Interpretation Methods Research Articles

How reliable is the distinction between thoracolumbar AO type A3 and A4 fractures? A systematic literature review.

The AOSpine classification divides thoracolumbar burst fractures into A3 and A4 fractures; nevertheless, past research has found inconsistent interobserver reliability in detecting those two fracture patterns. This systematic analysis aims to synthesize data on the reliability of discriminating between A3 and A4 fractures. We searched PubMed, Scopus, and the Web of Science for studies reporting the inter- and intra-observer reliability of detecting thoracolumbar AO A3 and A4 fractures using computed tomography (CT). The search spanned 2013 to 2023 and included both primarily reliability and observational comparative studies. We followed the PRISMA guidelines and used the modified COSMIN checklist to assess the studies' quality. Kappa coefficient (k) values were categorized according to Landis and Koch, from slight to excellent. Of the 396 identified studies, nine met the eligibilitycriteria; all were primarily reliability studies except one observational study. Interobserver k values for A3/A4 fracturesvaried widely among studies (0.19-86). The interobserver reliability was poor in two studies, fair in one study, moderate in four studies, and excellent in two studies. Only two studies reported intra-observer reliability, showing fair and excellent agreement. The included studies revealed significant heterogeneity in study design, sample size, and interpretation methods. Considerable variability exists in interobserver reliability for distinguishing A3 and A4 fractures from slight to excellent agreement. This variability might be attributed to methodological heterogeneity among studies, limitations of reliability analysis, or diagnostic pitfalls in differentiating between A3 and A4. Most observational studies comparing the outcome of A3 and A4 fractures do not report interobserver agreement, and this should be considered when interpreting their results.

Kompetensi Auditor Sebagai Faktor Pendukung Audit Investigasi

Fraud detection is urgent for many companies or agencies. Cases of fraud and irregularities are increasingly rampant in Indonesia. Cases of corruption, misappropriation of assets, abuse of authority, and fraudulent financial statements often occur in various government agencies and companies. This study aims to determine auditor competence as a supporter of investigative audits. An interpretive qualitative method with a phenomenological approach was used in this study. Data collection techniques were carried out through interviews and observation. Data analysis was carried out by compiling questions, recording interview results, and analyzing and organizing them. The results showed that auditor competence has an influence on investigative audits. Qualified forensic analysis skills, interview skills to obtain information, and critical thinking to solve every problem in the field. Auditor competence in terms of understanding and knowledge related to regulations and laws is very important because it is the basis or guideline for conducting investigative audits. Because auditor competence is an important factor in supporting investigative audits, competency development is very necessary. Training, seminars, or continuing education can be a form of development that can be implemented by auditors. Qualified competence will improve the quality of the audit.

Moss-m7G: A Motif-Based Interpretable Deep Learning Method for RNA N7-Methlguanosine Site Prediction.

N-7methylguanosine (m7G) modification plays a crucial role in various biological processes and is closely associated with the development and progression of many cancers. Accurate identification of m7G modification sites is essential for understanding their regulatory mechanisms and advancing cancer therapy. Previous studies often suffered from insufficient research data, underutilization of motif information, and lack of interpretability. In this work, we designed a novel motif-based interpretable method for m7G modification site prediction, called Moss-m7G. This approach enables the analysis of RNA sequences from a motif-centric perspective. Our proposed word-detection module and motif-embedding module within Moss-m7G extract motif information from sequences, transforming the raw sequences from base-level into motif-level and generating embeddings for these motif sequences. Compared with base sequences, motif sequences contain richer contextual information, which is further analyzed and integrated through the Transformer model. We constructed a comprehensive m7G data set to implement the training and testing process to address the data insufficiency noted in prior research. Our experimental results affirm the effectiveness and superiority of Moss-m7G in predicting m7G modification sites. Moreover, the introduction of the word-detection module enhances the interpretability of the model, providing insights into the predictive mechanisms.

