Recursive Partitioning Research Articles

Regression tree applications to studying alcohol-related problems among college students.

Machine learning algorithms hold promise for developing precision medicine approaches to addiction treatment yet have been used sparingly to identify predictors of alcohol-related problems. Recursive partitioning, a machine learning algorithm, can identify salient predictors and clinical cut points that can guide treatment. This study aimed to identify predictors and cut points of alcohol-related problems and to examine result stability in two separate, large data sets of college student drinkers (n = 5,090 and 2,808). Four regression trees were grown using the "rpart" package in R. Seventy-one predictors were classified as demographics (e.g., age), alcohol use indicators (e.g., typical quantity/frequency), or psychosocial indicators (e.g., anxiety). Predictors and cut points were extracted and used to manually recreate the tree in the other data set to test result stability. Outcome variables were alcohol-related problems as measured by the Alcohol Use Disorder Identification Test and Brief Young Adult Alcohol Consequences Questionnaire. Coping with depression, conformity motives, binge drinking frequency, typical/heaviest quantity, drunk frequency, serious harm reduction protective behavioral strategies, substance use, and psychosis symptoms best predicted alcohol-related problems across the four trees; coping with depression (cut point range: 1.83-2.17) and binge drinking frequency (cut point range: 1.5-2.5) were the most common splitting variables. Model fit indices suggest relatively stable results accounting for 17%-30% of the variance. Results suggest the nine salient predictors, particularly coping with depression motives scores around 2 and binge drinking frequency around two to three times per month, are important targets to consider when treating alcohol-related problems for college students. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Extent of Resection Thresholds in Molecular Subgroups of Newly Diagnosed Isocitrate Dehydrogenase-Wildtype Glioblastoma.

Maximizing the extent of resection (EOR) improves outcomes in glioblastoma (GBM). However, previous GBM studies have not addressed the EOR impact in molecular subgroups beyond IDH1/IDH2 status. In the current article, we evaluate whether EOR confers a benefit in all GBM subtypes or only in particular molecular subgroups. A retrospective cohort of newly diagnosed GBM isocitrate dehydrogenase (IDH)-wildtype undergoing resection were prospectively included in a database (n = 138). EOR and residual tumor volume (RTV) were quantified with semiautomated software. Formalin-fixed paraffin-embedded tumor tissues were analyzed by targeted next-generation sequencing. The association between recurrent genomic alterations and EOR/RTV was evaluated using a recursive partitioning analysis to identify thresholds of EOR or RTV that may predict survival. The Kaplan-Meier methods and multivariable Cox proportional hazards regression methods were applied for survival analysis. Patients with EOR ≥88% experienced 44% prolonged overall survival (OS) in multivariable analysis (hazard ratio: 0.56, P = .030). Patients with alterations in the TP53 pathway and EOR <89% showed reduced OS compared to TP53 pathway altered patients with EOR>89% (10.5 vs 18.8 months; HR: 2.78, P = .013); however, EOR/RTV was not associated with OS in patients without alterations in the TP53 pathway. Meanwhile, in all patients with EOR <88%, PTEN-altered had significantly worse OS than PTEN-wildtype (9.5 vs 15.4 months; HR: 4.53, P < .001). Our results suggest that a subset of molecularly defined GBM IDH-wildtype may benefit more from aggressive resections. Re-resections to optimize EOR might be beneficial in a subset of molecularly defined GBMs. Molecular alterations should be taken into consideration for surgical treatment decisions in GBM IDH-wildtype.

Building semi-supervised decision trees with semi-cart algorithm

AbstractDecision trees are a fundamental statistical learning tool for addressing classification and regression problems through a recursive partitioning approach that effectively accommodates numerical and categorical data [1, 2]. The Classification and regression tree (CART) algorithm underlies modern Boosting methodologies such as Gradient boosting machine (GBM), Extreme gradient boosting (XGBoost), and Light gradient boosting machine (LightGBM). However, the standard CART algorithm may require improvement due to its inability to learn from unlabeled data. This study proposes several modifications to incorporate test data into the training phase. Specifically, we introduce a method based on Graph-based semi-supervised learning called “Distance-based Weighting,” which calculates and removes irrelevant records from the training set to accelerate the training process and improve performance. We present Semi-supervised classification and regression tree (Semi-Cart), a new implementation of CART that constructs a decision tree using weighted training data. We evaluated its performance on thirteen datasets from various domains. Our results demonstrate that Semi-Cart outperforms standard CART methods and contributes to statistical learning.

