CHAID Research Articles

Penerapan Metode Klasifikasi Chi-Square Automatic Interaction Detection dan Exhaustive Chi-Square Automatic Interaction Detection

The Chi-Square Automatic Interaction Detection (CHAID) and Exhaustive CHAID methods are nonparametric statistical methods that can be used to classify. CHAID and Exhaustive CHAID were used to determine the significant relationship between the dependent variable and the independent variables based on the chi-square independence test. This study was applied to data on the study period of students of FMIPA UNMUL batch 2014. Based on the CHAID and Exhaustive CHIAD methods, it can be seen that the dependent variable of the study period has a significant relationship with the independent variable, namely the study program and GPA predicate. Where students who graduated on time for the Statistics, Biology and Chemistry study program with a satisfactory GPA predicate of 82 students and with a very satisfactory GPA predicate and cum laude with 46 students. Meanwhile, students who did not graduate on time for the Statistics, Biology and Chemistry study program with an adequate GPA predicate of 5 students, a satisfactory GPA predicate of 41 students, very satisfactory and cum laude with 3 students. Students who graduated on time for the Physics study program were 13 students and those who did not graduate on time were 34 students. The chi-square independence test performed on the CHAID method uses fewer possible categorical pairs than the Exhaustive CHAID method which uses all possible categorical pairs so that it requires a long computational and calculation time.

Variability of Meat and Carcass Quality from Worldwide Native Chicken Breeds.

The present research aimed to determine the differential clustering patterns of carcass and meat quality traits in local chicken breeds from around the world and to develop a method to productively characterize minority bird populations. For this, a comprehensive meta-analysis of 91 research documents that dealt with the study of chicken local breeds through the last 20 years was performed. Thirty-nine traits were sorted into the following clusters: weight-related traits, histological properties, pH, color traits, water-holding capacity, texture-related traits, flavor content-related nucleotides, and gross nutrients. Multicollinearity problems reported for pH 72 h post mortem, L* meat 72 h post mortem, a* meat 72 h post mortem, sex, firmness, and chewiness, were thus discarded from further analyses (VIF < 5). Data-mining cross-validation and chi-squared automatic interaction detection (CHAID) decision tree development allowed us to detect similarities across genotypes. Easily collectable trait, such as shear force, muscle fiber diameter, carcass/pieces weight, and pH, presented high explanatory potential of breed variability. Hence, the aforementioned variables must be considered in the experimental methodology of characterization of carcass and meat from native genotypes. This research enables the characterization of local chicken populations to satisfy the needs of specific commercial niches for poultry meat consumers.

Analysis of awareness of academicians and graduate students about digital product copyrights with chi-squared automatic interaction detector

Analysis of awareness of academicians and graduate students about digital product copyrights with chi-squared automatic interaction detector

HYPERTENSIVE HEART DISEASE IN ADOLESCENCE. PRELIMINARY RESULTS OF THE PESESCAD-HTA STUDY

Objective: Identify the presence of hypertensive heart disease and its relationship with prehypertension and hypertension Design and method: A descriptive, cross-sectional study was carried out in 385 prehypertensive adolescents and 128 adolescents with essential hypertension, aged 12–15 years, from among a total of 1,545 adolescents screened in the School Screening for High Blood Pressure in Adolescents Project (PESESCAD-HTA). An echocardiogram was performed in 513 adolescents (prehypertensive plus hypertensive). For the multivariate analysis of risk factors related to LVH, a decision tree was obtained using the chi square automatic interaction detector (CHAID) technique. Results: Among prehypertensive and hypertensive adolescents, the prevalence of left ventricular hypertrophy was 6.49% (CI = 4.43–9.41) and 21.09% (CI = 14.92–58.95), respectively. In the sample of 513 individuals with prehypertension and hypertension, a decision tree was designed, using the chi square automatic interaction detector (CHAID) technique, with the presence of left ventricular hypertrophy as the dependent variable. Conclusions: The best predictors of left ventricular hypertrophy were a family history of obesity, and its interaction with the age and the sex of the adolescent.