Determination of the role and factors of technopolis development in the economic security of the depressed regions

Purpose: is to develop the integrated approach to assessing and determining the role and factors of technopolis development in the context of improving economic security of the depressed region.Methods: to analyze the current state of technopolis development in the Russian Federation, the comprehensive multi-component methodological approach was developed, including qualitative and quantitative analysis, as well as statistical methods of data interpretation. This approach was applied to assess the technopolis development of 14 science cities in Russia, the results of which were presented in the form of the composite index heat map. The source of initial data is Rosstat.Results:the study analyzed the evolution of the technopolis concept from the late 19th century to the present. This made it possible to identify the key factors influencing the transformation of scientific and innovation ecosystems. In particular, it was found that modern technopolises in Russia are often the result of renaming or transformation of existing science cities. In the context of economic security of the depressed regions, the factors influencing technopolis development were analyzed. Special attention was paid to the science city of Biysk, located in the largest depressive region of the country – Altai Krai.Conclusions and Relevance: the study showed that technopolises can act as catalysts of economic revival of the depressed regions. However, it also revealed the risks of creating socio-economic imbalances, which indicates the need for a differentiated approach when implementing technopolis projects in the such regions. The results of the study can be used to develop strategies for the management and development of technopolises, as well as to improve the economic security of the depressed regions. The main directions of further research may include analyzing the relationship between technopolis development and economic security, as well as the development of specific management and financing mechanisms.

Development and validation of 10-year risk prediction models of cardiovascular disease in Chinese type 2 diabetes mellitus patients in primary care using interpretable machine learning-based methods.

To develop 10-year cardiovascular disease (CVD) risk prediction models in Chinese patients with type 2 diabetes mellitus (T2DM) managed in primary care using machine learning (ML) methods. In this 10-year population-based retrospective cohort study, 141 516 Chinese T2DM patients aged 18 years or above, without history of CVD or end-stage renal disease and managed in public primary care clinics in 2008, were included and followed up until December 2017. Two-thirds of the patients were randomly selected to develop sex-specific CVD risk prediction models. The remaining one-third of patients were used as the validation sample to evaluate the discrimination and calibration of the models. ML-based methods were applied to missing data imputation, predictor selection, risk prediction modelling, model interpretation, and model evaluation. Cox regression was used to develop the statistical models in parallel for comparison. During a median follow-up of 9.75 years, 32 445 patients (22.9%) developed CVD. Age, T2DM duration, urine albumin-to-creatinine ratio (ACR), estimated glomerular filtration rate (eGFR), systolic blood pressure variability and glycated haemoglobin (HbA1c) variability were the most important predictors. ML models also identified nonlinear effects of several predictors, particularly the U-shaped effects of eGFR and body mass index. The ML models showed a Harrell's C statistic of >0.80 and good calibration. The ML models performed significantly better than the Cox regression models in CVD risk prediction and achieved better risk stratification for individual patients. Using routinely available predictors and ML-based algorithms, this study established 10-year CVD risk prediction models for Chinese T2DM patients in primary care. The findings highlight the importance of renal function indicators, and variability in both blood pressure and HbA1c as CVD predictors, which deserve more clinical attention. The derived risk prediction tools have the potential to support clinical decision making and encourage patients towards self-care, subject to further research confirming the models' feasibility, acceptability and applicability at the point of care.

An international relations quantitative evaluation model (IRQEM) based on an integrated method.

International relations (IR) have great uncertainty and instability. Bad IR or conflicts will bring about heavy economic losses and widespread social unrest domestically and internationally. The accurate prediction for bilateral relations can support decision making for timely responses, which will be used to find ways to maintain development in the complex international situation. An international relations quantitative evaluation model (IRQEM) is proposed by integrating a variety of research models and methods like the interpretative structural modeling method (ISM), Bayesian network (BN) model, the Bayesian search (BS), and the expectation-maximization (EM) algorithm, which is novel for IR research. Factors from several different fields are identified as BN nodes. Each node is assigned different state values. The hierarchical structure of these BN nodes is obtained by ISM. The data collection of 192 cases is used to construct the BN model by GeNIe 4.0. The IRQEM can be used to evaluate the influence of emergencies on IR. The critical factors of IR also can be explored through our proposed model. Results show that the prediction of bilateral relations under emergencies can be realized by updating the indicator set when emergencies occur. The capability to anticipate threats of IR changes is advanced by optimizing the reporting information of IR forecasting through a combination of qualitative and quantitative methods, charts, and texts. Relevant analysis results can provide support for national security decision making.