Coupled scRNA-seq and Bulk-seq reveal the role of HMMR in hepatocellular carcinoma.

Hyaluronan-mediated motility receptor (HMMR) is overexpressed in multiple carcinomas and influences the development and treatment of several cancers. However, its role in hepatocellular carcinoma (HCC) remains unclear. The "limma" and "GSVA" packages in R were used to perform differential expression analysis and to assess the activity of signalling pathways, respectively. InferCNV was used to infer copy number variation (CNV) for each hepatocyte and "CellChat" was used to analyse intercellular communication networks. Recursive partitioning analysis (RPA) was used to re-stage HCC patients. The IC50 values of various drugs were evaluated using the "pRRophetic" package. In addition, quantitative reverse transcription polymerase chain reaction (qRT-PCR) was performed to confirm HMMR expression in an HCC tissue microarray. Flow cytometry (FCM) and cloning, Edu and wound healing assays were used to explore the capacity of HMMR to regulate HCC tumour. Multiple cohort studies and qRT-PCR demonstrated that HMMR was overexpressed in HCC tissue compared with normal tissue. In addition, HMMR had excellent diagnostic performance. HMMR knockdown inhibited the proliferation and migration of HCC cells in vitro. Moreover, high HMMR expression was associated with "G2M checkpoint" and "E2F targets" in bulk RNA and scRNA-seq, and FCM confirmed that HMMR could regulate the cell cycle. In addition, HMMR was involved in the regulation of the tumour immune microenvironment via immune cell infiltration and intercellular interactions. Furthermore, HMMR was positively associated with genomic heterogeneity with patients with high HMMR expression potentially benefitting more from immunotherapy. Moreover, HMMR was associated with poor prognosis in patients with HCC and the re-staging by recursive partitioning analysis (RPA) gave a good prognosis prediction value and could guide chemotherapy and targeted therapy. The results of the present study show that HMMR could play a role in the diagnosis, prognosis, and treatments of patients with HCC based on bulk RNA-seq and scRAN-seq analyses and is a promising molecular marker for HCC.

Cardiometabolic and immune response to exercise training in patients with metabolic syndrome: retrospective analysis of two randomized clinical trials.

Metabolic syndrome (MetS) is defined by the presence of central obesity plus ≥two metabolic/cardiovascular risk factors (RF), with inflammation being a major disease-driving mechanism. Structured endurance exercise training (ET) may positively affect these traits, as well as cardiorespiratory fitness (V̇O2peak). We explore individual ET-mediated improvements of MetS-associated RF in relation to improvements in V̇O2peak and inflammatory profile. MetS patients from two randomized controlled trials, ExMET (n = 24) and OptimEx (n = 34), had performed 4- or 3-months supervised ET programs according to the respective trial protocol. V̇O2peak, MetS-defining RFs (both RCTs), broad blood leukocyte profile, cytokines and plasma proteins (ExMET only) were assessed at baseline and follow-up. Intra-individual changes in RFs were analysed for both trials separately using non-parametric approaches. Associations between changes in each RF over the exercise period (n-fold of baseline values) were correlated using a non-parametrical approach (Spearman). RF clustering was explored by uniform manifold approximation and projection (UMAP) and changes in RF depending on other RF or exercise parameters were explored by recursive partitioning. Four months of ET reduced circulating leukocyte counts (63.5% of baseline, P = 8.0e-6), especially effector subtypes. ET response of MetS-associated RFs differed depending on patients' individual RF constellation, but was not associated with individual change in V̇O2peak. Blood pressure lowering depended on cumulative exercise duration (ExMET: ≥102 min per week; OptimEx-MetS: ≥38 min per session) and baseline triglyceride levels (ExMET: <150 mg/dl; OptimEx-MetS: <174.8 mg/dl). Neuropilin-1 plasma levels were inversely associated with fasting plasma triglycerides (R: -0.4, P = 0.004) and changes of both parameters during the ET phase were inversely correlated (R: -0.7, P = 0.0001). ET significantly lowered effector leukocyte blood counts. The improvement of MetS-associated cardiovascular RFs depended on individual basal RF profile and exercise duration but was not associated with exercise-mediated increase in V̇O2peak. Neuropilin-1 may be linked to exercise-mediated triglyceride lowering.

