important clinical insights into esthetic dentistry by offering valuable information on long-term color stability and the effect of polishing on common esthetic restorative materials used in pediatric dentistry. Varshney P, Khan SY, Jindal MK, et al. Quantification of Color Variation of Various Esthetic Restorative Materials in Pediatric Dentistry. Int J Clin Pediatr Dent 2024;17(7):754-765.

How substance use preferences and practices relate to fentanyl exposure among people who use drugs in Rhode Island, USA

BackgroundOver 107,000 people died in the United States (U.S.) from drug overdose in 2022, with over one million overdose deaths since 1999. The U.S. drug market is characterized by a highly toxic, unregulated, and rapidly changing supply. Understanding the extent of exposure to fentanyl among people who use drugs (PWUD) will guide public health interventions aimed to decrease overdose. MethodsWe utilized baseline data from the Rhode Island Prescription and Illicit Drug Study, a randomized controlled trial of harm reduction-oriented interventions for PWUD in Rhode Island from 2020 to 2023. We evaluated sociodemographic and drug use-related covariates and examined fentanyl presence in urine drug testing (UDT). We built a classification and regression tree (CART) model to identify subpopulations with the highest likelihood of fentanyl presence in UDT. ResultsAmong 446 participants, those with fentanyl present in UDT tended to be younger, non-Hispanic white, and had recently injected drugs (p<0.05 for all). The CART analysis demonstrated a large variation in sample sub-groups’ likelihood of fentanyl presence in UDT, from an estimated probability of 0.09 to 0.90. Expected recent fentanyl exposure was the most important predictor of fentanyl in UDT. ConclusionsUnivariate analyses and CART modeling showed substantial variation in the presence of fentanyl in UDT among PWUD. Harm reduction services for people actively injecting drugs and drug checking programs based on capacity-building, empowerment, and targeted towards those not yet engaged in services are urgently needed to support PWUD in navigating the current volatile drug supply.

Characterisation of the ringed seal (Pusa hispida) acoustic repertoire during spring in the Western Canadian Arctic

ABSTRACT Understanding the acoustic repertoire of a species is crucial for comprehending its ecology and can also provide a valuable tool in the analysis of passive acoustic monitoring data. Despite being the most abundant seal species in the Arctic, the call repertoire of ringed seals (Pusa hispida) remains poorly studied. This paper aims to provide a comprehensive and quantitative description of the calls produced by ringed seals. Data collection occurred in May 2022 near Ulukhaktok in the Western Canadian Arctic. Acoustic recorders were deployed in cracks in the sea ice that were regularly used by ringed seals as haul-out areas. All calls were counted and classified into one of three categories: yelps, barks and growls. High-quality calls were further analysed with ten acoustic parameters calculated for each signal. Cluster and classification and regression tree (CART) analyses were used to assess if the visual classification of calls was supported by the acoustic parameters calculated. The cluster and CART analyses affirmed the presence of all three distinct call types in the ringed seal acoustic repertoire. Classification of unseen calls using the CART model demonstrated an accuracy of 98%. The findings presented here serve as foundational information on the acoustic repertoire of ringed seals.

Landslide susceptibility and building exposure assessment using machine learning models and geospatial analysis techniques

Landslides are among the most dangerous hazards in Asia, posing a significant threat to human lives, infrastructure, and sustainable development. Landslide susceptibility maps provide useful insights into hazard potential but lack quantitative exposure assessments to develop targeted mitigation strategies and resource allocation. This study aims to propose an integrated approach for landslide hazards and exposure evaluation using machine learning models on the Google Earth Engine environment and geospatial analysis techniques. A geospatial database was established to predict hazards and evaluate exposure, including data on topography, geology, hydrology, climate features, land use, and building data. The landslide susceptibility map was created with advanced machine-learning algorithms, including Classification And Regression Tree (CART), Random Forest (RF), Gradient Boosting (GB), and Support Vector Machine (SVM). The ROC curve and the Wilcoxon signed-rank test were employed to evaluate the performance differences among the CART, GB, RF, and SVM models. The results indicated that the RF model demonstrated the highest performance, leading to its selection for creating a landslide susceptibility map. Landslide exposure was evaluated by overlaying the landslide susceptibility map with building data to quantify the number of affected houses by landslides across districts and communes. The analysis results identified the Cho Don district as the most exposed, with 46,237 households located in high and very high landslide susceptibility zones, followed by Ba Be district (39,631 households), Bac Kan city (37,266 households), Bach Thong district (28,495 households), Cho Moi district (28,436 households), Na Ri district (17,723 households), Ngan Son district (14,142 households), and Pac Nam district (13,034 households). These findings enable the identification of the potential consequences of landslides on infrastructure, human settlements, and livelihoods, contributing to the promotion of disaster reduction and prevention strategies.

