Interpretable Machine Learning Models Research Articles

Interpretable machine learning framework to predict gout associated with dietary fiber and triglyceride-glucose index

BackgroundGout prediction is essential for the development of individualized prevention and treatment plans. Our objective was to develop an efficient and interpretable machine learning (ML) model using the SHapley Additive exPlanation (SHAP) to link dietary fiber and triglyceride-glucose (TyG) index to predict gout.MethodsUsing datasets from the National Health and Nutrition Examination Survey (NHANES) (2005–2018) population to study dietary fiber, the TyG index was used to predict gout. After evaluating the performance of six ML models and selecting the Light Gradient Boosting Machine (LGBM) as the optimal algorithm, we interpret the LGBM model for predicting gout using SHAP and reveal the decision-making process of the model.ResultsAn initial survey of 70,190 participants was conducted, and after a gradual exclusion process, 12,645 cases were finally included in the study. Selection of the best performing LGBM model for prediction of gout associated with dietary fiber and TyG index (Area under the ROC curve (AUC): 0.823, 95% confidence interval (CI): 0.798–0.848, Accuracy: 95.3%, Brier score: 0.077). The feature importance of SHAP values indicated that age was the most important feature affecting the model output, followed by uric acid (UA). The SHAP values showed that lower dietary fiber values had a more pronounced effect on the positive prediction of the model, while higher values of the TyG index had a more pronounced effect on the positive prediction of the model.ConclusionThe interpretable LGBM model associated with dietary fiber and TyG index showed high accuracy, efficiency, and robustness in predicting gout. Increasing dietary fiber intake and lowering the TyG index are beneficial in reducing the potential risk of gout.

Developing interpretable machine learning model for evaluating young modulus of cemented paste backfill

Cemented paste backfill (CPB), a mixture of wet tailings, binding agent, and water, proves cost-effective and environmentally beneficial. Determining the Young modulus during CPB mix design is crucial. Utilizing machine learning (ML) tools for Young modulus evaluation and prediction streamlines the CPB mix design process. This study employed six ML models, including three shallow models Extreme Gradient Boosting (XGB), Gradient Boosting (GB), Random Forest (RF) and three hybrids Extreme Gradient Boosting-Particle Swarm Optimization (XGB-PSO), Gradient Boosting-Particle Swarm Optimization (GB-PSO), Random Forest-Particle Swarm Optimization (RF-PSO). The XGB-PSO hybrid model exhibited superior performance (coefficient of determination R2 = 0.906, root mean square error RMSE = 19.535 MPa, mean absolute error MAE = 13.741 MPa) on the testing dataset. Shapley Additive Explanation (SHAP) values and Partial Dependence Plots (PDP) provided insights into component influences. Cement/Tailings ratio emerged as the most crucial factor for enhancing Young modulus in CPB. Global interpretation using SHAP values identified six essential input variables: Cement/Tailings, Curing age, Cc, solid content, Fe2O3 content, and SiO2 content.

Robustness and Interpretability of Machine Learning Models in Financial Forecasting

Purpose: The practice of financial forecasting is an essential component of contemporary financial management and the process of making decisions on investments. As a result of the complexity and volatility of financial markets, traditional financial forecasting techniques often fail to adequately capture the situation. Methodology/ Findings: One of the most effective methods for improving the precision and effectiveness of financial forecasting is the use of machine learning techniques. Through an examination of its potential, limitations, and future possibilities. They take linear and nonlinear possibilities into account in their study. Our focus is on linear methods, namely penalized regressions, and ensemble of models. The study considers a range of nonlinear techniques, including tree-based methods like boosted trees and random forests, and deep and shallow neural networks in both feed-forward and recurrent forms. They also think about ensemble and hybrid models, which combine features from several kinds of alternatives. Implications to Theory, Practice and Policy: A brief overview of the tests used to measure outstanding predictive ability is provided. In the last part of this article, they focus on the possible applications of machine learning in the fields of economics and finance, and we provide an example that makes use of high-frequency financial data (Benti, Chaka, and Semie, 2023).

Interpretable machine learning model for shear strength estimation of circular concrete‐filled steel tubes

Interpretable machine learning model for shear strength estimation of circular concrete‐filled steel tubes

Identification of Mitophagy-Associated Genes for the Prediction of Metabolic Dysfunction-Associated Steatohepatitis Based on Interpretable Machine Learning Models.