Extent of Resection Thresholds in Molecular Subgroups of IDH-Wildtype Glioblastoma

INTRODUCTION: Maximizing the extent of resection (EOR) improves outcomes in glioblastoma (GBM). However, prior GBM studies have not addressed the impact of EOR in molecular subgroups of GBM beyond IDH1/IDH2 status. Therefore, it remains unclear whether EOR confers a benefit in all GBM subtypes or only in particular molecular subgroups. METHODS: Patients with newly diagnosed GBM IDH-wildtype undergoing resection were prospectively included in a database (n=138). EOR and RTV were quantified with semi-automated software. Formalin-fixed paraffin-embedded tumor tissues were analyzed by targeted next-generation sequencing. The association between recurrent genomic alterations and EOR/RTV was evaluated using a recursive partitioning analysis (RPA) to identify thresholds of EOR or RTV that may predict survival. The Kaplan-Meier methods and multivariable Cox proportional hazards regression methods were applied for survival analysis. RESULTS: Patients with EOR = 95.9% and younger than 67.5 years experienced improved survival compared to older patients with EOR &lt;95.9% (Hazard ratio [HR] 5.85, p &lt; 0.002). Patients with alterations in the TP53 pathway and EOR &lt;88.72% showed reduced OS (mOS: 10.5 vs. 18.8 months; HR: 2.78, p = 0.013). However, EOR/RTV was not associated with OS in patients without alterations in the TP53 pathway. Among patients with EOR &lt;87.69%, PTEN altered had significantly worse overall survival than PTEN wildtype (9.5 vs. 15.4 months; HR: 4.53, p &lt; 0.001). CONCLUSIONS: Our results suggest that a subset of molecularly defined GBMs IDH-wildtype may benefit more from aggressive resections. Re-resections to optimize EOR might be beneficial in a subset of molecularly defined GBMs. Molecular alterations should be taken into consideration for surgical treatment decisions in GBM IDH-wildtype.

Differentiation between adrenocortical carcinoma and lipid-poor adrenal adenoma using a multiparametric MRI-based diagnostic algorithm

PurposeThe purpose of this study was to evaluate the capabilities of multiparametric magnetic resonance imaging (MRI) in differentiating between lipid-poor adrenal adenoma (LPAA) and adrenocortical carcinoma (ACC). Materials and methodsPatients of two centers who underwent surgical resection of LPAA or ACC after multiparametric MRI were retrospectively included. A training cohort was used to build a diagnostic algorithm obtained through recursive partitioning based on multiparametric MRI variables, including apparent diffusion coefficient and chemical shift signal ratio (i.e., tumor signal intensity index). The diagnostic performances of the multiparametric MRI-based algorithm were evaluated using a validation cohort, alone first and then in association with adrenal tumor size using a cut-off of 4 cm. Performances of the diagnostic algorithm for the diagnosis of ACC vs. LPAA were calculated using pathology as the reference standard. ResultsFifty-four patients (27 with LPAA and 27 with ACC; 37 women; mean age, 48.5 ± 13.3 [standard deviation (SD)] years) were used as the training cohort and 61 patients (24 with LPAA and 37 with ACC; 47 women; mean age, 49 ± 11.7 [SD] years) were used as the validation cohort. In the validation cohort, the diagnostic algorithm yielded best accuracy for the diagnosis of ACC vs. LPAA (75%; 46/61; 95% CI: 55–88) when used without lesion size. Best sensitivity was obtained with the association of the diagnostic algorithm with tumor size (96%; 23/24; 95% CI: 80–99). Best specificity was obtained with the diagnostic algorithm used alone (76%; 28/37; 95% CI: 60–87). ConclusionA multiparametric MRI-based diagnostic algorithm that includes apparent diffusion coefficient and tumor signal intensity index helps discriminate between ACC and LPAA with high degrees of specificity and accuracy. The association of the multiparametric MRI-based diagnostic algorithm with adrenal lesion size helps maximize the sensitivity of multiparametric MRI for the diagnosis of ACC.

