Decision trees: an overview and their use in medicine

An efficient improved parrot optimizer for bladder cancer classification

Bladder Cancer (BC) is a common disease that comes with a high risk of morbidity, death, and expense. Primary risk factors for BC include exposure to carcinogens in the workplace or the environment, particularly tobacco. There are several difficulties, such as the requirement for a qualified expert in BC classification. The Parrot Optimizer (PO), is an optimization method inspired by key behaviors observed in trained Pyrrhura Molinae parrots, but the PO algorithm becomes stuck in sub-regions, has less accuracy, and a high error rate. So, an Improved variant of the PO (IPO) algorithm was developed using a combination of two strategies: (1) Mirror Reflection Learning (MRL) and (2) Bernoulli Maps (BMs). Both strategies improve optimization performance by avoiding local optimums and striking a compromise between convergence speed and solution diversity. The performance of the proposed IPO is evaluated against eight other competitor algorithms in terms of statistical convergence and other metrics according to Friedman's test and Bonferroni-Dunn test on the IEEE Congress on Evolutionary Computation conducted in 2022 (CEC 2022) test suite functions and nine BC datasets from official repositories. The IPO algorithm ranked number one in best fitness and is more optimal than the other eight MH algorithms for CEC 2022 functions. The proposed IPO algorithm was integrated with the Support Vector Machine (SVM) classifier termed (IPO-SVM) approach for bladder cancer classification purposes. Nine BC datasets were then used to confirm the effectiveness of the proposed IPO algorithm. The experiments show that the IPO-SVM approach outperforms eight recently proposed MH algorithms. Using the nine BC datasets, IPO-SVM achieved an Accuracy (ACC) of 84.11%, Sensitivity (SE) of 98.10%, Precision (PPV) of 95.59%, Specificity (SP) of 95.98%, and F-score (F1) of 94.15%. This demonstrates how the proposed IPO approach can help to classify BCs effectively. The open-source codes are available at https://www.mathworks.com/matlabcentral/fileexchange/169846-an-efficient-improved-parrot-optimizer.

Development of decision tree classification algorithms in predicting mortality of COVID-19 patients

INTRODUCTION

The accurate prediction of COVID-19 mortality risk, considering influencing factors, is crucial in guiding effective public policies to alleviate the strain on the healthcare system. As such, this study aimed to assess the efficacy of decision tree algorithms (CART, C5.0, and CHAID) in predicting COVID-19 mortality risk and compare their performance with that of the logistic model.

METHODS

This retrospective cohort study examined 5080 cases of COVID-19 in Babol, a city in northern Iran, who tested positive for the virus via PCR from March 2020 to March 2022. In order to check the validity of the findings, the data was randomly divided into an 80% training set and a 20% testing set. The prediction models, such as Logistic regression models and decision tree algorithms, were trained on the 80% training data and tested on the 20% testing data. The accuracy of these methods for the test samples was assessed using measures like ROC curve, sensitivity, specificity, and AUC.

RESULTS

The findings revealed that the mortality rate for COVID-19 patients who were admitted to hospitals was 7.7%. Through cross validation, it was determined that the CHAID algorithm outperformed other decision tree and logistic regression algorithms in specificity, and precision but not sensitivity in predicting the risk of COVID-19 mortality. The CHAID algorithm demonstrated a specificity, precision, accuracy, and F-score of 0.98, 0.70, 0.95, and 0.52 respectively. All models indicated that factors such as ICU hospitalization, intubation, age, kidney disease, BUN, CRP, WBC, NLR, O2 sat, and hemoglobin were among the factors that influenced the mortality rate of COVID-19 patients.

CONCLUSIONS

The CART and C5.0 models had outperformed in sensitivity but CHAID demonstrates a better performance compared to other decision tree algorithms in specificity, precision, accuracy and shows a slight improvement over the logistic regression method in predicting the risk of COVID-19 mortality in the population under study.