Combinatorial machine learning approaches for high-rise building cost prediction and their interpretability analysis

ABSTRACT This study focuses on addressing housing gaps in populous southern countries by emphasizing the importance of accurate early cost estimation in construction projects. It compares individual cost prediction models (Decision Tree, BP Neural Network, and Support Vector Machine) with combined prediction models (BP-DT and BP-SVM) for high-rise building cost prediction. The study employs interpretative analysis methods such as the Shapley additive explanation method, partial dependence plots, and individual conditional expectation plots to explore feature interplay and improve model transparency. Results show that the BP-SVM combination algorithm significantly reduces Mean Absolute Error (MAE) compared to other models. Key factors influencing cost estimation include “Estimated project duration” and “Ground floor area”, while others like “Below-ground floors” have minimal impact. The study highlights the interaction of various feature groups on prediction outcomes. Through feature interaction analysis, it is found that the Estimated project duration and Building architecture can have some negative correlation interaction. Estimated project duration and Interior decoration may have to cancel effects Overall, it contributes to construction management by aiding investors in better-assessing project profitability, thereby enhancing investment decision efficiency and quality.

Development of a machine learning-based model for the prediction and progression of diabetic kidney disease: A single centred retrospective study

BackgroundDiabetic kidney disease (DKD) is a diabetic microvascular complication often characterized by an unpredictable progression. Hence, early detection and recognition of patients vulnerable to progression is crucial. ObjectiveTo develop a prediction model to identify the stages of DKD and the factors contributing to progression to each stage using machine learning. MethodologyA retrospective study was conducted in a South Indian tertiary care hospital and collected the details of patients diagnosed with DKD from January 2017 to January 2022. Bayesian optimization-based machine learning techniques such as classification and regression were employed. The model was developed with the help of an optimization framework that effectively balances classification, prediction accuracy, and explainability. ResultsOf the 311 patients diagnosed with DKD, 227 were selected for the study. A system for predicting DKD has been created for a patient dataset utilizing a variety of machine-learning approaches. The eXtreme gradient (XG) Boost method excelled, achieving 88.75% accuracy, 88.57% precision, 91.4% sensitivity,100% specificity, and 89.49% F1-score. An interpretable data-driven method highlights significant features for early DKD diagnosis. The best explainable prediction model uses the XG Boost classifier, revealing serum uric acid, urea, phosphorous, red blood cells, calcium, and absolute eosinophil count as the major predictors influencing the progression of DKD. In the case of regression models, the gradient boost regressor performed the best, with an R2 score of 0.97. ConclusionMachine learning algorithms can effectively predict the stages of DKD and thus help physicians in providing patients with personalized care at the right time.

An interpretable artificial intelligence model based on CT for prognosis of intracerebral hemorrhage: a multicenter study

ObjectivesTo develop and validate a novel interpretable artificial intelligence (AI) model that integrates radiomic features, deep learning features, and imaging features at multiple semantic levels to predict the prognosis of intracerebral hemorrhage (ICH) patients at 6 months post-onset.Materials and methodsRetrospectively enrolled 222 patients with ICH for Non-contrast Computed Tomography (NCCT) images and clinical data, who were divided into a training cohort (n = 186, medical center 1) and an external testing cohort (n = 36, medical center 2). Following image preprocessing, the entire hematoma region was segmented by two radiologists as the volume of interest (VOI). Pyradiomics algorithm library was utilized to extract 1762 radiomics features, while a deep convolutional neural network (EfficientnetV2-L) was employed to extract 1000 deep learning features. Additionally, radiologists evaluated imaging features. Based on the three different modalities of features mentioned above, the Random Forest (RF) model was trained, resulting in three models (Radiomics Model, Radiomics-Clinical Model, and DL-Radiomics-Clinical Model). The performance and clinical utility of the models were assessed using the Area Under the Receiver Operating Characteristic Curve (AUC), calibration curve, and Decision Curve Analysis (DCA), with AUC compared using the DeLong test. Furthermore, this study employs three methods, Shapley Additive Explanations (SHAP), Grad-CAM, and Guided Grad-CAM, to conduct a multidimensional interpretability analysis of model decisions.ResultsThe Radiomics-Clinical Model and DL-Radiomics-Clinical Model exhibited relatively good predictive performance, with an AUC of 0.86 [95% Confidence Intervals (CI): 0.71, 0.95; P < 0.01] and 0.89 (95% CI: 0.74, 0.97; P < 0.01), respectively, in the external testing cohort.ConclusionThe multimodal explainable AI model proposed in this study can accurately predict the prognosis of ICH. Interpretability methods such as SHAP, Grad-CAM, and Guided Grad-Cam partially address the interpretability limitations of AI models. Integrating multimodal imaging features can effectively improve the performance of the model.Clinical relevance statementPredicting the prognosis of patients with ICH is a key objective in emergency care. Accurate and efficient prognostic tools can effectively prevent, manage, and monitor adverse events in ICH patients, maximizing treatment outcomes.