Patterns of the relationship between the Secchi disk depth and the optical characteristics of water in the Neva Estuary (Baltic Sea): the influence of environmental variables

The Secchi disc depth (Dsd) measurement is widely used to monitor eutrophication and the quality of the aquatic environment. This study aimed to investigate the relationship between Dsd and various factors, including the coefficient of attenuation of photosynthetically active radiation [Kd (PAR)], the depth of the euphotic zone (Deu), PAR at the Secchi disk depth (Esd) and the absorption coefficient of PAR (F) in the Neva Estuary, one of largest estuaries of the Baltic Sea. Environmental variables impacting these indices were identified using data collected from midsummer 2012 to 2020. The Dsd values in the estuary ranged from 0.3 to 4.0 m, with an average value of 1.8 m, while the Deu/Dsd ratio ranged from 1.5 to 6.0 with an average value of 2.8. These values were significantly lower than those observed in the open waters of the Baltic Sea. The highest Deu/Dsd ratio was observed in turbid waters characterized by high Kd(PAR) and low Dsd. Contrary to expectations, Dsd did not exhibit a significant relationship with the concentration of chlorophyll a, raising doubts about the utility of historical Dsd data for reconstructing phytoplankton development in the estuary. Principal component analysis did not identify the primary environmental variables strongly affecting the optical characteristics of water. However, recursive partitioning of the dataset using analysis of variance (CART approach) revealed that the concentration of suspended mineral matter (SMM) was the primary predictor of Deu/Dsd, Kd(PAR), and F. This SMM was associated with the frequent resuspension of bottom sediments during windy weather and construction activities in the estuary. Concentrations of suspended organic matter and the depth of the water area were found to be less significant as environmental variables. Furthermore, the CART approach demonstrated that different combinations of environmental variables in estuarine waters could result in similar optical indicator values. To reliably interpret the data and determine the optical characteristics of water in estuaries from Dsd, more complex models incorporating machine learning and neural connections are required. Additionally, reference determinations of Esd in various regions with specific sets of environmental variables would be valuable for comparative analyses and better understanding of estuarine systems.

Natural history of clonal haematopoiesis seen in real-world haematology settings.

Recursive partitioning of healthy consortia led to the development of the Clonal Hematopoiesis Risk Score (CHRS) for clonal haematopoiesis (CH); however, in the practical setting, most cases of CH are diagnosed after patients present with cytopenias or related symptoms. To address this real-world population, we characterize the clinical trajectories of 94 patients with CH and distinguish CH harbouring canonical DNMT3A/TET2/ASXL1 mutations alone ('sole DTA') versus all other groups ('non-sole DTA'). TET2, rather than DNMT3A, was the most prevalent mutation in the real-world setting. Sole DTA patients did not progress to myeloid neoplasm (MN) in the absence of acquisition of other mutations. Contrastingly, 14 (20.1%) of 67 non-sole DTA patients progressed to MN. CHRS assessment showed a higher frequency of high-risk CH in non-sole DTA (vs. sole DTA) patients and in progressors (vs. non-progressors). RUNX1 mutation conferred the strongest risk for progression to MN (odds ratio [OR] 10.27, 95% CI 2.00-52.69, p = 0.0053). The mean variant allele frequency across all genes was higher in progressors than in non-progressors (36.9% ± 4.62% vs. 24.1% ± 1.67%, p = 0.0064). This analysis in the post-CHRS era underscores the natural history of CH, providing insight into patterns of progression to MN.