This study aims to elucidate the role of mitochondrial autophagy in metabolic dysfunction-associated steatohepatitis (MASH) by identifying and validating key mitophagy-related genes and diagnostic models with diagnostic potential. The gene expression profiles and clinical information of MASH patients and healthy controls were obtained from the Gene Expression Omnibus database (GEO). Limma and functional enrichment analysis were used to identify the mitophagy-related differentially expressed genes (mito-DEGs) in MASH patients. Machine learning models were used to select key mito-DEGs and evaluate their efficacy in the early diagnosis of MASH. The expression levels of the key mito-DEGs were validated using datasets and cell models. A nomogram was constructed to assess the risk of MASH progression based on the expression of the key mito-DEGs. The mitophagy-related molecular subtypes of MASH were evaluated. Four mito-DEGs, namely MRAS, RAB7B, RETREG1, and TIGAR were identified. Among the machine learning models employed, the Support Vector Machine demonstrated the highest AUC value of 0.935, while the Light Gradient Boosting model exhibited the highest accuracy (0.9189), kappa (0.7204), and F1-score (0.9508) values. Based on these models, MRAS, RAB7B, and RETREG1 were selected for further analysis. The logistic regression model based on these genes could accurately predict MASH diagnosis. The nomogram model based on these DEGs exhibited excellent prediction performance. The expression levels of the three mito-DEGs were validated in the independent datasets and cell models, and the results were found to be consistent with the findings obtained through bioinformatics analysis. Furthermore, our findings revealed significant differences in gene expression patterns, immune characteristics, biological functions, and enrichment pathways between the mitophagy-related molecular subtypes of MASH. Subtype-specific small-molecule drugs were identified using the CMap database. Our research provides novel insights into the role of mitophagy in MASH and uncovers novel targets for predictive and personalized MASH treatments.

Wearable sensor devices can automatically identify the ON-OFF status of patients with Parkinson's disease through an interpretable machine learning model

Wearable sensor devices can automatically identify the ON-OFF status of patients with Parkinson's disease through an interpretable machine learning model

Creating machine learning models that interpretably link systemic inflammatory index, sex steroid hormones, and dietary antioxidants to identify gout using the SHAP (SHapley Additive exPlanations) method

BackgroundThe relationship between systemic inflammatory index (SII), sex steroid hormones, dietary antioxidants (DA), and gout has not been determined. We aim to develop a reliable and interpretable machine learning (ML) model that links SII, sex steroid hormones, and DA to gout identification.MethodsThe dataset we used to study the relationship between SII, sex steroid hormones, DA, and gout was from the National Health and Nutrition Examination Survey (NHANES). Six ML models were developed to identify gout by SII, sex steroid hormones, and DA. The seven performance discriminative features of each model were summarized, and the eXtreme Gradient Boosting (XGBoost) model with the best overall performance was selected to identify gout. We used the SHapley Additive exPlanation (SHAP) method to explain the XGBoost model and its decision-making process.ResultsAn initial survey of 20,146 participants resulted in 8,550 being included in the study. Selecting the best performing XGBoost model associated with SII, sex steroid hormones, and DA to identify gout (male: AUC: 0.795, 95% CI: 0.746- 0.843, accuracy: 98.7%; female: AUC: 0.822, 95% CI: 0.754- 0.883, accuracy: 99.2%). In the male group, The SHAP values showed that the lower feature values of lutein + zeaxanthin (LZ), vitamin C (VitC), lycopene, zinc, total testosterone (TT), vitamin E (VitE), and vitamin A (VitA), the greater the positive effect on the model output. In the female group, SHAP values showed that lower feature values of E2, zinc, lycopene, LZ, TT, and selenium had a greater positive effect on model output.ConclusionThe interpretable XGBoost model demonstrated accuracy, efficiency, and robustness in identifying associations between SII, sex steroid hormones, DA, and gout in participants. Decreased TT in males and decreased E2 in females may be associated with gout, and increased DA intake and decreased SII may reduce the potential risk of gout.

