Assessing the ability of an instrumental variable causal forest algorithm to personalize treatment evidence using observational data: the case of early surgery for shoulder fracture.

BACKGROUND: Comparative effectiveness research (CER) using observational databases has been suggested to obtain personalized evidence of treatment effectiveness. Inferential difficulties remain using traditional CER approaches especially related to designating patients to reference classes a priori. A novel Instrumental Variable Causal Forest Algorithm (IV-CFA) has the potential to provide personalized evidence using observational data without designating reference classes a priori, but the consistency of the evidence when varying key algorithm parameters remains unclear. We investigated the consistency of IV-CFA estimates through application to a database of Medicare beneficiaries with proximal humerus fractures (PHFs) that previously revealed heterogeneity in the effects of early surgery using instrumental variable estimators. METHODS: IV-CFA was used to estimate patient-specific early surgery effects on both beneficial and detrimental outcomes using different combinations of algorithm parameters and estimate variation was assessed for a population of 72,751 fee-for-service Medicare beneficiaries with PHFs in 2011. Classification and regression trees (CART) were applied to these estimates to create ex-post reference classes and the consistency of these classes were assessed. Two-stage least squares (2SLS) estimators were applied to representative ex-post reference classes to scrutinize the estimates relative to known 2SLS properties. RESULTS: IV-CFA uncovered substantial early surgery effect heterogeneity across PHF patients, but estimates for individual patients varied with algorithm parameters. CART applied to these estimates revealed ex-post reference classes consistent across algorithm parameters. 2SLS estimates showed that ex-post reference classes containing older, frailer patients with more comorbidities, and lower utilizers of healthcare were less likely to benefit and more likely to have detriments from higher rates of early surgery. CONCLUSIONS: IV-CFA provides an illuminating method to uncover ex-post reference classes of patients based on treatment effects using observational data with a strong instrumental variable. Interpretation of treatment effect estimates within each ex-post reference class using traditional CER methods remains conditional on the extent of measured information in the data.

Plasma amyloid ß 40/42 ratio predicts cerebral amyloidosis in cognitively normal individuals at risk for Alzheimer's disease.

INTRODUCTION: Blood-based biomarkers of pathophysiological brain amyloid ß (Aß) accumulation, particularly for preclinical target and large-scale interventions, are warranted to effectively enrich Alzheimer's disease clinical trials and management. METHODS: We investigated whether plasma concentrations of the Aß1-40/Aß1-42 ratio, assessed using the single-molecule array (Simoa) immunoassay, may predict brain Aß positron emission tomography status in a large-scale longitudinal monocentric cohort (N = 276) of older individuals with subjective memory complaints. We performed a hypothesis-driven investigation followed by a no-a-priori hypothesis study using machine learning. RESULTS: The receiver operating characteristic curve and machine learning showed a balanced accuracy of 76.5% and 81%, respectively, for the plasma Aß1-40/Aß1-42 ratio. The accuracy is not affected by the apolipoprotein E (APOE) ε4 allele, sex, or age. DISCUSSION: Our results encourage an independent validation cohort study to confirm the indication that the plasma Aß1-40/Aß1-42 ratio, assessed via Simoa, may improve future standard of care and clinical trial design.

Macular Telangiectasia Type 2: A Classification System Using MultiModal Imaging MacTel Project Report Number 10.

Purpose: To develop a severity classification for macular telangiectasia type 2 (MacTel) disease using multimodal imaging. Design: An algorithm was used on data from a prospective natural history study of MacTel for classification development. Subjects: A total of 1733 participants enrolled in an international natural history study of MacTel. Methods: The Classification and Regression Trees (CART), a predictive nonparametric algorithm used in machine learning, analyzed the features of the multimodal imaging important for the development of a classification, including reading center gradings of the following digital images: stereoscopic color and red-free fundus photographs, fluorescein angiographic images, fundus autofluorescence images, and spectral-domain (SD)-OCT images. Regression models that used least square method created a decision tree using features of the ocular images into different categories of disease severity. Main Outcome Measures: The primary target of interest for the algorithm development by CART was the change in best-corrected visual acuity (BCVA) at baseline for the right and left eyes. These analyses using the algorithm were repeated for the BCVA obtained at the last study visit of the natural history study for the right and left eyes. Results: The CART analyses demonstrated 3 important features from the multimodal imaging for the classification: OCT hyper-reflectivity, pigment, and ellipsoid zone loss. By combining these 3 features (as absent, present, noncentral involvement, and central involvement of the macula), a 7-step scale was created, ranging from excellent to poor visual acuity. At grade 0, 3 features are not present. At the most severe grade, pigment and exudative neovascularization are present. To further validate the classification, using the Generalized Estimating Equation regression models, analyses for the annual relative risk of progression over a period of 5 years for vision loss and for progression along the scale were performed. Conclusions: This analysis using the data from current imaging modalities in participants followed in the MacTel natural history study informed a classification for MacTel disease severity featuring variables from SD-OCT. This classification is designed to provide better communications to other clinicians, researchers, and patients. Financial Disclosures: Proprietary or commercial disclosure may be found after the references.