Abstract 6865: Single cell analysis of melanoma reveals a prognostic myeloid cell associated with survival in melanoma with brain metastases

Abstract INTRODUCTION: The interface of the innate and adaptive immune system are a critical factor in tumor behavior and responses to immunotherapy with myeloid cell behavior varying widely between various biogeographies. We sought to elucidate myeloid sub-type differences to characterize biology and support therapeutic strategies. METHODS: scRNA-seq of primary skin, acral, and metastatic melanoma were combined from 6 datasets with 126 patients for analysis. After integration, cells were analyzed with scCCESS, which uses an artificial neural network to reduce data and optimize k for k-means clusters. Myeloid clusters with analyzed with Recursive Partitioning Analysis (RPA), differential expressed gene (DEG) analysis, and pseudobulk comparison of RPA groups by gene expression. RESULTS: 102,971 single cells from 126 patients were analyzed to generate a cluster of 15,303 myeloid cells further subjected to clustering generating 6 cell types. RPA analysis of 6 myeloid populations in 46 patients with melanoma brain metastases generated 3 nodes with differing median survival months (17 vs 41 vs 57, p=0.01). There was a trend towards more adjuvant immunotherapy (p=0.057) and targeted therapy (p=0.019) in the worst surviving group. Myeloid type 1 cells showed increased expression of CLEC10A and AXL genes compared to all other cells (adj p = 0.000). Pseudobulk comparison of patient groups of genes showed CLEC10A was significant between all groups (p&amp;lt;0.05). CONCLUSIONS: Although there were no significant differences in neoadjuvant treatment, increased infiltration of CLEC10A myeloid cells showed improved survival in melanoma brain metastases. Targets of current therapies, such as AXL tyrosine kinase, have heterogenous presence across multiple cell types beyond tumors that may impact wide response variances, further study of these populations will have significant impact in both biomarker and therapeutics development. Citation Format: M. Usman Ahmad, Leong Heo, Ramesh V. Nair, Saurabh Sharma, Amanda Kirane. Single cell analysis of melanoma reveals a prognostic myeloid cell associated with survival in melanoma with brain metastases [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 6865.

Forest harvest operations productivity forecasting: a decisions tree approach

ABSTRACT In recent years, machinery used in forest harvesting operations has incorporated the ability to collect data during the harvesting operation automatically. The processing of these data allows for obtaining new perspectives on the harvest characteristics. In this sense, it is that the development of predictive models for harvest productivity is approached by processing the automatically retrieved data. In turn, these new models pave the way to develop new tools for operations management decision-making processes, providing a data-driven approach. In this case, forest productivity is analyzed based on different harvesting operational configurations defined by stand, trees, species, operators, shifts, etc. which make it possible to adequately predict what the wood-harvested volume will be, and thus, synchronize the rest of the supply chain logistics operations. The data processing is done through decision tree methods. Different methods of decision trees based on exhaustive Chi-square automatic interaction detection (CHAID), recursive binary partition, and conditional inference based that also uses binary recursive partition are tested. The results show that decision recursive binary partition methods tend to model the entire spectrum of the target variable in a more balanced manner. While exhaustive CHAID-based methods tend to be more accurate in global terms but more unbalanced. As a general comment of the method, global confusion matrices are around 50% accurate, and some operational configurations and productivity classes are predicted with almost 90% accuracy.

A tree-recursive partitioned multicast mechanism for NoC-based deep neural network accelerator

In chip multiprocessor systems (CMPs), Network on Chip (NoC) has been widely used due to its advantages of favorable reusability, high reliability, and low power consumption. Recently, using NoC platforms to accelerate deep neural networks (DNNs) has become a new trend. This design can enable the intermediate computation results of DNNs to be transmitted within the chip, reducing the number of accesses to off-chip memory. However, a large amount of one-to-many traffic in the DNN accelerator will occupy the system bandwidth, which will significantly reduce the performance of the NoC platform dominated by one-to-one traffic. To address this issue, we propose a tree-based recursive partitioning multicast scheme (TRPM), which increases the path diversity and improves the system bandwidth. We also design a single-cycle per-hop router architecture, which effectively enhances the transmission efficiency of multicast packets. Detailed simulation results show that compared with the latest tree-based multicast algorithm for DNN accelerators, our scheme reduces the number of routed packets by 35%, the classification latency by 13.5% and the average packet latency by 14.5% on average.