Estimation aboveground biomass in subtropical bamboo forests based on an interpretable machine learning framework

Forest biomass is an essential indicator of forest ecosystem carbon cycle and global climate change research, and traditional machine learning cannot explain the mechanism of feature variable impact on forest aboveground biomass (AGB). Therefore, we proposed an interpretable bamboo forest AGB prediction method based on Shaply Additive exPlanation (SHAP) and XGBoost model to explain the impact mechanism of feature variables on AGB. The bamboo forest AGB is estimated using the monthly and annual scale leaf area index (LAI), enhanced vegetation index (EVI), ratio vegetation index (RVI), precipitation (Pre), maximum temperature (Tmax), minimum temperature (Tmin) and solar radiation (Rad) data. The results showed that the method could be effectively predict AGB, and precipitation more important than temperature. The framework revealed the threshold effect, exceeded the threshold value, the impacts of LAI_Ann, EVI_Ann, and Pre_11 on AGB were stable. The SHAP interaction value between LAI_Ann and EVI_Ann decreased with increasing EVI_Ann and LAI_Ann. By contrast, when Pre_11 increased, the SHAP interaction value between LAI_Ann and Pre_11 increased with increasing LAI_Ann. The framework could also be easily implemented, providing an interpretable machine learning model of forest AGB.

AKIMLpred: An interpretable machine learning model for predicting acute kidney injury within seven days in critically ill patients based on a prospective cohort study

BackgroundEarly recognition and timely intervention for AKI in critically ill patients were crucial to reduce morbidity and mortality. This study aimed to use biomarkers to construct a optimal machine learning model for early prediction of AKI in critically ill patients within seven days. MethodsThe prospective cohort study enrolled 929 patients altogether who were admitted in ICU including 680 patients in training set (Jiefang Campus) and 249 patients in external testing set (Binjiang Campus). After performing strict inclusion and exclusion criteria, 421 patients were selected in training set for constructing predictive model and 167 patients were selected in external testing for evaluating the predictive performance of resulting model. Urine and blood samples were collected for kidney injury associated biomarkers detection. Baseline clinical information and laboratory data of the study participants were collected. We determined the average prediction efficiency of six machine learning models through 10-fold cross validation. ResultsIn total, 78 variables were collected when admission in ICU and 43 variables were statistically significant between AKI and non-AKI cohort. Then, 35 variables were selected as independent features for AKI by univariate logistic regression. Spearman correlation analysis was used to remove two highly correlated variables. Three ranking methods were used to explore the influence of 33 variables for further determining the best combination of variables. The gini importance ranking method was found to be applicable for variables filtering. The predictive performance of AKIMLpred which constructed by the XGBoost algorithm was the best among six machine learning models. When the AKIMLpred included the nine features (NGAL, IGFBP7, sCysC, CAF22, KIM-1, NT-proBNP, IL-6, IL-18 and L-FABP) with the highest influence ranking, its model had the best prediction performance, with an AUC of 0.881 and an accuracy of 0.815 in training set, similarly, with an AUC of 0.889 and an accuracy of 0.846 in validation set. Moreover, the performace was slightly outperformed in testing set with an AUC of 0.902 and an accuracy of 0.846. The SHAP algorithm was used to interpret the prediction results of AKIMLpred. The web-calculator of AKIMLpred was shown for predicting AKI with more convenient(https://www.xsmartanalysis.com/model/list/predict/model/html?mid=8065&symbol=11gk693982SU6AE1ms21). AKIMLpred was better than the optimal model built with only routine tests for predicting AKI in critically ill patients within 7 days. ConclusionThe model AKIMLpred constructed by the XGBoost algorithm with selecting the nine most influential biomarkers in the gini importance ranking method had the best performance in predicting AKI in critically ill patients within 7 days. This data-driven predictive model will help clinicians to make quick and accurate diagnosis.

Development of interpretable machine learning models for prediction of acute kidney injury after noncardiac surgery: a retrospective cohort study.