Knowledge discovery in manufacturing datasets using data mining techniques to improve business performance

Recently due &lt;span&gt;to the explosion in the data field, there is a great interest in the data science areas such as big data, artificial intelligence, data mining, and machine learning. Knowledge gives control and power in numerous manufacturing areas. Companies, factories, and all organizations owners aim to benefit from their huge; recorded data that increases and expands very quickly to improve their business and improve the quality of their products. In this research paper, the knowledge discovery in databases (KDD) technique has been followed, “association rules” algorithms “Apriori algorithm”, and “chi-square automatic interaction detection (CHAID) analysis tree” have been applied on real datasets belonging to (Emisal factory). This factory annually loses tons of production due to the breakdowns that occur daily inside the factory, which leads to a loss of profit. After analyzing and understanding the factory product processes, we found some breakdowns occur a lot of days during the product lifecycle, these breakdowns affect badly on the production lifecycle which led to a decrease in sales. So, we have mined the data and used the mentioned methods above to build a predictive model that will predict the breakdown types and help the factory owner to manage the breakdowns risks by taking accurate actions before the breakdowns happen.&lt;/span&gt;

Intersections of class, lifestyle and politics. New observations from Norway

Although social class was once central to political sociology, it has become increasingly less so; many analysts now believe that one’s class position is less important in determining political attitudes and political party preferences. Simultaneously, more attention has been paid to what might be called the culturalization of politics, as epitomized by the US culture wars and stereotypes like the “latte-drinking liberal.” Here, political attitudes are regarded as primarily structured by people’s lifestyles and broader way of life. But do political preferences have to be explained by either relations of sociomaterial conditions (e.g. class) or cultural orientations (e.g. status and lifestyles)? In this article, we argue in favor of an approach that aims to reconcile these factors, allowing for the empirical mapping of whether and how they intersect in shaping political party preferences. We investigate this by using detailed Norwegian survey data to measure the extent to which intraclass heterogeneity in political party choices can be accounted for by the interaction between class and lifestyle. We employ a novel combination of Multiple Correspondence Analysis (MCA) and Chi-Squared Automatic Interaction Detection (CHAID). In drawing on constructed models of the social space and the space of lifestyles, we show that there are important correspondences between these spaces and that their interaction may help account for party choices. The results highlight the need for a more complex account than that suggested in recent works of cultural stratification research.

Attitude-Based Segmentation of Residential Self-Selection and Travel Behavior Changes Affected by COVID-19

This study evaluated the effects of COVID-19 on attitudes toward residential associated with travel behavior on decisions regarding future relocation. Chi-square automatic interaction detection was used to generate tree and classification segments to investigate the various segmentations of travelers and residents around mass transit stations. The decision tree revealed that the most influential variables were the number of transport card ownerships, walking distance to the nearest mass station, number of households, type of resident, property ownership, travel cost, and trip frequency. During the COVID-19 pandemic, people have concentrated on reducing travel time, reducing the number of transfers, and decreasing unnecessary trips. Consequently, people who live near mass transit stations less than 400 and 400–1000 m away prefer to live in residential and rural areas in the future. Structural Equation Modeling was used to confirm the relationship between attitudes in normal and pandemic situations. According to the findings, attitudes toward residential accessibility of travel modes were a significant determinant of attitudes toward residential location areas. This research demonstrates travelers’ and residents’ uncertain decision-making regarding relocation, allowing policymakers and transport authorities to better understand their behavior to improve transportation services.

Social network analysis: Understanding nurses' advice-seeking interactions.

This study aimed to determine advice-seeking interactions of nurses in a private hospital by using social network analysis. This study was designed as a cross-sectional descriptive study. The study was conducted in a private hospital with 70 nurses. The data were collected with a social network analysis questionnaire. The social network analysis (SNA) focused on certain values such as network density, component, degree centrality, and betweenness centrality. The SNA was carried out using UCINET, and statistical analyses were performed with SPSS version 23.0. The network density was reported to be 0.062, and it was composed of three components. It was further noted that nurse Y1 was found to have the highest scores of degree and betweenness centrality. Chi-Square Automatic Interaction Detector (CHAID) analysis indicated that the most common variables that affected degree centrality score were education, department, and position. It was concluded that social network analysis was a useful instrument to delineate strengths and weaknesses of seeking advice relationships among nurses. Top- and middle-level nursing managers occupy a significant position in advice-seeking networks. Nursing managers with higher education degrees will absolutely improve advice-seeking networks.