Machine learning-based algorithms applied to drug prescriptions and other healthcare services in the Sicilian claims database to identify acromegaly as a model for the earlier diagnosis of rare diseases

Acromegaly is a rare disease characterized by a diagnostic delay ranging from 5 to 10 years from the symptoms’ onset. The aim of this study was to develop and internally validate machine-learning algorithms to identify a combination of variables for the early diagnosis of acromegaly. This retrospective population-based study was conducted between 2011 and 2018 using data from the claims databases of Sicily Region, in Southern Italy. To identify combinations of potential predictors of acromegaly diagnosis, conditional and unconditional penalized multivariable logistic regression models and three machine learning algorithms (i.e., the Recursive Partitioning and Regression Tree, the Random Forest and the Support Vector Machine) were used, and their performance was evaluated. The random forest (RF) algorithm achieved the highest Area under the ROC Curve value of 0.83 (95% CI 0.79–0.87). The sensitivity in the test set, computed at the optimal threshold of predicted probabilities, ranged from 28% for the unconditional logistic regression model to 69% for the RF. Overall, the only diagnosis predictor selected by all five models and algorithms was the number of immunosuppressants-related pharmacy claims. The other predictors selected by at least two models were eventually combined in an unconditional logistic regression to develop a meta-score that achieved an acceptable discrimination accuracy (AUC = 0.71, 95% CI 0.66–0.75). Findings of this study showed that data-driven machine learning algorithms may play a role in supporting the early diagnosis of rare diseases such as acromegaly.

Detecting Differential Item Functioning in Multidimensional Graded Response Models With Recursive Partitioning.

Differential item functioning (DIF) is a common challenge when examining latent traits in large scale surveys. In recent work, methods from the field of machine learning such as model-based recursive partitioning have been proposed to identify subgroups with DIF when little theoretical guidance and many potential subgroups are available. On this basis, we propose and compare recursive partitioning techniques for detecting DIF with a focus on measurement models with multiple latent variables and ordinal response data. We implement tree-based approaches for identifying subgroups that contribute to DIF in multidimensional latent variable modeling and propose a robust, yet scalable extension, inspired by random forests. The proposed techniques are applied and compared with simulations. We show that the proposed methods are able to efficiently detect DIF and allow to extract decision rules that lead to subgroups with well fitting models.

Development and Methodological Validation of a Modified Staging System for de Novo Metastatic Breast Cancer

Validation of a new method for prognostication of de novo metastatic breast cancer (dnMBC) to better reflect the heterogenecity of the disease. To perform external methodological validation of the Plichta staging system, a novel prognostic system for de novo metastatic breast cancer (dnMBC). This retrospective cohort study used a multicenter, nationwide, population-based Danish Breast Cancer Group database to validate the new method. Participants were patients with dnMBC diagnosed between 2010 and 2019. Data were analyzed from April to June 2023. A recursive partitioning analysis (RPA) was performed, as demonstrated by Plichta and colleagues, to group patients with similar overall survival (OS) based on clinical factors. The main outcome was to group patients into 4 prognostic groups based on 3-year OS as stage IVa, greater than 70%; stage IVb, 50% to 70%; stage IVc, 25% to less than 50%; or stage IVd, less than 25%. Bootstrapping was applied for 1000 iterations, with final stage assignments based on the most commonly occurring assignment. A total of 1859 women were included with a median (IQR) age of 69 (57-77) years. With a median potential follow-up of 89.9 (95% CI, 86.4-95.1) months and a median OS of 31.7 (95% CI, 29.5-34.1) months, the RPA stratified patients into 10 groups, with organ sites, estrogen receptor status, and human epidermal growth factor receptor 2 status as the key clinical factors. Three-year survival rates ranged from 62% (95% CI, 56%-69%) to 8% (95% CI, 3%-21%), which were further combined into 3 stage groups: IVb, 59.4% (95% CI, 56.2%-62.8%); IVc, 39.4% (95% CI, 36.2%-43.0%); and IVd, 15.4% (95% CI, 11.2%-21.3%) (P < .001). Following bootstrapping, an IVa group emerged, resulting in 4 stage groups with separate 3-year OS rates identified as IVa, 75.8% (95% CI, 67.8%-84.7%); IVb, 58.8% (95% CI, 55.5%-62.3%); IVc, 39.2% (95% CI, 35.8%-43.0%); and IVd, 14.4% (95% CI, 10.8%-19.4%) (P < .001). These findings provide external and independent validation of the methods applied in the novel Plichta staging system for dnMBC. This could guide future revisions of the current American Joint Committee on Cancer staging guidelines and may be incorporated as a stratification factor in clinical trials.