Efficient bladder cancer diagnosis using an improved RIME algorithm with Orthogonal Learning

Bladder cancer (BC) diagnosis presents a critical challenge in biomedical research, necessitating accurate tumor classification from diverse datasets for effective treatment planning. This paper introduces a novel wrapper feature selection (FS) method that leverages a hybrid optimization algorithm combining Orthogonal Learning (OL) with a rime optimization algorithm (RIME), termed mRIME. The mRIME algorithm is designed to avoid local optima, streamline the search process, and select the most relevant features without compromising classifier performance. It also introduces mRIME-SVM, a novel hybrid model integrating modified mRIME for FS with Support Vector Machine (SVM) for classification. The mRIME algorithm is employed as an FS method and is also utilized to fine-tune the hyperparameters of it the It SVM, enhancing the overall classification accuracy. Specifically, mRIME navigates complex search spaces to optimize FS without compromising classifier performance. Evaluated on eight diverse BC datasets, mRIME-SVM outperforms popular metaheuristic algorithms, ensuring precise and reliable diagnostic outcomes. Moreover, the proposed mRIME was employed for tackling global optimization problems. It has been thoroughly assessed using the IEEE Congress on Evolutionary Computation 2022 (CEC'2022) test suite. Comparative analyzes with Gray wolf optimization (GWO), Whale optimization algorithm (WOA), Harris hawks optimization (HHO), Golden Jackal Optimization (GJO), Hunger Game optimization algorithm (HGS), Sinh Cosh Optimizer (SCHO), and the original RIME highlight mRIME's competitiveness and efficacy across diverse optimization tasks. Leveraging mRIME's success, mRIME-SVM achieves high classification accuracy on nine BC datasets, surpassing existing models. Results underscore mRIME's competitiveness and applicability across diverse optimization tasks, extending its utility to enhance BC classification. This study contributes to advancing BC diagnostics with a robust computational framework, promising broader applications in bioinformatics and AI-driven medical research.

Development of predictive model for post-stroke depression at discharge based on decision tree algorithm: A multi-center hospital-based cohort study

OBJECTIVE

Post-stroke depression (PSD) is one of the most common and severe neuropsychological sequelae after stroke. Using a prediction model composed of multiple predictors may be more beneficial than verifying the predictive performance of any single predictor. The primary objective of this study was to construct practical prediction tools for PSD at discharge utilizing a decision tree (DT) algorithm.

METHODS

A multi-center prospective cohort study was conducted from May 2018 to October 2019 and stroke patients within seven days of onset were consecutively recruited. The independent predictors of PSD at discharge were identified through multivariate logistic regression with backward elimination. Classification and regression tree (CART) algorithm was employed as the DT model's splitting method.

RESULTS

A total of 876 stroke patients who were discharged from the neurology departments of three large general Class A tertiary hospitals in Wuhan were eligible for analysis. Firstly, we divided these 876 patients into PSD and non-PSD groups, history of coronary heart disease (OR = 1.835; 95 % CI, 1.106-3.046; P = 0.019), length of hospital stay (OR = 1.040; 95 % CI, 1.013-1.069; P = 0.001), NIHSS score (OR = 1.124; 95 % CI, 1.052-1.201; P = 0.001), and Mini mental state examination (MMSE) score (OR = 0.935; 95 % CI, 0.893-0.978; P = 0.004) were significant predictors. The subgroup analysis results have shown that hemorrhagic stroke, history of hypertension and higher modified Rankin Scale score (mRS) score were associated with PSD at discharge in the young adult stroke patients.

CONCLUSIONS

Several predictors of PSD at discharge were identified and convenient DT models were constructed to facilitate clinical decision-making.

Democratizing cheminformatics: interpretable chemical grouping using an automated KNIME workflow