Early identification of patients at high-risk of postoperative acute kidney injury (AKI) can facilitate the development of preventive approaches. This study aimed to develop prediction models for postoperative AKI in noncardiac surgery using machine learning algorithms. The authors also evaluated the predictive performance of models that included only preoperative variables or only important predictors. Adult patients undergoing noncardiac surgery were retrospectively included in the study (76457 patients in the discovery cohort and 11910 patients in the validation cohort). AKI was determined using the KDIGO criteria. The prediction model was developed using 87 variables (56 preoperative variables and 31 intraoperative variables). A variety of machine learning algorithms were employed to develop the model, including logistic regression, random forest, extreme gradient boosting, and gradient boosting decision trees. The performance of different models was compared using the area under the receiver operating characteristic curve (AUROC). Shapley Additive Explanations (SHAP) analysis was employed for model interpretation. The patients in the discovery cohort had a median age of 52 years (IQR: 42-61 years), and 1179 patients (1.5%) developed AKI after surgery. The gradient boosting decision trees algorithm showed the best predictive performance using all available variables, or only preoperative variables. The AUROCs were 0.849 (95% CI: 0.835-0.863) and 0.828 (95% CI: 0.813-0.843), respectively. The SHAP analysis showed that age, surgical duration, preoperative serum creatinine, and gamma-glutamyltransferase, as well as American Society of Anesthesiologists physical status III were the most important five features. When gradually reducing the features, the AUROCs decreased from 0.852 (including the top 40 features) to 0.839 (including the top 10 features). In the validation cohort, the authors observed a similar pattern regarding the models' predictive performance. The machine learning models the authors developed had satisfactory predictive performance for identifying high-risk postoperative AKI patients. Furthermore, the authors found that model performance was only slightly affected when only preoperative variables or only the most important predictive features were included.

Innovative framework for accurate and transparent forecasting of energy consumption: A fusion of feature selection and interpretable machine learning

The study presents a novel framework integrating feature selection (FS) and machine learning (ML) techniques to forecast inland national energy consumption (EC) in the United Kingdom across all energy sources. This innovative framework strategically combines three FS approaches with five interpretable ML models using Shapley Additive Explanations (SHAP), with the dual goal of enhancing accuracy and transparency in EC predictions. By meticulously selecting the most pertinent features from diverse features—including meteorological conditions, socioeconomic parameters, and historical consumption patterns of different primary fuels—the proposed framework enhances the robustness of the forecasting model. This is achieved through benchmarking three FS approaches: ensemble filter, wrapper, and a hybrid ensemble filter-wrapper. In addition, we introduce a novel ensemble filter FS, synthesizing outcomes from multiple base FS methods to make well-informed decisions about feature retention. Experimental results underscore the efficacy of integrating both wrapper and ensemble filter-wrapper FS approaches with interpretable ML models, ensuring the forecasting process remains comprehensible and interpretable while utilizing a manageable number of features (four to eight). In addition, experimental results indicate that different feature subsets are usually selected for each combined FS approach and ML model. This study not only demonstrates the framework's capability to provide accurate forecasts but also establishes it as a valuable tool for policymakers and energy analysts.

A Review on the Impact of Data Representation on Model Explainability

In recent years, advanced machine learning and artificial intelligence techniques have gained popularity due to their ability to solve problems across various domains with high performance and quality. However, these techniques are often so complex that they fail to provide simple and understandable explanations for the outputs they generate. To address this issue, the field of explainable artificial intelligence has recently emerged. On the other hand, most data generated in different domains are inherently structural; that is, they consist of parts and relationships among them. Such data can be represented using either a simple data-structure or form , such as a vector , or a complex data-structure, such as a graph . The effect of this representation form on the explainability and interpretability of machine learning models is not extensively discussed in the literature. In this survey paper, we review efficient algorithms proposed for learning from inherently structured data, emphasizing how their representation form affects the explainability of learning models. A conclusion of our literature review is that using complex forms or data-structures for data representation improves not only the learning performance, but also the explainability and transparency of the model.

Achieving Regulatory Compliance in Cloud Computing through ML

In today's dynamic cloud computing landscape, achieving regulatory compliance presents significant challenges for organizations due to evolving security threats and complex legal requirements. This research paper explores the role of machine learning (ML) in enhancing regulatory compliance within cloud environments. The study reviews current regulatory frameworks, compliance challenges, and the impact of non-compliance on organizations. By analysing real-world case studies, including Microsoft Azure Sentinel and Google Cloud's Data Loss Prevention (DLP) API, this paper demonstrates how ML technologies can automate compliance tasks, enhance security, and improve reporting accuracy. Key benefits of ML integration include efficiency gains, cost reductions, enhanced security, and improved auditability. Furthermore, emerging trends in ML techniques, such as deep learning and federated learning, are discussed along with actionable recommendations for successful ML implementation in cloud compliance strategies. The findings emphasize the importance of investing in data governance, continuous monitoring, and interpretability of ML models to ensure ethical and effective compliance management. Overall, this research sheds light on the transformative potential of ML in optimizing regulatory compliance practices and outlines future directions for leveraging advanced technologies to address evolving compliance challenges.