Spatio‐temporal analysis of snow depth and snow water equivalent in a mountainous catchment: Insights from in‐situ observations and statistical modelling

AbstractThis research, conducted in the mountainous catchment near Abant Lake in the Western Black Sea region of Türkiye, aimed to investigate the spatiotemporal variations of snow depth (SD) and snow water equivalent (SWE) throughout the snow season from December 2019 to March 2020, encompassing both accumulation and melting periods. In total, 14 snow surveys were conducted, covering 58 permanent snow measurement points (PSMP) marked with snow poles. The classification and regression tree (CART) method was employed to statistically analyse their relationships with eight variables: snow period, forest canopy, aspect, slope, elevation, slope position, plan and profile curvature. The root mean square error (RMSE) for SD and SWE was determined to be 0.15 m and 46 mm, respectively. The study findings revealed that mean SD and SWE values were higher in forest gaps compared with under‐forest and open areas. Although the snow cover disappeared earliest in under‐forest areas, the melting rate was observed to be 43% and 17% slower compared with forest gaps and open areas, respectively. Wind redistribution resulted in minimum snow accumulation on western aspects, upper slope positions and ridges, while maximum accumulation was observed on southern aspects, valleys and lower slope positions. Higher elevations (&gt;1580 meters) experienced faster snow melting rates, leading to earlier disappearance of snow cover. PSMPs located on slopes with lower degrees (&lt;15°) exhibited lesser accumulation and earlier snow disappearance. The CART model identified the snow period as the most significant factor in predicting SD and SWE, based on variations in snowfall and air temperature. Other significant variables included forest canopy, aspect and elevation. The study suggests that the CART method is well‐suited for modelling complex snow dynamics, providing valuable insights into spatiotemporal variations in SD and SWE in mountainous regions.

The association between potential predictors and death of patients during the COVID-19 pandemic in Shiraz: a hierarchical multiple regression analysis

IntroductionIdentifying clinical factors that increase the risk of mortality in COVID-19 patients is crucial. This enables targeted screening, optimizing treatment, and prevention of severe complications, ultimately reducing death rates. This study aimed to develop prediction models for the death of patients (i.e., survival or death) during the COVID-19 pandemic in Shiraz, exploring the main influencing factors.MethodWe conducted a retrospective cohort study using hospital-based records of 1030 individuals diagnosed with COVID-19, who were hospitalized for treatment between March 21, 2021, and March 21, 2022, in Shiraz, Iran. Variables related to the final outcome were selected based on criteria and univariate logistic regression. Hierarchical multiple logistic regression and classification and regression tree (CART) models were utilized to explore the relationships between potential influencing factors and the final outcome. Additionally, methods were employed to identify the high-risk population for increased mortality rates during COVID-19. Finally, accuracy was evaluated the performance of the models, with the area under the receiver operator characteristic curve(AUC), sensitivity, and specificity metrics.ResultsIn this study, 558 (54.2%) individuals infected with COVID-19 died. The final model showed that the type of medicine antiviral (OR: 11.10, p = 0.038) than reference (antiviral and corticosteroid), and discharge oxygen saturation(O2) (OR: 1.10, p < 0.001) had a positive association with the chance of survival, but other variables were not considered as predictive variables. Predictive models for the final outcome(death) achieved accuracies ranging from 81 to 87% for hierarchical multiple logistic regression and from 87 to 94% for the CART model. Therefore, the CART model performed better than the hirerical multiple logistic regression model.ConclusionThese findings firstly elucidate the incidence and associated factors of the outcome (death) among patients in Shiraz, Iran. Furthermore, we demonstrated that antiviral medication alone (without corticosteroids) and high O2 increase the survival chances of COVID patients.

Enhancing adult learner success in higher education through decision tree models: A machine learning approach

This article explores the use of machine learning, specifically Classification and Regression Trees (CART), to address the unique challenges faced by adult learners in higher education. These learners confront socio-cultural, economic, and institutional hurdles, such as stereotypes, financial constraints, and systemic inefficiencies. The study utilizes decision tree models to evaluate their effectiveness in predicting graduation outcomes, which helps in formulating tailored educational strategies. The research analyzed a comprehensive dataset spanning the academic years 2013–2014 to 2021–2022, evaluating the predictive accuracy of CART models using precision, recall, and F1 score. Findings indicate that attendance, age, and Pell Grant eligibility are key predictors of academic success, demonstrating the strong capability of the model across various educational metrics. This highlights the potential of machine learning (ML) to improve data-driven decision-making in educational settings. The results affirm the effectiveness of Decision Tree (DT) models in meeting the educational needs of adult learners and underscore the need for institutions to adapt their strategies to provide more inclusive and supportive environments. This study advocates for a shift towards nuanced, data-driven approaches in higher education, emphasizing the development of strategies that address the distinct challenges of adult learners, aiming to enhance inclusivity and support within the sector.