With the increased availability of chemical data in public databases, innovative techniques and algorithms have emerged for the analysis, exploration, visualization, and extraction of information from these data. One such technique is chemical grouping, where chemicals with common characteristics are categorized into distinct groups based on physicochemical properties, use, biological activity, or a combination. However, existing tools for chemical grouping often require specialized programming skills or the use of commercial software packages. To address these challenges, we developed a user-friendly chemical grouping workflow implemented in KNIME, a free, open-source, low/no-code, data analytics platform. The workflow serves as an all-encompassing tool, expertly incorporating a range of processes such as molecular descriptor calculation, feature selection, dimensionality reduction, hyperparameter search, and supervised and unsupervised machine learning methods, enabling effective chemical grouping and visualization of results. Furthermore, we implemented tools for interpretation, identifying key molecular descriptors for the chemical groups, and using natural language summaries to clarify the rationale behind these groupings. The workflow was designed to run seamlessly in both the KNIME local desktop version and KNIME Server WebPortal as a web application. It incorporates interactive interfaces and guides to assist users in a step-by-step manner. We demonstrate the utility of this workflow through a case study using an eye irritation and corrosion dataset.Scientific contributionsThis work presents a novel, comprehensive chemical grouping workflow in KNIME, enhancing accessibility by integrating a user-friendly graphical interface that eliminates the need for extensive programming skills. This workflow uniquely combines several features such as automated molecular descriptor calculation, feature selection, dimensionality reduction, and machine learning algorithms (both supervised and unsupervised), with hyperparameter optimization to refine chemical grouping accuracy. Moreover, we have introduced an innovative interpretative step and natural language summaries to elucidate the underlying reasons for chemical groupings, significantly advancing the usability of the tool and interpretability of the results.

Proximal humeral bone density assessment and prediction analysis using machine learning techniques: An innovative approach in medical research

Background

Patients with fractures of the proximal humerus often local complications and failures attributed to osteoporosis. Currently, there is a lack of straight forward screening methods for assessing the extent of local osteoporosis in the proximal humerus. This study utilizes machine learning techniques to establish a diagnostic approach for evaluating local osteoporosis by analyzing the patient's demographic data, bone density, and X-ray ratio of the proximal humerus.

Methods

A cohort comprising a total of 102 hospitalized patients admitted during the period spanning from 2021 to 2023 underwent random selection procedures. Resulting in exclusion of 5 patients while enrolling 97 patients for analysis encompassing patient demographics, shoulder joint anteroposterior radiographs, and bone density information. Using the modified Tingart index methodology involving multiple measurements denoted as M1 through M4 obtained from humeral shafts. Within this cohort comprised 76 females (78.4 %) and 21 males (21.6 %), with an average age of 73.0 years (range: 43-98 years). There were 25 cases with normal bone density, 35 with osteopenia, and 37 with osteoporosis. Machine learning techniques were used to randomly divide the 97 cases into training (n = 59) and validation (n = 38) sets with a ratio of 6:4 using stratified random sampling. A decision tree model was built in the training set, and significant diagnostic indicators were selected, with the performance of the decision tree evaluated using the validation set. Multinomial logistic regression methods were used to verify the strength of the relationship between the selected indicators and osteoporosis.

Results

The decision tree identified significant diagnostic indicators as the humeral shaft medullary cavity ratio M2/M4, age, and gender. M2/M4 ≥ 1.13 can be used as an important screening criterion; M2/M4 < 1.13 was predicted as local osteoporosis; M2/M4 ≥ 1.13 and age ≥83 years were also predicted as osteoporosis. M2/M4 ≥ 1.13 and age <64 years or males aged between 64 and 83 years were predicted as the normal population; M2/M4 ≥ 1.13 and females aged between 64 and 83 years were predicted as having osteopenia. The decision tree's accuracy in the training set was 0.7627 (95 % CI (0.6341, 0.8638)), and its accuracy in the test set was 0.7895 (95 % CI (0.6268, 0.9045)). Multinomial logistic regression results showed that humeral shaft medullary cavity ratios M2/M4, age, and gender in X-ray images were significantly associated with the occurrence of osteoporosis.

Conclusion

Utilizing X-ray data of the proximal humerus in conjunction with demographic information such as gender and age enable the prediction of localized osteoporosis, facilitating physicians' rapid comprehension of osteoporosis in patients and optimization of clinical treatment plans.

Level of evidence

Level IV retrospective case study.