Interpretable machine learning models for failure cause prediction in imbalanced oil pipeline data

Pipelines are critical arteries in the oil and gas industry and require massive capital investment to safely construct networks that transport hydrocarbons across diverse environments. However, these pipeline systems are prone to integrity failure, which results in significant economic losses and environmental damage. Accurate prediction of pipeline failure events using historical oil pipeline accident data enables asset managers to plan sufficient maintenance, rehabilitation, and repair activities to prevent catastrophic failures. However, learning the complex interdependencies between pipeline attributes and rare failure events presents several analytical challenges. This study proposes a novel machine learning (ML) framework to accurately predict pipeline failure causes on highly class-imbalanced data compiled by the United States Pipeline and Hazardous Materials Safety Administration. Natural language processing techniques were leveraged to extract informative features from unstructured text data. Furthermore, class imbalance in the dataset was addressed via oversampling and intrinsic cost-sensitive learning (CSL) strategies adapted for the multi-class case. Nine machine and deep learning architectures were benchmarked, with LightGBM demonstrating superior performance. The integration of CSL yielded an 86% F1 score and a 0.82 Cohen kappa score, significantly advancing prior research. This study leveraged a comprehensive Shapley Additive explanation analysis to interpret the predictions from the LightGBM algorithm, revealing the key factors driving failure probabilities. Leveraging sentiment analysis allowed the models to capture a richer, more multifaceted representation of the textual data. This study developed a novel CSL approach that integrates domain knowledge regarding the varying cost impacts of misclassifying different failure types into ML models. This research demonstrated an effective fusion of text insights from inspection reports with structured pipeline data that enhances model interpretability. The resulting AI modeling framework generated data-driven predictions of the causes of failure that could enable transportation agencies with actionable insights. These insights enable tailored preventative maintenance decisions to proactively mitigate emerging pipeline failures.

Prioritizing user requirements for digital products using explainable artificial intelligence: A data-driven analysis on video conferencing apps

The advent of Industry 5.0 has brought a wealth of digital information to mobile app stores. With the help of emerging technologies such as machine learning and explainable artificial intelligence (XAI), these large amounts of user-generated data can be efficiently captured and analyzed. In this study, we propose an app store analysis framework and demonstrate the utility of the framework by mining and prioritizing user requirements in three popular video conferencing apps. We used the Sentistrength sentiment analysis tool, structural topic modeling, the Gephi web analysis tool, machine learning, and XAI techniques to conduct an in-depth analysis of user requirements in Microsoft Teams, ZOOM Cloud Meetings, and Google Meet. The findings indicated that Steal data, Audio and video quality, Customer service, Hacker issues, Meeting and account passwords, Mute and unmute, Features, and Office platform were the web conferencing system's key areas for improvement. The study demonstrated the usability of app store analysis frameworks and the great potential of XAI to provide insights about requirements prioritization by interpreting machine learning models. Additionally, it offered valuable suggestions for app developers on using the massive data in app stores to improve their apps.

Machine-learning analysis reveals an important role for negative selection in shaping cancer aneuploidy landscapes

BackgroundAneuploidy, an abnormal number of chromosomes within a cell, is a hallmark of cancer. Patterns of aneuploidy differ across cancers, yet are similar in cancers affecting closely related tissues. The selection pressures underlying aneuploidy patterns are not fully understood, hindering our understanding of cancer development and progression.ResultsHere, we apply interpretable machine learning methods to study tissue-selective aneuploidy patterns. We define 20 types of features corresponding to genomic attributes of chromosome-arms, normal tissues, primary tumors, and cancer cell lines (CCLs), and use them to model gains and losses of chromosome arms in 24 cancer types. To reveal the factors that shape the tissue-specific cancer aneuploidy landscapes, we interpret the machine learning models by estimating the relative contribution of each feature to the models. While confirming known drivers of positive selection, our quantitative analysis highlights the importance of negative selection for shaping aneuploidy landscapes. This is exemplified by tumor suppressor gene density being a better predictor of gain patterns than oncogene density, and vice versa for loss patterns. We also identify the importance of tissue-selective features and demonstrate them experimentally, revealing KLF5 as an important driver for chr13q gain in colon cancer. Further supporting an important role for negative selection in shaping the aneuploidy landscapes, we find compensation by paralogs to be among the top predictors of chromosome arm loss prevalence and demonstrate this relationship for one paralog interaction. Similar factors shape aneuploidy patterns in human CCLs, demonstrating their relevance for aneuploidy research.ConclusionsOur quantitative, interpretable machine learning models improve the understanding of the genomic properties that shape cancer aneuploidy landscapes.