A predictive ambulance dispatch algorithm to the scene of a motor vehicle crash: the search for optimal over and under triage rates.

BackgroundCalls for emergency medical assistance at the scene of a motor vehicle crash (MVC) substantially contribute to the demand on ambulance services. Triage by emergency medical dispatch systems is therefore important, to ensure the right care is provided to the right patient, in the right amount of time. A lights and sirens (L&S) response is the highest priority ambulance response, also known as a priority one or hot response. In this context, over triage is defined as dispatching an ambulance with lights and sirens (L&S) to a low acuity MVC and under triage is not dispatching an ambulance with L&S to those who require urgent medical care. We explored the potential for crash characteristics to be used during emergency ambulance calls to identify those MVCs that required a L&S response.MethodsWe conducted a retrospective cohort study using ambulance and police data from 2014 to 2016. The predictor variables were crash characteristics (e.g. road surface), and Medical Priority Dispatch System (MPDS) dispatch codes. The outcome variable was the need for a L&S ambulance response. A Chi-square Automatic Interaction Detector technique was used to develop decision trees, with over/under triage rates determined for each tree. The model with an under/over triage rate closest to that prescribed by the American College of Surgeons Committee on Trauma (ACS COT) will be deemed to be the best model (under triage rate of ≤ 5% and over triage rate of between 25–35%.ResultsThe decision tree with a 2.7% under triage rate was closest to that specified by the ACS COT, had as predictors—MPDS codes, trapped, vulnerable road user, anyone aged 75 + , day of the week, single versus multiple vehicles, airbag deployment, atmosphere, surface, lighting and accident type. This model had an over triage rate of 84.8%.ConclusionsWe were able to derive a model with a reasonable under triage rate, however this model also had a high over triage rate. Individual EMS may apply the findings here to their own jurisdictions when dispatching to the scene of a MVC.Supplementary InformationThe online version contains supplementary material available at 10.1186/s12873-022-00609-5.

Study of Hospitalization Costs in Patients with Cerebral Ischemia Based on E-CHAID Algorithm.

Background The aging of the population has led to a rapid increase in the prevalence of most neurological diseases between 1990 and 2016, with a growth rate of up to 117%, which has put enormous pressure on medical insurance funds. As one of the core diseases of disease diagnosis grouping, the hospitalization cost composition and grouping research of patients with cerebral ischemic disease can help to determine scientific payment standards and reduce the economic burden of patients. Aim We aimed to understand the cost composition and influencing factors of hospitalized patients with cerebral ischemic diseases and to identify a reasonable cost grouping scheme. Methods The data come from the homepage of medical records of inpatients with cerebral ischemia in a tertiary hospital in Sichuan Province from 2018 to 2020. After cleaning the data, a total of 5,204 pieces of data were obtained. Nonparametric tests and gamma regression models were used to explore the influencing factors of hospitalization costs. Taking the influencing factors as the predictor variables and the hospitalization cost as the target variable, the exhaustive Chi-squared automatic interaction detector (E-CHAID) algorithm was used to form the costs grouping, and the payment standard of the hospitalization cost for each group was determined. The rationality of cost grouping was evaluated by coefficient of variation (CV) and Kruskal–Wallis H test. Results From 2018 to 2020, the average hospital stay of 5,204 inpatients with cerebral ischemic disease was 10.70 days, and the average hospitalization cost was 17,206.09 RMB yuan. Among the hospitalization costs, diagnosis costs and drug costs accounted for the highest proportion, accounting for 41.18% and 22.38%, respectively, in 2020. Gender, age, admission route, comorbidities and complications, super length of stay (>30 days), and discharge mode had significant effects on hospitalization costs (P < 0.05). Patients were divided into 10 cost groups, and the grouping nodes included comorbidities and complications, discharge mode, age, gender, and admission route. The CV of 9 of the 10 cost groups is less than or equal to 1. The Kruskal–Wallis H test showed that the difference between groups was statistically significant (P < 0.05). Conclusion The cost grouping of patients with cerebral ischemic diseases based on the E-CHAID algorithm is reasonable. This study examined the effects of super length of stay (>30 days), comorbidities and complications, and age on hospitalization cost in patients with cerebral ischemic disease. This study can provide a theoretical basis for advancing the China Healthcare Security Diagnosis Related Groups (CHS-DRG) grouping program and medical expense payment, thereby reducing the disease burden of patients.