Predicting pre- and post-operative acute kidney injury in elderly patients with coronary artery disease

BackgroundLimited evidence exists regarding the clinical baseline characteristics at admission for acute kidney injury (AKI) before and after interventional cardiac procedures (ICP) in elderly patients with coronary artery disease (CAD). MethodsA total of 488 elderly patients were enrolled in this retrospective single-center study conducted from January 2019 to July 2022, and a classification and regression tree (CART) analysis was performed to identify the high-risk population. ResultsThe AKI incidence was 21.1 % (103/488) in this study, with 27 and 76 individuals developing AKI before and after ICP, respectively. CART analysis revealed that exposure to nephrotoxic drugs and diuretics had the strongest predictive capacities for identifying patients at risk of developing pre-ICP AKI, with the incidence among these high-risk patients ranging from 6.5 % to 13.8 %. Meanwhile, the optimum discriminators for identifying those at high risk of post-ICP AKI were the administration of diuretics, D-value ≤ −860 mL, age >73 years, and administration of nephrotoxic drugs, and the latter model predicted that the AKI incidence among high-risk patients was between 50.0 % and 60.0 %. ConclusionsElderly patients with CAD exhibited an elevated incidence of AKI. CART models suggested that exposure to nephrotoxic drugs and diuretics, D-value, and age were significantly associated with AKI in the elderly with CAD. Importantly, these baseline characteristics at admission could be utilized to identify elderly patients at high risk of pre- and post-ICP AKI.

Increased NGS testing and real-world clinical usage of targeted therapy: All dressed up, nowhere to go.

e13758 Background: National and International recommendations mandate panel- based biomarker testing for all advanced cases of NSCLC. However, analogous to uptake of many other state of the art cancer management strategies, the uptake of NGS based testing and subsequent targeted therapy varies greatly across socio-demographic groups, explained by awareness and economic restraints. This study investigates the potential differences in uptake of NGS based testing and precision medicine in advanced NSCLC patients from India. Methods: This is a single center non-interventional study where retrospective review of patient data of biomarker driven advanced NSCLC patients was carried out. The records were recovered from electronic health records of the hospital. Single gene testing for EGFR and ALK are performed using Roche Cobas V2 and D5F3 Ventana systems respectively. A machine learning algorithm: Classification and Regression Tree (CART) was employed. Results: A total of 5894 patients of advanced NSCLC were identified. Of these 33% received NGS based biomarker testing at diagnosis. The proportion of patients who received NGS tests increased over calendar time from 2014-2023, with an average increment of 15.8% every year, and peak increase in 2022 of 51%. NGS based testing yielded a positive result in 80% cases with a median turnaround time of 18.2+/-3 days. NGS detected 10.2% cases more in EGFR, 3.2% cases less in ALK, 3.1% more in ROS1. Overall NGS was able to detect 37.8% extra cases of biomarker driven cases. Among the biomarker driven, uptake of targeted therapy was 65% for MET, 83% for ROS1, 52% for RET, 17.6% for ERBB2, 63% for BRAF V600E, 75% for EGFR and 79% for ALK at any given point in the disease. None of the G12C KRAS received selective treatment owing to drug unavailability in the country. Applying the CART model, targeted therapy was received by patients younger than 68 years of age, male gender, with ECOG status 0-2, and absence of brain metastases at diagnosis. Patients with brain metastases at diagnosis, females and those &gt;69 years of age were less likely to opt for TKI(p&lt;0.02*). Conclusions: This is the largest cohort from India reporting real world uptake of NGS based biomarker testing and targeted therapy. There is a clear disparity in terms of gender and age group, possibly attributable to social stigmata and taboos prevailing in rural parts of the country. Despite increased detection rates, access to targeted therapy is still a concern owing to inaccessibility to drugs/ lack of global clinical trials in India as well as lack of patient support programs/groups.