Explainable and visualizable machine learning models to predict biochemical recurrence of prostate cancer.

Machine learning (ML) models presented an excellent performance in the prognosis prediction. However, the black box characteristic of ML models limited the clinical applications. Here, we aimed to establish explainable and visualizable ML models to predict biochemical recurrence (BCR) of prostate cancer (PCa). A total of 647 PCa patients were retrospectively evaluated. Clinical parameters were identified using LASSO regression. Then, cohort was split into training and validation datasets with a ratio of 0.75:0.25 andBCR-related features were included in Cox regression and five ML algorithm to construct BCR prediction models. The clinical utility of each model wasevaluated by concordance index (C-index) values and decision curve analyses (DCA). Besides, Shapley Additive Explanation (SHAP) values were used to explain the features in the models. We identified 11 BCR-related features using LASSO regression, then establishing five ML-based models, including random survival forest (RSF), survival support vector machine (SSVM), survival Tree (sTree), gradient boosting decision tree (GBDT), extreme gradient boosting (XGBoost), and a Cox regression model, C-index were 0.846 (95%CI 0.796-0.894), 0.774 (95%CI 0.712-0.834), 0.757 (95%CI 0.694-0.818), 0.820 (95%CI 0.765-0.869), 0.793 (95%CI 0.735-0.852), and 0.807 (95%CI 0.753-0.858), respectively. The DCA showed that RSF model had significant advantages over all models. In interpretability of ML models, the SHAP value demonstrated the tangible contribution of each feature in RSF model. Our score system provide reference for the identification for BCR, and the crafting of a framework for making therapeutic decisions for PCa on a personalized basis.

Hydrologic interpretation of machine learning models for 10-daily streamflow simulation in climate sensitive upper Indus catchments

Hydrologic interpretation of machine learning models for 10-daily streamflow simulation in climate sensitive upper Indus catchments

Pseudo datasets explain artificial neural networks

AbstractMachine learning enhances predictive ability in various research compared to conventional statistical approaches. However, the advantage of the regression model is that it can effortlessly interpret the effect of each predictor. Therefore, interpretable machine-learning models are desirable as the deep-learning technique advances. Although many studies have proposed ways to explain neural networks, this research suggests an intuitive and feasible algorithm to interpret any set of input features of artificial neural networks at the population-mean level changes. The new algorithm provides a novel concept of generating pseudo datasets and evaluating the impact due to changes in the input features. Our approach can accurately obtain the effect estimate from single to multiple input neurons and depict the association between the predictive and outcome variables. According to computer simulation studies, the explanatory effects of the predictors derived by the neural network as a particular case could approximate the general linear model estimates. Besides, we applied the new method to three real-life analyzes. The results demonstrated that the new algorithm could obtain similar effect estimates from the neural networks and regression models. Besides, it yields better predictive errors than the conventional regression models. Again, it is worth noting that the new pipeline is much less computationally intensive than the SHapley Additive exPlanations (SHAP), which could not simultaneously measure the impact due to two or more inputs while adjusting for other features.

Drivers of natural gas use in U.S. residential buildings.

Natural gas is the primary fuel used in U.S. residences, yet little is known about its consumption patterns and drivers. We use daily county-level gas consumption data to assess the spatial patterns of the relationships and the sensitivities of gas consumption to outdoor air temperature across U.S. households. We fitted linear-plus-plateau functions to daily gas consumption data in 1000 counties, and derived two key coefficients: the heating temperature threshold (Tcrit) and the gas consumption rate change per 1°C temperature drop (Slope). We identified the main predictors of Tcrit and Slope (like income, employment rate, and building type) using interpretable machine learning models built on census data. Finally, we estimated a potential 2.47 million MtCO2 annual emission reduction in U.S. residences by gas savings due to household insulation improvements and hypothetical behavioral change toward reduced consumption by adopting a 1°C lower Tcrit than the current value.