Data-Driven Food Desert Metric to Understand Access to Grocery Stores Using Chi-Square Automatic Interaction Detector Decision Tree Analysis

A food desert is a geographic area lacking spatial and socioeconomic access to healthy foods. Disparities in food access and availability hinder public health and individual wellbeing. Access to healthy food has been evaluated by many agencies and researches yet they do not comparably demarcate food deserts or identify vulnerable populations in methodical terms. Existing literature suggests a link between food deserts, income level, and vehicle ownership. This study evaluates the existing methods and proposes a novel data-driven method to identify food deserts in Baltimore, Maryland. This study evaluates responses from 573 respondents for an in-depth analysis of individual grocery store choice and travel decisions. Chi-square automatic interaction detector (CHAID) decision trees are used to develop a user-generated food desert metric. Income level is found to be a key indicator for food desert demarcation, more than vehicle ownership. Network distance was applied to develop the prioritization matrix for a food desert. This research provides a replicable method for determining food-insecure areas in a locality by aggregating individual data to identify such areas. Such a metric can aid policymakers to make investment decisions and to direct resources to areas of need.

Clinical Prediction Rule for Identifying the Stroke Patients who will Obtain Clinically Important Improvement of Upper Limb Motor Function by Robot-Assisted Upper Limb

BackgroundThe number of studies on the characteristics of patients with stroke who would benefit from robot-assisted upper limb rehabilitation is limited, and there are no clear criteria for determining which individuals should receive such treatment. The current study aimed to develop a clinical prediction rule using machine learning to identify the characteristics of patients with stroke who can the achieve minimal clinically important difference of the Fugl-Meyer Upper Extremity Evaluation (FMA-UE) after single-joint hybrid assistive limb (HAL-SJ) rehabilitation. MethodsThis study included 71 patients with subacute stroke who received HAL-SJ rehabilitation. The chi-square automatic interaction detector (CHAID) model was applied to predict improvement in upper limb motor function. Based the analysis using CHAID, age, sex, days from stroke onset to the initiation of HAL-SJ rehabilitation, and upper limb motor and cognitive functions were used as independent variables. Improvement in upper limb motor function was determined based on the minimal clinically important difference of the FMA-UE, which was used as a dependent variable. ResultsAccording to the CHAID model, the FMA-UE score during the initiation of HAL-SJ rehabilitation was the most significant predictive factor for patients who are likely to respond to the intervention. Interestingly, this therapy was more effective in patients with moderate upper limb motor dysfunction and early initiation of HAL-SJ rehabilitation. The accuracy of the CHAID model was 0.89 (95% confidence interval: 0.81–0.96). ConclusionWe developed a clinical prediction rule for identifying the characteristics of patients with stroke whose upper limb motor function can improve with HAL-SJ rehabilitation.

Subjective assessment underestimates surgical risk: On the potential benefits of cardiopulmonary exercise testing for open thoracoabdominal repair.