An interpretable artificial intelligence model based on CT for prognosis of intracerebral hemorrhage: a multicenter study

ObjectivesTo develop and validate a novel interpretable artificial intelligence (AI) model that integrates radiomic features, deep learning features, and imaging features at multiple semantic levels to predict the prognosis of intracerebral hemorrhage (ICH) patients at 6 months post-onset.Materials and methodsRetrospectively enrolled 222 patients with ICH for Non-contrast Computed Tomography (NCCT) images and clinical data, who were divided into a training cohort (n = 186, medical center 1) and an external testing cohort (n = 36, medical center 2). Following image preprocessing, the entire hematoma region was segmented by two radiologists as the volume of interest (VOI). Pyradiomics algorithm library was utilized to extract 1762 radiomics features, while a deep convolutional neural network (EfficientnetV2-L) was employed to extract 1000 deep learning features. Additionally, radiologists evaluated imaging features. Based on the three different modalities of features mentioned above, the Random Forest (RF) model was trained, resulting in three models (Radiomics Model, Radiomics-Clinical Model, and DL-Radiomics-Clinical Model). The performance and clinical utility of the models were assessed using the Area Under the Receiver Operating Characteristic Curve (AUC), calibration curve, and Decision Curve Analysis (DCA), with AUC compared using the DeLong test. Furthermore, this study employs three methods, Shapley Additive Explanations (SHAP), Grad-CAM, and Guided Grad-CAM, to conduct a multidimensional interpretability analysis of model decisions.ResultsThe Radiomics-Clinical Model and DL-Radiomics-Clinical Model exhibited relatively good predictive performance, with an AUC of 0.86 [95% Confidence Intervals (CI): 0.71, 0.95; P < 0.01] and 0.89 (95% CI: 0.74, 0.97; P < 0.01), respectively, in the external testing cohort.ConclusionThe multimodal explainable AI model proposed in this study can accurately predict the prognosis of ICH. Interpretability methods such as SHAP, Grad-CAM, and Guided Grad-Cam partially address the interpretability limitations of AI models. Integrating multimodal imaging features can effectively improve the performance of the model.Clinical relevance statementPredicting the prognosis of patients with ICH is a key objective in emergency care. Accurate and efficient prognostic tools can effectively prevent, manage, and monitor adverse events in ICH patients, maximizing treatment outcomes.

CWD as a New Health Threat in Europe and the Adequacy and Effectiveness of Instruments of Legal Response from a Comparative Legal Perspective

Prions cause infectious and fatal neurodegenerative diseases in mammals. Chronic wasting disease (CWD) affects wild and farmed cervids. The increasing number of cases in Europe, the resistance of prions to external conditions, and the persistence period threaten not only wild cervid populations but also the economy. The possible zoonotic potential of CWD is of growing concern. CWD is a relevant issue as far as the idea of “one health” is concerned, which is a fundamental principle of European veterinary law. Methods of legal text analysis and interpretation are used for this comparative legal study. Research reveals that countries struggling to tackle CWD employ different normative approaches to the problem and use different control and eradication schemes. The results of this study indicate that it is reasonable to issue uniform regulations in the European Union at the common, rather than national, level. The European legislation should creatively draw on the experience of North American countries that have been struggling with the discussed disease for a long time.