Decision Tree-Based Classification Approach to Discover Factors Affecting Vitamin D Level with Machine Learning

Purpose: Vitamin D level is emphasized as an important biomarker in determining risk factors for different diseases. Vitamin D is an important vitamin for human health and its deficiency is associated with serious health problems. Therefore, it is of great importance to detect vitamin D deficiency, which can be easily prevented and treated. The possible relationship between vitamin D deficiency and musculoskeletal pain, osteoporosis, diabetes mellitus, hypertension is frequently discussed in researches. In this research, it is aimed to analyze the factors in determining the vitamin D level and the decision rules related to it. Methods: A descriptive framework based on one of the machine learning techniques, that is decision tree is followed. The data used to create the decision rules were obtained from volunteers between the ages of 18-85 who applied to Izmir Katip Çelebi University Atatürk Training and Research Hospital Infectious Diseases and Family Medicine Polyclinics and agreed to participate in the study between 01.03.2017 and 01.09.2017. Results: It was observed that age, gender and laboratory test values are strong predictors for vitamin D level. As a result of two CART (Classification and Regression Trees) models, %90.47 and %95 predictive accuracies were observed respectively. In the first model, uric acid, age and creatine; in the second model TSH, ALP and smoking(yes) were the most important three biomarkers affecting vitamin D level. Discussion: The collected features give a comprehensive list of variables that have an effect on vitamin D in the dataset under consideration. Important findings of the study include not only the identification of these variables, but also the effective categorization determination procedures. In contrast to previous research, the Age variable is the most influential factor within the scope of this dataset, which includes demographic information on patients and their existing disorders.

A Statiscal Analysis of the Role Various of Co-variables in Detemining, Number of Nodes to be Dissected in Endometrial Cancer by Cart Model, Ahpgic

Aim and Objective: The main objective of this paper is to predict the role of covariables in determining the number of nodes to be dissected in endometrial cancer, using the best regression model. Also, to compare the accuracy of the cart model with the traditional regression model, to accurately find and predict the co-variable in determining the number of nodes to be dissected. Material Method: Data on 170 endometrial cancer patients with their covariates were collected from the institute ahpgic and used for the said objectives. The data for this paper was collected wherein dependent variable is total number of lymph node involved and 10 co-variates (independent variables) age, Postmenopausal Bleeding, Obstetrics History, Nodal Status, Tumor Size, Histology, Grade, Myometrial Invasion, Lymphovascular Space Invasion and Cervical Extension. Methods: multiple regression and cart model. Results: Average number of lymph node dissection among patients having tumor size less than 1.9 cm is 3.73 (approx4) and the patients having a tumor size 1.9 cm is 12.4 (approx13). Average nos of nodes dissection among the patients having prior dissected nodal staus as b/l pelvic lymphdenectomy 10.9 (approx 11) and patients having prior dissected b/l paraortic + b/l pelvic lymhadenectomy is 14.1 (approx14). Thus CART MODEL can predict with more accuracy of 95.9% than the multiple regression model which is of 88.3%, based on the selected covariates and validated by receiver operating characteristics (ROC) curve. Conclusion: Thus we conclude that if tumor size &gt;1.9cm (approx&gt; 2cm) the 12 nodes and if less than 1.9cm (approx&lt; 2cm) then 3.73 i.e approx 4 nodes should be dissected We found that classification and regression tree (CART) model is able to predict the role of the co variate i.e tumor size in deciding the number of lymph node dissection for the EC patients with an accuracy of 95.9% based on the selected covariates and validated by receiver operating characteristics (ROC) curve. Thus CART MODEL can predict with more accuracy of 95.9% than the multiple regression model which is of 88.3%, based on the selected covariates and validated by receiver operating characteristics (ROC) curve. Purpose: The above study will be of help in deciding the nos of nodes to be dissected in endometrial cancer so, that unnecessary morbidities like bleeding and lymphoedem, and waste of resources i.e money and time.

Ocular Biometric Components in Hyperopic Children and a Machine Learning-Based Model to Predict Axial Length.

The purpose of this study was to investigate the development of optical biometric components in children with hyperopia, and apply a machine-learning model to predict axial length. Children with hyperopia (+1 diopters [D] to +10 D) in 3 age groups: 3 to 5years (n=74), 6 to 8years (n=102), and 9 to 11years (n=36) were included. Axial length, anterior chamber depth, lens thickness, central corneal thickness, and corneal power were measured; all participants had cycloplegic refraction within 6 months. Spherical equivalent (SEQ) was calculated. A mixed-effects model was used to compare sex and age groups and adjust for interocular correlation. A classification and regression tree (CART) analysis was used to predict axial length and compared with the linear regression. Mean SEQ for all 3 age groups were similar but the 9 to 11year old group had 0.49D less hyperopia than the 3 to 5year old group (P < 0.001). With the exception of corneal thickness, all other ocular components had a significant sex difference (P < 0.05). The 3 to 5year group had significantly shorter axial length and anterior chamber depth and higher corneal power than older groups (P < 0.001). Using SEQ, age, and sex, axial length can be predicted with a CART model, resulting in lower mean absolute error of 0.60 than the linear regression model (0.76). Despite similar values of refractive errors, ocular biometric parameters changed with age in hyperopic children, whereby axial length growth is offset by reductions in corneal power. We provide references for optical components in children with hyperopia, and a machine-learning model for convenient axial length estimation based on SEQ, age, and sex.