Machine learning: a new era for cardiovascular pregnancy physiology and cardio-obstetrics research

The maternal cardiovascular system undergoes functional and structural adaptations during pregnancy and postpartum to support increased metabolic demands of offspring and placental growth, labor, and delivery, as well as recovery from childbirth. Thus, pregnancy imposes physiological stress upon the maternal cardiovascular system, and in the absence of an appropriate response it imparts potential risks for cardiovascular complications and adverse outcomes. The proportion of pregnancy-related maternal deaths from cardiovascular events has been steadily increasing, contributing to high rates of maternal mortality. Despite advances in cardiovascular physiology research, there is still no comprehensive understanding of maternal cardiovascular adaptations in healthy pregnancies. Furthermore, current approaches for the prognosis of cardiovascular complications during pregnancy are limited. Machine learning (ML) offers new and effective tools for investigating mechanisms involved in pregnancy-related cardiovascular complications as well as the development of potential therapies. The main goal of this review is to summarize existing research that uses ML to understand mechanisms of cardiovascular physiology during pregnancy and develop prediction models for clinical application in pregnant patients. We also provide an overview of ML platforms that can be used to comprehensively understand cardiovascular adaptations to pregnancy and discuss the interpretability of ML outcomes, the consequences of model bias, and the importance of ethical consideration in ML use.

A Mixed Methods Pilot Study to Evaluate User Engagement with MedMicroMaps: A Novel Interactive E-learning Tool for Medical Microbiology

Educators are witnessing the unfolding of the era of artificial intelligence, raising the question of how to transfer the benefits of yesterday's pedagogy to the future of education. An interactive digital mind map of infectious diseases was developed for second-year medical students (n = 865). Analysis of user engagement showed global distribution with 498 QR scans on a single day. Student responses (n = 79, 9.1% response rate) indicated positive feedback on the resources of Extremely Satisfied (range 65-75%, n = 59-51). The findings of the study support further expansion of MedMicroMaps to cross-platform interfaces with adaptations for diverse audiences within allied health fields.

Supplementary Information

The online version contains supplementary material available at 10.1007/s40670-024-02047-3.

Metabolomic and lipidomic fingerprints in inflammatory skin diseases - Systemic illumination of atopic dermatitis, hidradenitis suppurativa and plaque psoriasis

Auto-inflammatory skin diseases place considerable symptomatic and emotional burden on the affected and put pressure on healthcare expenditures. Although most apparent symptoms manifest on the skin, the systemic inflammation merits a deeper analysis beyond the surface. We set out to identify systemic commonalities, as well as differences in the metabolome and lipidome when comparing between diseases and healthy controls. Lipidomic and metabolomic LC-MS profiling was applied, using plasma samples collected from patients suffering from atopic dermatitis, plaque-type psoriasis or hidradenitis suppurativa or healthy controls. Plasma profiles revealed a notable shift in the non-enzymatic anti-oxidant defense in all three inflammatory disorders, placing cysteine metabolism at the center of potential dysregulation. Lipid network enrichment additionally indicated the disease-specific provision of lipid mediators associated with key roles in inflammation signaling. These findings will help to disentangle the systemic components of autoimmune dermatological diseases, paving the way to individualized therapy and improved prognosis.

Bloodstream infection: Derivation and validation of a reliable and multidimensional prognostic score based on a machine learning model (BLISCO)

BACKGROUND

A bloodstream infection (BSI) prognostic score applicable at the time of blood culture collection is missing.

METHODS

In total, 4,327 patients with BSIs were included, divided into a derivation (80%) and a validation dataset (20%). Forty-two variables among host-related, demographic, epidemiological, clinical, and laboratory extracted from the electronic health records were analyzed. Logistic regression was chosen for predictive scoring.

RESULTS

The 14-day mortality model included age, body temperature, blood urea nitrogen, respiratory insufficiency, platelet count, high-sensitive C-reactive protein, and consciousness status: a score of ≥ 6 was correlated to a 14-day mortality rate of 15% with a sensitivity of 0.742, a specificity of 0.727, and an area under the curve of 0.783. The 30-day mortality model further included cardiovascular diseases: a score of ≥ 6 predicting 30-day mortality rate of 15% with a sensitivity of 0.691, a specificity of 0.699, and an area under the curve of 0.697.

CONCLUSIONS

A quick mortality score could represent a valid support for prognosis assessment and resources prioritizing for patients with BSIs not admitted in the intensive care unit.