BackgroundInitial clinical evaluation (ICE) is traditionally considered a useful screening tool to identify frail patients during the preoperative assessment. However, emerging evidence supports the more objective assessment of cardiorespiratory fitness (CRF) via cardiopulmonary exercise testing (CPET) to improve surgical risk stratification. Herein, we compared both subjective and objective assessment approaches to highlight the interpretive idiosyncrasies.MethodsAs part of routine preoperative patient contact, patients scheduled for major surgery were prospectively “eyeballed” (ICE) by two experienced clinicians before more detailed history taking that also included the American Society of Anesthesiologists score classification. Each patient was subjectively judged to be either “frail” or “not frail” by ICE and “fit” or “unfit” from a thorough review of the medical notes. Subjective data were compared against the more objective validated assessment of postoperative outcomes using established CPET “cut‐off” metrics incorporating peak pulmonary oxygen uptake, V̇O2PEAK at the anaerobic threshold (V̇O2‐AT), and ventilatory equivalent for carbon dioxide that collectively informed risk stratification. These data were retrospectively extracted from a single‐center prospective National Health Service database. Data were analyzed using the Chi‐square automatic interaction detection decision tree method.ResultsA total of 127 patients were examined that comprised 58% male and 42% female patients aged 69 ± 10 years with a body mass index of 29 ± 7 kg/m2. Patients were poorly conditioned with a V̇O2PEAK almost 20% lower than predicted for age, sex‐matched healthy controls with 35% exhibiting a V̇O2‐AT < 11 ml/kg/min. Disagreement existed between the subjective assessments of risk with ∼34% of patients classified as not frail on ICE were considered unfit by notes review (p < .0001). Furthermore, ∼35% of patients considered not frail on ICE and ∼31% of patients considered fit by notes review exhibited a V̇O2‐AT < 11 ml/kg/min, and of these, ∼28% and ∼19% were classified as intermediate to high risk.ConclusionsThese findings highlight the interpretive limitations associated with the subjective assessment of patient frailty with surgical risk classification underestimated in up to a third of patients compared to the validated assessment of CRF. They reinforce the benefits of a more objective and integrated approach offered by CPET that may help us to improve perioperative risk assessment and better direct critical care provision in patients scheduled for “high‐stakes” surgery including open thoracoabdominal aortic aneurysm repair.

The Prediction Algorithm and Characteristics Analysis of Kuroshio Sea Surface Temperature Anomalies

Based on 130 climate signal indexes provided by National Climate Center of China, this paper established a decision tree diagnostic prediction model for Spring Kuroshio Sea Surface Temperature (SST) from 1961 to 2015 (65 years) by using Chi-Squared Automatic Interaction Detector (CHAID) algorithm in data mining and obtained five rule sets to determine whether Spring Kuroshio SST is high or not. Considering the data of the 44 years from 1961 to 2004 as the training set of the model and the other years as the test set, the training accuracy of the model can reach to 95.45% and the test accuracy can reach to 81.82%. Three types of Spring Kuroshio SST are different in intensity and distribution. The results show that the prediction model of Spring Kuroshio SST based on CHAID algorithm has a high prediction accuracy, with the reasonable and effective model and the well-thought-out decision rules. Moreover, based on the results of decision classification, the SST anomalies correspond to different distribution characteristics of summer daily precipitation anomalies in eastern China, which can provide a new idea and method for climate prediction of regional summer precipitation.

Early Detection of Inflammation-Prone STEMI Patients Using the CRP Troponin Test (CTT).

Elevated concentrations of C-reactive protein (CRP) early during an acute coronary syndrome (ACS) may reflect the magnitude of the inflammatory response to myocardial damage and are associated with worse outcome. However, the routine measurement of both CRP and cardiac troponin simultaneously in the setting of ST-segment myocardial infarction (STEMI) is not used broadly. Here, we sought to identify and characterize individuals who are prone to an elevated inflammatory response following STEMI by using a combined CRP and troponin test (CTT) and determine their short- and long-term outcome. We retrospectively examined 1186 patients with the diagnosis of acute STEMI, who had at least two successive measurements of combined CRP and cardiac troponin (up to 6 h apart), all within the first 48 h of admission. We used Chi-Square Automatic Interaction Detector (CHAID) tree analysis to determine which parameters, timing (baseline vs. serial measurements), and cut-offs should be used to predict mortality. Patients with high CRP concentrations (above 90th percentile, >33 mg/L) had higher 30 day and all-cause mortality rates compared to the rest of the cohort, regardless of their troponin test status (above or below 118,000 ng/L); 14.4% vs. 2.7%, p < 0.01. Furthermore, patients with both high CRP and high troponin levels on their second measurement had the highest 30-day mortality rates compared to the rest of the cohort; 21.4% vs. 3.7%, p < 0.01. These patients also had the highest all-cause mortality rates after a median follow-up of 4.5 years compared to the rest of the cohort; 42.9% vs. 12.7%, p < 0.01. In conclusion, serial measurements of both CRP and cardiac troponin might detect patients at increased risk for short-and long-term mortality following STEMI. We suggest the future use of the combined CTT as a potential early marker for inflammatory-prone patients with worse outcomes following ACS. This sub-type of patients might benefit from early anti-inflammatory therapy such as colchicine and anti-interleukin-1ß agents.