Myocarditis-A Helpful Algorithm to Overcome Diagnostic Challenges in the Pediatric Population.

This study was designed to investigate clinical differences between pediatric patients who presented with chest pain, tachycardia, and/or tachypnea who subsequently were or were not diagnosed with myocarditis. The results were used to develop a decision tree to aid in rapid diagnosis of pediatric myocarditis. A retrospective case-control study was performed using the electronic medical records of children aged 0 to 18 years between the years 2003 and 2020 with a complaint of chest pain, tachycardia, and/or tachypnea. Patients included in the study were those diagnosed with myocarditis and those with suspected myocarditis, which was ultimately ruled out. Demographic and clinical differences between the research groups were analyzed. A decision tree was rendered using the rpart (Recursive Partitioning and Regression Trees) package. Four thousand one hundred twenty-five patients were screened for eligibility. Seventy-three myocarditis patients and 292 nonmyocarditis patients were included. Compared with the control group, the study group was found to have a higher mean respiratory rate (37 ± 23 vs 23 ± 7 breaths per minute) and mean heart rate (121 ± 44 vs 97 ± 25 beats per minute) and lower mean systolic and diastolic blood pressure (102 ± 27/56 ± 17 mm Hg vs 114 ± 14/67 ± 10 mm Hg). The mean white blood cell count was greater in the case group (13 ± 6 vs 10 ± 5 × 103/μL). A decision tree was rendered using simple demographic and clinical variables. The accuracy of the algorithm was 85.2%, with 100% accuracy in patients aged 0 to 2.5 years and 69% in patients aged 2.5 to 18 years. The clinical and laboratory characteristics described in this study were similar to what is described in the literature. The decision tree may aid in the diagnosis of myocarditis in patients 2.5 years and younger. In the population aged 2.5 to 18 years, the decision tree did not constitute an adequate tool for detecting myocarditis.

A New Model for Building Energy Modeling and Management Using Predictive Analytics: Partitioned Hierarchical Multitask Regression (PHMR)

Buildings are major consumers of energy, accounting for a significant proportion of total energy use worldwide. This substantial energy consumption not only leads to increased operational costs but also contributes to environmental concerns such as greenhouse gas emissions. In the United States, building energy consumption accounts for about 40% of total energy use, highlighting the importance of efficient energy management. Therefore, accurate prediction of energy usage in buildings is crucial. However, accurate prediction of building energy consumption remains a challenge due to the intricate interaction of indoor and outdoor variables. This study introduces the Partitioned Hierarchical Multitask Regression (PHMR), an innovative model integrating recursive partition regression (RPR) with multitask learning (hierML). PHMR adeptly predicts building energy consumption by integrating both indoor factors, such as building design and operational variables, and outdoor environmental influences. Rigorous simulation studies illustrate PHMR’s efficacy. It outperforms traditional single-predictor regression models, achieving a 32.88% to 41.80% higher prediction accuracy, especially in scenarios with limited training data. This highlights PHMR’s robustness and adaptability. The practical application of PHMR in managing a modular house’s Heating, Ventilation, and Air Conditioning (HVAC) system in Spain resulted in a 37% improvement in prediction accuracy. This significant efficiency gain is evidenced by a high Pearson correlation coefficient (0.8) between PHMR’s predictions and actual energy consumption. PHMR not only offers precise predictions for energy consumption but also facilitates operational cost reductions, thereby enhancing sustainability in building energy management. Its application in a real-world setting demonstrates the model’s potential as a valuable tool for architects, engineers, and facility managers in designing and maintaining energy-efficient buildings. The model’s integration of comprehensive data analysis with domain-specific knowledge positions it as a crucial asset in advancing sustainable energy practices in the building sector.