Development of a machine learning approach for prediction of red blood cell transfusion in patients undergoing Cesarean section at a single institution

Despite recent advances in surgical techniques and perinatal management in obstetrics for reducing intraoperative bleeding, blood transfusion may occur during a cesarean section (CS). This study aims to identify machine learning models with an optimal diagnostic performance for intraoperative transfusion prediction in parturients undergoing a CS. Additionally, to address model performance degradation due to data imbalance, this study further investigated the variation in predictive model performance depending on the ratio of event to non-event data (1:1, 1:2, 1:3, and 1:4 model datasets and raw data).The area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve (AUPRC) were evaluated to compare the predictive accuracy of different machine learning algorithms, including XGBoost, K-nearest neighbor, decision tree, support vector machine, multilayer perceptron, logistic regression, random forest, and deep neural network. We compared the predictive performance of eight prediction algorithms that were applied to five types of datasets. The intraoperative transfusion in maternal CS was 7.2% (1020/14,254). XGBoost showed the highest AUROC (0.8257) and AUPRC (0.4825) among the models. The most significant predictors for transfusion in maternal CS as per machine learning models were placenta previa totalis, haemoglobin, placenta previa partialis, and platelets. In all eight prediction algorithms, the change in predictive performance based on the AUROC and AUPRC according to the resampling ratio was insignificant. The XGBoost algorithm exhibited optimal performance for predicting intraoperative transfusion. Data balancing techniques employed to alter the event data composition ratio of the training data failed to improve the performance of the prediction model.

Clinical prediction models in children that use repeated measurements with time-varying covariates: a scoping review

BACKGROUND

Emerging evidence suggests that clinical prediction models that use repeated (time-varying) measurements within each patient may have higher predictive accuracy than models that use patient information from a single measurement.

OBJECTIVE

To determine the breadth of the published literature reporting the development of clinical prediction models in children that use time-varying predictors.

DATA SOURCES

MEDLINE, EMBASE and Cochrane databases.

ELIGIBILITY CRITERIA

We included studies reporting the development of a multivariable clinical prediction model in children, with or without validation, to predict a repeatedly measured binary or time-to-event outcome and utilizing at least one repeatedly measured predictor.

SYNTHESIS METHODS

We categorized included studies by the method used to model time-varying predictors.

RESULTS

Of 99 clinical prediction model studies that had a repeated measurements data structure, only 27 (27%) used methods that incorporated the repeated measurements as time-varying predictors in a single model. Among these 27 time-varying prediction model studies, we grouped model types into nine categories: time-dependent Cox regression, generalized estimating equations, random effects model, landmark model, joint model, neural network, K-nearest neighbor, support vector machine and tree-based algorithms. Where there was comparison of time-varying models to single measurement models, using time-varying predictors improved predictive accuracy.

CONCLUSIONS

Various methods have been used to develop time-varying prediction models in children, but there is a paucity of pediatric time-varying models in the literature. Incorporating time-varying covariates in pediatric prediction models may improve predictive accuracy. Future research in pediatric prediction model development should further investigate whether incorporation of time-varying covariates improves predictive accuracy.

The Menstrual Health Manager (MHM): A Resource to Reduce Discrepancies Between Science and Practice in Sport and Exercise

Inadequate research on female health and performance; the complexity of the research; low menstrual health literacy of athletes, coaches, and support staff; and ethical and cultural sensitivities are all recognized as barriers to effective health monitoring for females in sports. Frameworks have been developed for academics to follow to help improve the quality of female-specific research. However, a similar resource that enables correct terminology, and use of health monitoring techniques has not been provided for sporting organizations, coaches, support staff or athletes. Therefore, this critical commentary presents a new resource, the Menstrual Health Manager. This resource may be used to determine the level of menstrual health monitoring detail that may be used by organisations, coaches or athletes, and specifies what reproductive health details the data will provide. This resource aims to provide organizations and coaches with a means of understanding the data that inform their decisions for female athletes. Utilization of this resource may aid in the consistent use of terminology and methods for female-specific health monitoring in both sports and research.