Customer churn prediction for telecommunication industry: A Malaysian Case Study.

Background: Customer churn is a term that refers to the rate at which customers leave the business. Churn could be due to various factors, including switching to a competitor, cancelling their subscription because of poor customer service, or discontinuing all contact with a brand due to insufficient touchpoints. Long-term relationships with customers are more effective than trying to attract new customers. A rise of 5% in customer satisfaction is followed by a 95% increase in sales. By analysing past behaviour, companies can anticipate future revenue. This article will look at which variables in the Net Promoter Score (NPS) dataset influence customer churn in Malaysia's telecommunications industry.  The aim of This study was to identify the factors behind customer churn and propose a churn prediction framework currently lacking in the telecommunications industry.   Methods: This study applied data mining techniques to the NPS dataset from a Malaysian telecommunications company in September 2019 and September 2020, analysing 7776 records with 30 fields to determine which variables were significant for the churn prediction model. We developed a propensity for customer churn using the Logistic Regression, Linear Discriminant Analysis, K-Nearest Neighbours Classifier, Classification and Regression Trees (CART), Gaussian Naïve Bayes, and Support Vector Machine using 33 variables.   Results: Customer churn is elevated for customers with a low NPS. However, an immediate helpdesk can act as a neutral party to ensure that the customer needs are met and to determine an employee's ability to obtain customer satisfaction.   Conclusions: It can be concluded that CART has the most accurate churn prediction (98%). However, the research is prohibited from accessing personal customer information under Malaysia's data protection policy. Results are expected for other businesses to measure potential customer churn using NPS scores to gather customer feedback.

Identification of significant risks in pediatric acute lymphoblastic leukemia (ALL) through machine learning (ML) approach.

Pediatric acute lymphoblastic leukemia (ALL) through machine learning (ML) technique was analyzed to determine the significance of clinical and phenotypic variables as well as environmental conditions that can identify the underlying causes of child ALL. Fifty pediatric patients (n = 50) included who were diagnosed with acute lymphoblastic leukemia (ALL) according to the inclusion and exclusion criteria. Clinical variables comprised of the blood biochemistry (CBC, LFTs, RFTs) results, and distribution of type of ALL, i.e., T ALL or B ALL. Phenotypic data included the age, sex of the child, and consanguinity, while environmental factors included the habitat, socioeconomic status, and access to filtered drinking water. Fifteen different features/attributes were collected for each case individually. To retrieve most useful discriminating attributes, four different supervised ML algorithms were used including classification and regression trees (CART), random forest (RM), gradient boosted machine (GM), and C5.0 decision tree algorithm. To determine the accuracy of the derived CART algorithm on future data, a ten-fold cross validation was performed on the present data set. The ALL was common in children of age below 5 years in male patients whole belonged to middle class family of rural areas. (B-ALL) was most frequent as compared with T-ALL. The consanguinity was present in 54% of cases. Low levels of platelets and hemoglobin and high levels of white blood cells were reported in child ALL patients. CART provided the best and complete fit for the entire data set yielding a 99.83% model fit accuracy, and a misclassification of 0.17% on the entire sample space, while C5.0 reported 98.6%, random forest 94.44%, and gradient boosted machine resulted in 95.61% fitting. The variable importance of each primary discriminating attribute is platelet 43%, hemoglobin 24%, white blood cells 4%, and sex of the child 4%. An overall accuracy of 87.4% was recorded for the classifier. Platelet count abnormality can be considered as a major factor in predicting pediatric ALL. The machine learning algorithms can be applied efficiently to provide details for the prognosis for better treatment outcome. Graphical Abstract Identification of significant risks in pediatric acute lymphoblastic leukemia (ALL) through machine learning (ML) approach.

Analyzing pedestrian crash injury severity under different weather conditions.