CWD as a New Health Threat in Europe and the Adequacy and Effectiveness of Instruments of Legal Response from a Comparative Legal Perspective

Prions cause infectious and fatal neurodegenerative diseases in mammals. Chronic wasting disease (CWD) affects wild and farmed cervids. The increasing number of cases in Europe, the resistance of prions to external conditions, and the persistence period threaten not only wild cervid populations but also the economy. The possible zoonotic potential of CWD is of growing concern. CWD is a relevant issue as far as the idea of “one health” is concerned, which is a fundamental principle of European veterinary law. Methods of legal text analysis and interpretation are used for this comparative legal study. Research reveals that countries struggling to tackle CWD employ different normative approaches to the problem and use different control and eradication schemes. The results of this study indicate that it is reasonable to issue uniform regulations in the European Union at the common, rather than national, level. The European legislation should creatively draw on the experience of North American countries that have been struggling with the discussed disease for a long time.

Inferring dynamical models from time-series biological data using an interpretable machine learning method based on weighted expression trees

Abstract The growing time-series data make it possible to glimpse the hidden dynamics in various fields. However, developing a computational toolbox with high interpretability to unveil the interaction dynamics from data remains a crucial challenge. Here, we propose a new computational approach called Automated Dynamical Model Inference based on Expression Trees (ADMIET), in which the machine learning algorithm, the numerical integration of ordinary differential equations and the interpretability from prior knowledge are embedded into the symbolic learning scheme to establish a general framework for revealing the hidden dynamics in time-series data. ADMIET takes full advantage of both machine learning algorithm and expression tree. Firstly, we translate the prior knowledge into constraints on the structure of expression tree, reducing the search space and enhancing the interpretability. Secondly, we utilize the proposed adaptive penalty function to ensure the convergence of gradient descent algorithm and the selection of the symbols. Compared to gene expression programming, ADMIET exhibits its remarkable capability in function fitting with higher accuracy and broader applicability. Moreover, ADMIET can better fit parameters in nonlinear forms compared to regression methods. Furthermore, we apply ADMIET to two typical biological systems and one real data with different prior knowledge to infer the dynamical equations. The results indicate that ADMIET can not only discover the interaction relationships but also provide accurate estimates of the parameters in the equations. These results demonstrate ADMIET's superiority in revealing interpretable dynamics from time-series biological data.

"I want my son to die before I do": A phenomenological study on the views of mothers with disabled children about death after the 6 February 2023 earthquakes in Türkiye.

In this study, it was aimed to investigate the experiences of mothers with disabled children directly affected by the 6 February 2023 earthquakes in Türkiye regarding the concept of death in the context of social representations. The interpretive phenomenological analysis method, which is a qualitative research method, was used in the study. The content of semi-structured interviews held with 23 mothers was analyzed according to the analysis guidelines of Smith and Osborn. As a result of the analyses, four themes representing the views of the participants on the concept of death, which were "the perception of death, individual factors affecting the perception of death, environmental factors affecting the perception of death, and methods of coping with death anxiety," as well as fifteen categories under these themes, were revealed. The results of this study present the experiences and needs of mothers with disabled children after the aforementioned earthquakes, their needs in this process, their views about death, and their coping resources within a cultural framework. According to the results, the existing needs and death anxiety of mothers with disabled children have become more prominent after the earthquakes.

Idealism, materialism, and Vygotsky’s cultural historical theory

Vygotsky straddled the period of the Russian Revolution and found himself facing the Marxist materialist ideology of the Soviet Union with the need for a new method of psychology. Ironically, the Soviet Union’s need for a Marxist based method of psychology coincided with Vygotsky’s prior research on methods of interpretation which were inspired by Hegel and primarily based on the role of consciousness and culture. As a result of Vygotsky’s pre-revolutionary work and inspiration from Hegel clashing with the post-revolutionary need for a new methodology for psychology, Vygotsky developed his Cultural Historical Theory. In presenting his new theory, Vygotsky attempted to resolve a fundamental ideological conflict between idealism and materialism. Furthermore, Vygotsky worked to create an effective new research method by drawing inspiration from Gestalt psychology, Hegel, Marx, and Engels. The result of Vygotsky’s efforts was a theory based on psychology of consciousness and mind rather than a biology-based psychology focused entirely on analysis of stimuli and responses. In analyzing Vygotsky’s theory, it is useful to draw inspiration from Vygotsky’s criticism of pure empiricism, and to be inspired by Vygotsky’s demonstration on how deeply rooted differences between societies may be bridged by finding unexpected commonalities within opposing ideologies.