Using machine learning to improve the diagnostic accuracy of the modified Duke/ESC 2015 criteria in patients with suspected prosthetic valve endocarditis - a proof of concept study

INTRODUCTION

Prosthetic valve endocarditis (PVE) is a serious complication of prosthetic valve implantation, with an estimated yearly incidence of at least 0.4-1.0%. The Duke criteria and subsequent modifications have been developed as a diagnostic framework for infective endocarditis (IE) in clinical studies. However, their sensitivity and specificity are limited, especially for PVE. Furthermore, their most recent versions (ESC2015 and ESC2023) include advanced imaging modalities, e.g., cardiac CTA and [18F]FDG PET/CT as major criteria. However, despite these significant changes, the weighing system using major and minor criteria has remained unchanged. This may have introduced bias to the diagnostic set of criteria. Here, we aimed to evaluate and improve the predictive value of the modified Duke/ESC 2015 (MDE2015) criteria by using machine learning algorithms.

METHODS

In this proof-of-concept study, we used data of a well-defined retrospective multicentre cohort of 160 patients evaluated for suspected PVE. Four machine learning algorithms were compared to the prediction of the diagnosis according to the MDE2015 criteria: Lasso logistic regression, decision tree with gradient boosting (XGBoost), decision tree without gradient boosting, and a model combining predictions of these (ensemble learning). All models used the same features that also constitute the MDE2015 criteria. The final diagnosis of PVE, based on endocarditis team consensus using all available clinical information, including surgical findings whenever performed, and with at least 1 year follow up, was used as the composite gold standard.

RESULTS

The diagnostic performance of the MDE2015 criteria varied depending on how the category of 'possible' PVE cases were handled. Considering these cases as positive for PVE, sensitivity and specificity were 0.96 and 0.60, respectively. Whereas treating these cases as negative, sensitivity and specificity were 0.74 and 0.98, respectively. Combining the approaches of considering possible endocarditis as positive and as negative for ROC-analysis resulted in an excellent AUC of 0.917. For the machine learning models, the sensitivity and specificity were as follows: logistic regression, 0.92 and 0.85; XGBoost, 0.90 and 0.85; decision trees, 0.88 and 0.86; and ensemble learning, 0.91 and 0.85, respectively. The resulting AUCs were, in the same order: 0.938, 0.937, 0.930, and 0.941, respectively.

DISCUSSION

In this proof-of-concept study, machine learning algorithms achieved improved diagnostic performance compared to the major/minor weighing system as used in the MDE2015 criteria. Moreover, these models provide quantifiable certainty levels of the diagnosis, potentially enhancing interpretability for clinicians. Additionally, they allow for easy incorporation of new and/or refined criteria, such as the individual weight of advanced imaging modalities such as CTA or [18F]FDG PET/CT. These promising preliminary findings warrant further studies for validation, ideally in a prospective cohort encompassing the full spectrum of patients with suspected IE.

Predicting Tumor Dynamics Post-Staged GKRS: Machine Learning Models in Brain Metastases Prognosis

This study assesses the predictive performance of six machine learning models and a 1D Convolutional Neural Network (CNN) in forecasting tumor dynamics within three months following Gamma Knife radiosurgery (GKRS) in 77 brain metastasis (BM) patients. The analysis meticulously evaluates each model before and after hyperparameter tuning, utilizing accuracy, AUC, and other metrics derived from confusion matrices. The CNN model showcased notable performance with an accuracy of 98% and an AUC of 0.97, effectively complementing the broader model analysis. Initial findings highlighted that XGBoost significantly outperformed other models with an accuracy of 0.95 and an AUC of 0.95 before tuning. Post-tuning, the Support Vector Machine (SVM) demonstrated the most substantial improvement, achieving an accuracy of 0.98 and an AUC of 0.98. Conversely, XGBoost showed a decline in performance after tuning, indicating potential overfitting. The study also explores feature importance across models, noting that features like "control at one year", "age of the patient", and "beam-on time for volume V1 treated" were consistently influential across various models, albeit their impacts were interpreted differently depending on the model's underlying mechanics. This comprehensive evaluation not only underscores the importance of model selection and hyperparameter tuning but also highlights the practical implications in medical diagnostic scenarios, where the accuracy of positive predictions can be crucial. Our research explores the effects of staged Gamma Knife radiosurgery (GKRS) on larger tumors, revealing no significant outcome differences across protocols. It uniquely considers the impact of beam-on time and fraction intervals on treatment efficacy. However, the investigation is limited by a small patient cohort and data from a single institution, suggesting the need for future multicenter research.