Examining Financial Hardship and Caregiver Subgroups in Kinship Foster Placements: A Machine Learning Approach

Children placed with kinship foster parents can experience less disruption and stronger family ties than children in non-kinship placements. However, financial hardship can restrict kinship caregivers from taking in relatives’ children. This study investigated (1) kinship caregivers’ financial standing compared to a national subsample of caregivers and (2) whether certain factors moderate the likelihood that a kinship caregiver will be able to provide care for additional non-relative children without additional financial assistance from the Department of Social Services (DSS). This study utilized primary data from 345 relatives across North Carolina and nationally representative secondary data on 6394 individuals’ financial circumstances. One-sample t-tests and chi-square goodness-of-fit tests revealed that caregivers who participated in our study generally fared better financially than caregivers at the national level. Model-based recursive partitioning results showed that if an additional child is placed in the home, the caregiver’s perceived capacity to provide care without extra DSS support decreased by approximately 19%, with a greater decrease (35%) among a subgroup of caregivers with low financial well-being status. The heterogeneity in caregivers’ experiences, capacities, and financial needs buttresses the need for nuanced interventions and programs targeting these caregivers, enabling them to provide more stable care for children placed in their homes.

Comparison of troponin and natriuretic peptides in Takotsubo syndrome and acute coronary syndrome: a meta-analysis

ObjectiveTakotsubo syndrome (TTS) is an acute heart failure syndrome which resembles acute coronary syndrome (ACS) at presentation. Differentiation requires coronary angiography, but where this does not occur immediately, cardiac biomarkers...

The International Association for the Study of Lung Cancer Mesothelioma Staging Project: Proposals for Revisions of the “T” Descriptors in the Forthcoming Ninth Edition of the TNM Classification for Pleural Mesothelioma

IntroductionThe primary tumor (T) component in the eighth edition of pleural mesothelioma (PM) staging system is based on pleural involvement and extent of invasion. Quantitative assessment of pleural tumor has been found to be prognostic. We explored quantitative and qualitative metrics to develop recommendations for T descriptors in the upcoming ninth edition of the PM staging system. MethodsThe International Association for the Study of Lung Cancer prospectively collected data on patients with PM. Sum of maximum pleural thickness (Psum) was recorded. Optimal combinations of Psum and eighth edition cT descriptors were assessed using recursive binary splitting algorithm, with bootstrap resampling to correct for the adaptive nature of the splitting algorithm, and validated in the eighth edition data. Overall survival (OS) was calculated by the Kaplan-Meier method and differences in OS assessed by the log-rank test. ResultsOf 7338 patients submitted, 3598 were eligible for cT analysis and 1790 had Psum measurements. Recursive partitioning identified optimal cutpoints of Psum at 12 and 30 mm, which, in combination with extent of invasion, yielded four prognostic groups for OS. Fmax greater than 5 mm indicated poor prognosis. cT4 category (based on invasion) revealed similar performance to eighth edition. Three eighth edition descriptors were eliminated based on low predictive accuracy. Eighth edition pT descriptors remained valid in ninth edition analyses. ConclusionGiven reproducible prognostication by Psum, size criteria will be incorporated into cT1 to T3 categories in the ninth edition. Current cT4 category and all pT descriptors will be maintained, with reclassification of fissural invasion as pT2.