A Trait-Based Consumer Segmentation for Food Waste Reduction Campaigns

Background: While there is still hunger in the world, a significant amount of food is wasted, which harms the environment. This study focuses on food waste at the consumer level and investigates the role of personality traits on food-waste-aversion. Focus of the Article: Segmentation with personality traits for food waste reduction campaigns. Research Question: Is there a link between personality traits and food-waste-aversion? Are there any associations among consumers’ levels of food-waste-aversion, frugality, conscientiousness, and religiosity? Importance to the Social Marketing Field: Segmentation is a neglected marketing tool in designing campaigns against food waste. This study identifies possible market segments of social marketing campaigns against food waste. In addition, associations among food-waste-aversion and personality traits of conscientiousness, frugality, and religiosity are shown in this study. Methods: This study adopts a cross-sectional research design. A convenience sample of 301 consumers in Turkey is surveyed via an online questionnaire. Results: Results of Chi-Square Automatic Interaction Detector (CHAID) analysis indicate five distinct consumer segments, namely frugal believers, frugal seculars, conscientious individuals, casual females, and casual males. Moreover, positive associations ( p &lt; 0.001) among food-waste-aversion and personality traits of conscientiousness, frugality, and religiosity are shown. Recommendations for Research or Practice: This study provides a segmentation procedure with the trait perspective. Frugality, conscientiousness, and religiosity traits can play an essential role in food waste reduction. Targeting individuals with communications fit with their personality is likely to increase the success of food waste reduction interventions. Limitations: Due to a lack of behavioral data, this study investigates food waste at the attitudinal level. Further study could use behavioral measures. In addition, the majority of participants in the survey are Muslim. In order to validate research findings across different cultures, it should be carried out in other countries.

Prediction of the live weight at breeding age from morphological measurements taken at weaning in indigenous Honamli kids using data mining algorithms

The purpose of this study was to predict live weight at breeding age (LW) based on weaning morphological traits, which birth weight (BW), weaning weight (WW), withers height (WH), back height (BH), rump height (RH), chest depth (CD), body length (BL), tail length (TL), chest girth (CG), leg girth (LG), front shark circumference (FSC), head length (HL), head width (HW), nose length (NL), ear length (EL), and ear width (EW). For this purpose, measurements were taken from 84 Honamli kids born in 2018. The study also included sex, birth type (BT), and ear type as the nominal predictors. For this purpose, two MARS (Multivariate Adaptive Regression Splines), which are interaction (MARS2) and non-interaction (MARS1), and based-tree algorithms, such as CART (Classification and Regression Tree), CHAID (Chi-Square Automatic Interaction Detector), and Exhaustive CHAID, were used by cross-validation 5 and compared with each other considering the predictive performance by taking into account nine predictive performances criteria. LW has a significantly positive and high linear relationship with WH (0.770), BH (0.770), RH (0.750), BL (0.750), and CG (0.770), respectively (p < 0.01). According to these criteria, second-order interaction MARS2 model had the best performance among all data mining algorithms. Also, the CHAID algorithm was the best predictor of LW among regression tree-based algorithms. The CHAID algorithm predicted that the Honamli goat with 14.426 < WW < 15.575kg and HW > 16.464cm had the heaviest LW at 56.268kg. The MARS2 model showed that the heaviest LW could be produced by WW > 16.10kg, HW > 17cm, Sex-Male × BL > 60cm, WW × BL < 50cm, BT-twin × WW < 15.60kg, BL > 50cm × CG > 62.4cm and male goats. Also, CHAID and MARS2 algorithms explain 92.00% and 94.50% of the variation in LW, respectively. According to the results, it can be concluded that the CHAID and MARS algorithms used in the prediction of LW at breeding age could give an idea to reveal the breed standards examined for breeding purposes. While determining that there are important statistical methods in defining body characteristics at weaning in a complex way, the body characteristics determined by these models can be used as indirect selection criteria.