Predicting New Graduate Nurses’ Retention during Transition Using Decision Tree Methods: A Longitudinal Study

Background. Although retaining new nurses is imperative for the future of the nursing profession, it remains a challenging task in the healthcare industry. Understanding the career journey of new graduates as they transition from students to nurses is vital. However, longitudinal studies investigating the factors influencing retention during this period are lacking. Aim. The aim of this study is to identify the influencing factors and develop a longitudinal prediction model for new graduate nurse retention. Methods. A secondary data analysis was conducted using the New Nurse e-Cohort Study dataset from two survey periods, November–December 2020 and February–March 2022. The participants were categorized into either retention or turnover groups based on their turnover experiences. A decision tree based on classification and regression tree (CART) analysis was utilized. Results. Of the total 586 participants, 463 (79%) were in the retention group. The CART model highlighted that new nurses’ retention was significantly associated with younger age, higher readiness for practice (clinical problem-solving) during the nursing program, lower transition shock (such as confusion in professional values, loss of social support, and conflicts between theory and practice), and a higher person-environment fit (person-job fit). The predictive accuracy of the CART model was 79.7%. Conclusion. To retain new nurses, nursing educators and hospital managers should collaborate to prepare nursing students for actual practice, offer support during organizational socialization, and foster healthy professional values for competence in the workplace. Implications for Nursing Management. Transforming the educational strategies of nursing programs and hospital management policies is imperative to ultimately enhance the retention of new graduate nurses.

Development of interpretable machine learning models to predict in-hospital prognosis of acute heart failure patients.

In recent years, there has been remarkable development in machine learning (ML) models, showing a trend towards high prediction performance. ML models with high prediction performance often become structurally complex and are frequently perceived as black boxes, hindering intuitive interpretation of the prediction results. We aimed to develop ML models with high prediction performance, interpretability, and superior risk stratification to predict in-hospital mortality and worsening heart failure (WHF) in patients with acute heart failure (AHF). Based on the Kyoto Congestive Heart Failure registry, which enrolled 4056 patients with AHF, we developed prediction models for in-hospital mortality and WHF using information obtained on the first day of admission (demographics, physical examination, blood test results, etc.). After excluding 16 patients who died on the first or second day of admission, the original dataset (n=4040) was split 4:1 into training (n=3232) and test datasets (n=808). Based on the training dataset, we developed three types of prediction models: (i) the classification and regression trees (CART) model; (ii) the random forest (RF) model; and (iii) the extreme gradient boosting (XGBoost) model. The performance of each model was evaluated using the test dataset, based on metrics including sensitivity, specificity, area under the receiver operating characteristic curve (AUC), Brier score, and calibration slope. For the complex structure of the XGBoost model, we performed SHapley Additive exPlanations (SHAP) analysis, classifying patients into interpretable clusters. In the original dataset, the proportion of females was 44.8% (1809/4040), and the average age was 77.9±12.0. The in-hospital mortality rate was 6.3% (255/4040) and the WHF rate was 22.3% (900/4040) in the total study population. In the in-hospital mortality prediction, the AUC for the XGBoost model was 0.816 [95% confidence interval (CI): 0.815-0.818], surpassing the AUC values for the CART model (0.683, 95% CI: 0.680-0.685) and the RF model (0.755, 95% CI: 0.753-0.757). Similarly, in the WHF prediction, the AUC for the XGBoost model was 0.766 (95% CI: 0.765-0.768), outperforming the AUC values for the CART model (0.688, 95% CI: 0.686-0.689) and the RF model (0.713, 95% CI: 0.711-0.714). In the XGBoost model, interpretable clusters were formed, and the rates of in-hospital mortality and WHF were similar among each cluster in both the training and test datasets. The XGBoost models with SHAP analysis provide high prediction performance, interpretability, and reproducible risk stratification for in-hospital mortality and WHF for patients with AHF.