OBJECTIVE: Pedestrians are the most vulnerable road users due to the lack of mass, speed, and protection compared to other types of road users. Adverse weather conditions may reduce road friction and visibility and thus increase crash risk. There is limited evidence and considerable discrepancy with regard to impacts of weather conditions on injury severity in the literature. This article investigated factors affecting pedestrian injury severity level under different weather conditions based on a publicly available accident database in Great Britain. METHOD: Accident data from Great Britain that are publicly available through the STATS19 database were analyzed. Factors associated with pedestrian, driver, and environment were investigated using a novel approach that combines a classification and regression tree with random forest approach. RESULTS: Significant severity predictors under fine weather conditions from the models included speed limits, pedestrian age, light conditions, and vehicle maneuver. Under adverse weather conditions, the significant predictors were pedestrian age, vehicle maneuver, and speed limit. CONCLUSIONS: Elderly pedestrians are associated with higher pedestrian injury severities. Higher speed limits increase pedestrian injury severity. Based on the research findings, recommendations are provided to improve pedestrian safety.

Mixture effects of 30 environmental contaminants on incident metabolic syndrome-A prospective study.

BACKGROUND: Several cross-sectional studies have linked different environmental contaminants to the metabolic syndrome (MetS). However, mixture effects have not been investigated and no prospective studies exist regarding environmental contaminants and the MetS. OBJECTIVES: To study mixture effects of contaminants on the risk of incident MetS in a prospective fashion. METHODS: Our sample consisted of 452 subjects from the Prospective Study of the Vasculature in Uppsala Seniors (PIVUS) study (50% women, all aged 70years) free from the MetS at baseline, being followed for 10years. At baseline, 30 different environmental contaminants were measured; 6 polychlorinated biphenyls (PCBs), 3 organochlorine (OC) pesticides, one dioxin, one polybrominated diphenyl ether (all in plasma), 8 perfluoroalkyl substances (in plasma) and 11 metals (in whole blood). The MetS was defined by the ATPIII/NCEP criteria. Gradient boosted Classification and Regression Trees (CARTs) was used to evaluate potential synergistic and additive mixture effects on incident MetS. RESULTS: During 10-year follow-up, 92 incident cases of the MetS occurred. PCB126, PCB170, hexachlorobenzene (HCB) and PCB118 levels were all associated with incident MetS in an additive fashion (OR 1.73 for a change from 10th to 90th percentile (95%CI 1.24-3.04) for PCB126, OR 0.63 (0.42-0.78) for PCB170, OR 1.44 (1.09-2.20) for HCB and OR 1.46 (1.13-2.43) for PCB118). No synergistic effects were found. CONCLUSION: A mixture of environmental contaminants, with PCB126, PCB170, HCB and PCB118 being the most important, showed associations with future development of the MetS in an additive fashion in this prospective study. Thus, mixture effects of environmental contaminants could contribute to the development of cardio-metabolic derangements.

Repeated measurements of blood lactate concentration as a prognostic marker in horses with acute colitis evaluated with classification and regression trees (CART) and random forest analysis.

The objective of this study was to investigate the prognostic value of single and repeated measurements of blood l-lactate (Lac) and ionised calcium (iCa) concentrations, packed cell volume (PCV) and plasma total protein (TP) concentration in horses with acute colitis. A total of 66 adult horses admitted with acute colitis (<24 h) to a referral hospital in the 2002-2011 period were included. The prognostic value of Lac, iCa, PCV and TP recorded at admission and 6 h post admission was analysed with univariate analysis, logistic regression, classification and regression trees, as well as random forest analysis. Ponies and Icelandic horses made up 59% of the population, whilst the remaining 41% were horses. Blood lactate concentration at admission was the only individual parameter significantly associated with probability of survival to discharge (P < 0.001). In a training sample, a Lac cut-off value of 7 mmol/L had a sensitivity of 0.66 and a specificity of 0.92 in predicting survival. In independent test data, the sensitivity was 0.69 and the specificity was 0.76. At the observed survival rate (38%), the optimal decision tree identified horses as non-survivors when the Lac at admission was ≥4.3 mmol/L and the Lac 6 h post admission stayed at >2 mmol/L (sensitivity, 0.72; specificity, 0.8). In conclusion, blood lactate concentration measured at admission and repeated 6 h later aided the prognostic evaluation of horses with acute colitis in this population with a very high mortality rate. This should allow clinicians to give a more reliable prognosis for the horse.