Idealism, materialism, and Vygotsky's cultural historical theory.

Vygotsky straddled the period of the Russian Revolution and found himself facing the Marxist materialist ideology of the Soviet Union with the need for a new method of psychology. Ironically, the Soviet Union's need for a Marxist based method of psychology coincided with Vygotsky's prior research on methods of interpretation which were inspired by Hegel and primarily based on the role of consciousness and culture. As a result of Vygotsky's pre-revolutionary work and inspiration from Hegel clashing with the post-revolutionary need for a new methodology for psychology, Vygotsky developed his Cultural Historical Theory. In presenting his new theory, Vygotsky attempted to resolve a fundamental ideological conflict between idealism and materialism. Furthermore, Vygotsky worked to create an effective new research method by drawing inspiration from Gestalt psychology, Hegel, Marx, and Engels. The result of Vygotsky's efforts was a theory based on psychology of consciousness and mind rather than a biology-based psychology focused entirely on analysis of stimuli and responses. In analyzing Vygotsky's theory, it is useful to draw inspiration from Vygotsky's criticism of pure empiricism, and to be inspired by Vygotsky's demonstration on how deeply rooted differences between societies may be bridged by finding unexpected commonalities within opposing ideologies.

Lightweight Low-Voltage AC Arc-Fault Detection Method Based on the Interpretability Method

Electrical fires are frequently caused by low-voltage AC series arc faults, which can result in significant injuries and property damage. The installation of arc-fault detection devices is mandated or recommended in many regions and countries across the world, yet the current devices’ detection accuracy is insufficient to completely eliminate the risk posed by arc faults. The method based on artificial intelligence is a solution with high detection accuracy, but the AI model is a ‘black box’. When a misjudgment occurs, the cause of the model error cannot be found fundamentally, and the modification and light weight of the model also presents significant difficulties when using the approach. Given the aforementioned issues, this research proposes a novel lightweight low-voltage AC arc-fault detection method based on the explainability approach. By applying the attention mechanism approach and performing a visual analysis, the contribution of arc features to model detection is determined. Model input data optimization and model structure simplification are achieved at the same time as increased model detection accuracy. Ultimately, an experimental prototype for arc-fault detection is designed and validated. Test results demonstrate the effectiveness of the method by demonstrating that the lightweight model maintains 99.69% detection accuracy, even after optimizing the input data by 80% and reducing the model parameters by 51.52%.

Ozone Pollution in China Affected by Climate Change in a Carbon Neutral Future as Predicted by a Process‐Based Interpretable Machine Learning Method

AbstractOzone (O3) pollution is a severe air quality issue in China, posing a threat to human health and ecosystems. The climate change will affect O3 levels by directly changing physical and chemical processes of O3 and indirectly changing natural emissions of O3 precursors. In this study, near‐surface O3 concentrations in China in 2030 and 2060 are predicted using the process‐based interpretable Extreme Gradient Boosting (XGBoost) model integrated with multi‐source data. The results show that the climate‐driven O3 levels over eastern China are projected to decrease by more than 0.4 ppb in 2060 under the carbon neutral scenario (SSP1‐1.9) compared with the high emission scenario (SSP5‐8.5). Among this reduction, 80% is attributed to the changes in physical and chemical processes of O3 related to a cooler climate, while the remaining 20% is attributed to the reduced biogenic isoprene emissions.

In-depth insight into the driving factors of the compressive strength development of MKPC based on interpretable machine learning methods