Ensemble machine learning using hydrometeorological information to improve modeling of quality parameter of raw water supplying treatment plants

Source and raw water quality may deteriorate due to rainfall and river flow events that occur in watersheds. The effects on raw water quality are normally detected in drinking water treatment plants (DWTPs) with a time-lag after these events in the watersheds. Early warning systems (EWSs) in DWTPs require models with high accuracy in order to anticipate changes in raw water quality parameters. Ensemble machine learning (EML) techniques have recently been used for water quality modeling to improve accuracy and decrease variance in the outcomes. We used three decision-tree-based EML models (random forest [RF], gradient boosting [GB], and eXtreme Gradient Boosting [XGB]) to predict two critical parameters for DWTPs, raw water Turbidity and UV absorbance (UV254), using rainfall and river flow time series as predictors. When modeling raw water turbidity, the three EML models (rRF-Tu2=0.87, rGB-Tu2=0.80 and rXGB-Tu2=0.81) showed very good performance metrics. For raw water UV254, the three models (rRF-UV2=0.89, rGB-UV2=0.85 and rXGB-UV2=0.88) again showed very good performance metrics. Results from this study suggest that EML approaches could be used in EWSs to anticipate changes in the quality parameters of raw water and enhance decision-making in DWTPs.

Artificial intelligence in the diagnosis and treatment of acute appendicitis: a narrative review

Artificial intelligence is transforming healthcare. Artificial intelligence can improve patient care by analyzing large amounts of data to help make more informed decisions regarding treatments and enhance medical research through analyzing and interpreting data from clinical trials and research projects to identify subtle but meaningful trends beyond ordinary perception. Artificial intelligence refers to the simulation of human intelligence in computers, where systems of artificial intelligence can perform tasks that require human-like intelligence like speech recognition, visual perception, pattern-recognition, decision-making, and language processing. Artificial intelligence has several subdivisions, including machine learning, natural language processing, computer vision, and robotics. By automating specific routine tasks, artificial intelligence can improve healthcare efficiency. By leveraging machine learning algorithms, the systems of artificial intelligence can offer new opportunities for enhancing both the efficiency and effectiveness of surgical procedures, particularly regarding training of minimally invasive surgery. As artificial intelligence continues to advance, it is likely to play an increasingly significant role in the field of surgical learning. Physicians have assisted to a spreading role of artificial intelligence in the last decade. This involved different medical specialties such as ophthalmology, cardiology, urology, but also abdominal surgery. In addition to improvements in diagnosis, ascertainment of efficacy of treatment and autonomous actions, artificial intelligence has the potential to improve surgeons' ability to better decide if acute surgery is indicated or not. The role of artificial intelligence in the emergency departments has also been investigated. We considered one of the most common condition the emergency surgeons have to face, acute appendicitis, to assess the state of the art of artificial intelligence in this frequent acute disease. The role of artificial intelligence in diagnosis and treatment of acute appendicitis will be discussed in this narrative review.

Artificial Intelligence in Pediatric Emergency Medicine: Applications, Challenges, and Future Perspectives

The dawn of Artificial intelligence (AI) in healthcare stands as a milestone in medical innovation. Different medical fields are heavily involved, and pediatric emergency medicine is no exception. We conducted a narrative review structured in two parts. The first part explores the theoretical principles of AI, providing all the necessary background to feel confident with these new state-of-the-art tools. The second part presents an informative analysis of AI models in pediatric emergencies. We examined PubMed and Cochrane Library from inception up to April 2024. Key applications include triage optimization, predictive models for traumatic brain injury assessment, and computerized sepsis prediction systems. In each of these domains, AI models outperformed standard methods. The main barriers to a widespread adoption include technological challenges, but also ethical issues, age-related differences in data interpretation, and the paucity of comprehensive datasets in the pediatric context. Future feasible research directions should address the validation of models through prospective datasets with more numerous sample sizes of patients. Furthermore, our analysis shows that it is essential to tailor AI algorithms to specific medical needs. This requires a close partnership between clinicians and developers. Building a shared knowledge platform is therefore a key step.