Developing Machine Learning Algorithms to Support Patient-centered, Value-based Carpal Tunnel Decompression Surgery.

Background:Carpal tunnel syndrome (CTS) is extremely common and typically treated with carpal tunnel decompression (CTD). Although generally an effective treatment, up to 25% of patients do not experience meaningful benefit. Given the prevalence, this amounts to considerable morbidity and cost without return. Being able to reliably predict which patients would benefit from CTD preoperatively would support more patient-centered and value-based care.Methods:We used registry data from 1916 consecutive patients undergoing CTD for CTS at a regional hand center between 2010 and 2019. Improvement was defined as change exceeding the respective QuickDASH subscale’s minimal important change estimate. Predictors included a range of clinical, demographic and patient-reported variables. Data were split into training (75%) and test (25%) sets. A range of machine learning algorithms was developed using the training data and evaluated with the test data. We also used a machine learning technique called chi-squared automatic interaction detection to develop flowcharts that could help clinicians and patients to understand the chances of a patient improving with surgery.Results:The top performing models predicted functional and symptomatic improvement with accuracies of 0.718 (95% confidence interval 0.660, 0.771) and 0.759 (95% confidence interval 0.708, 0.810), respectively. The chi-squared automatic interaction detection flowcharts could provide valuable clinical insights from as little as two preoperative questions.Conclusions:Patient-reported outcome measures and machine learning can support patient-centered and value-based healthcare. Our algorithms can be used for expectation management and to rationalize treatment risks and costs associated with CTD.

Effect of match-related contextual factors on positional performance in the national rugby league

Objectives To examine the effects of match-related contextual variables on positional groups and success in the National Rugby League (NRL). Methods Data relating to match location, match outcome, quality of opposition and match type (absolute score differential) from all matches across the 2015–2019 NRL seasons were collected, in addition to 14 previously identified Factors (technical performance indicators). A decision tree, grown using the Exhaustive Chi-square Automatic Interaction Detector (CHAID) algorithm, was used to model the effect of each of these match-related contexts on positional contribution according to match outcome. Results The accuracy of the exhaustive CHAID model in explaining the influence of positional groups on match outcome was 66%. The model revealed four primary splits: interchange forwards, utility backs, adjustables and a group containing the remaining three positional groups (forwards, backs, and interchange). Conclusions Results suggest that interchange forwards, utility backs and adjustables could have a definitive role within the team compared to the remaining positional groups in determining match outcome. In contrast to team-level research, there is a greater emphasis on the importance of defensive actions (e.g. try causes, tackles made) at a positional level than attacking performance indicators. The moderate classification accuracy justifies the use of this approach for examination of the interactions between match-related contextual variables, performance indicators and positional groups.

Food security and agricultural challenges in West-African rural communities: a machine learning analysis

ABSTRACT This article investigated household-level food security for Ghana, Liberia, and Senegal. Different agroclimatic, ecological, social, and farming conditions in West Africa were represented. Using data-driven Random Forest and Chi-Square Automatic Interaction Detection (CHAID) decision tree methodology, this study classified 644 Ghanaian, 323 Liberian, and 510 Senegalese households for comparison and interpretation on food security. The predictors growing Liberian and Senegalese decision trees imply community support, diverse selling channels outside villages, resolving the dispute over farmland, and increasing community-level investment for food availability and access demonstrate household food security. Predictor importance on food security for Ghana highlighted the role of independent producers and food suppliers toward stability. Household food security or insecurity was distinguished by location-specific and gender-led households in Liberia and Senegal. Practically, the results presented a need to step-up agricultural education and extension based on an empirical field survey and its interpretations. The results can add considerations to the role of farming households as independent and individual suppliers and consumers to long-standing dimensions of food security, i.e., food availability, access, and stability.