Magnesium potassium phosphate cement (MKPC) is a kind of Mg-chemically bonded phosphate ceramic commonly used for rapidly repairing dilapidated structures. In this study, a compressive strength dataset of MKPC was constructed, and four advanced machine learning (ML) algorithms (XGBoost, RF, GBDT and ANN) were selected to establish a high-precision compressive strength prediction model of MKPC. The SHAP and PDP methods are also used for interpretability analysis of ML-MKPC models. The XGBoost model has good generalizability and reliability while achieving high prediction accuracy. The RF and GBDT models performed similarly to the XGBoost model on the training set but performed poorly on the testing set. The ANN model is poorly trained on both the training and testing sets, with a risk of underfitting. The R2 of the XGBoost model at the different compressive strength stages still reaches above 0.80, indicating that it not only captures the complex relationships of the overall dataset well but also effectively predicts the staged strength dataset. Feature importance analysis revealed that the curing age (T), water-to-binder ratio (W/B), mineral admixtures-to-binder ratio (MA/B) and phosphate-to-magnesium ratio (P/M) are the principal variables affecting the compressive strength of MKPC. The partial interpretation shows that the optimum value range is determined when W/B is 0.10–0.18, MA/B is 0–0.20, P/M is 0.40–1.0, and R/M is 0–0.12. The composition of mineral admixtures with high-Ca, high-Si and low-Al systems seems to be more conducive to participating in the hydration reaction of MKPC. The ML-MKPC compressive strength prediction model developed in this study can provide theoretical support for the subsequent composition design and performance optimization of MKPC.

Interpretable artificial intelligence to optimise use of imatinib after resection in patients with localised gastrointestinal stromal tumours: an observational cohort study.

Current guidelines recommend use of adjuvant imatinib therapy for many patients with gastrointestinal stromal tumours (GISTs); however, its optimal treatment duration is unknown and some patient groups do not benefit from the therapy. We aimed to apply state-of-the-art, interpretable artificial intelligence (ie, predictions or prescription logic that can be easily understood) methods on real-world data to establish which groups of patients with GISTs should receive adjuvant imatinib, its optimal treatment duration, and the benefits conferred by this therapy. In this observational cohort study, we considered for inclusion all patients who underwent resection of primary, non-metastatic GISTs at the Memorial Sloan Kettering Cancer Center (MSKCC; New York, NY, USA) between Oct 1, 1982, and Dec 31, 2017, and who were classified as intermediate or high risk according to the Armed Forces Institute of Pathology Miettinen criteria and had complete follow-up data with no missing entries. A counterfactual random forest model, which used predictors of recurrence (mitotic count, tumour size, and tumour site) and imatinib duration to infer the probability of recurrence at 7 years for a given patient under each duration of imatinib treatment, was trained in the MSKCC cohort. Optimal policy trees (OPTs), a state-of-the-art interpretable AI-based method, were used to read the counterfactual random forest model by training a decision tree with the counterfactual predictions. The OPT recommendations were externally validated in two cohorts of patients from Poland (the Polish Clinical GIST Registry), who underwent GIST resection between Dec 1, 1981, and Dec 31, 2011, and from Spain (the Spanish Group for Research in Sarcomas), who underwent resection between Oct 1, 1987, and Jan 30, 2011. Among 1007 patients who underwent GIST surgery in MSKCC, 117 were included in the internal cohort; for the external cohorts, the Polish cohort comprised 363 patients and the Spanish cohort comprised 239 patients. The OPT did not recommend imatinib for patients with GISTs of gastric origin measuring less than 15·9 cm with a mitotic count of less than 11·5 mitoses per 5 mm2 or for those with small GISTs (<5·4 cm) of any site with a count of less than 11·5 mitoses per 5 mm2. In this cohort, the OPT cutoffs had a sensitivity of 92·7% (95% CI 82·4-98·0) and a specificity of 33·9% (22·3-47·0). The application of these cutoffs in the two external cohorts would have spared 38 (29%) of 131 patients in the Spanish cohort and 44 (35%) of 126 patients in the Polish cohort from unnecessary treatment with imatinib. Meanwhile, the risk of undertreating patients in these cohorts was minimal (sensitivity 95·4% [95% CI 89·5-98·5] in the Spanish cohort and 92·4% [88·3-95·4] in the Polish cohort). The OPT tested 33 different durations of imatinib treatment (<5 years) and found that 5 years of treatment conferred the most benefit. If the identified patient subgroups were applied in clinical practice, as many as a third of the current cohort of candidates who do not benefit from adjuvant imatinib would be encouraged to not receive imatinib, subsequently avoiding unnecessary toxicity on patients and financial strain on health-care systems. Our finding that 5 years is the optimal duration of imatinib treatment could be the best source of evidence to inform clinical practice until 2028, when a randomised controlled trial with the same aims is expected to report its findings. National Cancer Institute.