A review of machine learning methods for cancer characterization from microbiome data

Recent studies have shown that the microbiome can impact cancer development, progression, and response to therapies suggesting microbiome-based approaches for cancer characterization. As cancer-related signatures are complex and implicate many taxa, their discovery often requires Machine Learning approaches. This review discusses Machine Learning methods for cancer characterization from microbiome data. It focuses on the implications of choices undertaken during sample collection, feature selection and pre-processing. It also discusses ML model selection, guiding how to choose an ML model, and model validation. Finally, it enumerates current limitations and how these may be surpassed. Proposed methods, often based on Random Forests, show promising results, however insufficient for widespread clinical usage. Studies often report conflicting results mainly due to ML models with poor generalizability. We expect that evaluating models with expanded, hold-out datasets, removing technical artifacts, exploring representations of the microbiome other than taxonomical profiles, leveraging advances in deep learning, and developing ML models better adapted to the characteristics of microbiome data will improve the performance and generalizability of models and enable their usage in the clinic.

Strategies for Reliable Stress Recognition: A Machine Learning Approach Using Heart Rate Variability Features

Stress recognition, particularly using machine learning (ML) with physiological data such as heart rate variability (HRV), holds promise for mental health interventions. However, limited datasets in affective computing and healthcare research can lead to inaccurate conclusions regarding the ML model performance. This study employed supervised learning algorithms to classify stress and relaxation states using HRV measures. To account for limitations associated with small datasets, robust strategies were implemented based on methodological recommendations for ML with a limited dataset, including data segmentation, feature selection, and model evaluation. Our findings highlight that the random forest model achieved the best performance in distinguishing stress from non-stress states. Notably, it showed higher performance in identifying stress from relaxation (F1-score: 86.3%) compared to neutral states (F1-score: 65.8%). Additionally, the model demonstrated generalizability when tested on independent secondary datasets, showcasing its ability to distinguish between stress and relaxation states. While our performance metrics might be lower than some previous studies, this likely reflects our focus on robust methodologies to enhance the generalizability and interpretability of ML models, which are crucial for real-world applications with limited datasets.

Refining the rheological characteristics of high drug loading ointment via SDS and machine learning

This paper presents an optimized preparation process for external ointment using the Definitive Screening Design (DSD) method. The ointment is a Traditional Chinese Medicine (TCM) formula developed by Professor WYH, a renowned TCM practitioner in Jiangsu Province, China, known for its proven clinical efficacy. In this study, a stepwise regression model was employed to analyze the relationship between key process factors (such as mixing speed and time) and rheological parameters. Machine learning techniques, including Monte Carlo simulation, decision tree analysis, and Gaussian process, were used for parameter optimization. Through rigorous experimentation and verification, we have successfully identified the optimal preparation process for WYH ointment. The optimized parameters included drug ratio of 24.5%, mixing time of 8 min, mixing speed of 1175 rpm, petroleum dosage of 79 g, liquid paraffin dosage of 6.7 g. The final ointment formulation was prepared using method B. This research not only contributes to the optimization of the WYH ointment preparation process but also provides valuable insights and practical guidance for designing the preparation processes of other TCM ointments. This advanced DSD method enhances the screening approach for identifying the best preparation process, thereby improving the scientific rigor and quality of TCM ointment preparation processes.

A Potential Screening Strategy to Identify Probable Syphilis Infections in the Urban Emergency Department Setting

Background

Syphilis diagnosis in the emergency department (ED) setting is often missed due to the lack of ED-specific testing strategies. We characterized ED patients with high-titer syphilis infections (HTSIs) with the goal of defining a screening strategy that most parsimoniously identifies undiagnosed, untreated syphilis infections.

Methods

Unlinked, de-identified remnant serum samples from patients attending an urban ED, between 10 January and 9 February 2022, were tested using a three-tier testing algorithm, and sociodemographic variables were extracted from ED administrative database prior to testing. Patients who tested positive for treponemal antibodies in the first tier and positive at high titer (≥1:8) for nontreponemal antibodies in the second tier were classified as HTSI. Human immunodeficiency virus (HIV) status was determined with Bio-Rad enzyme-linked immunosorbent assay and confirmatory assays. Exact logistic regression and classification and regression tree (CART) analyses were performed to determine factors associated with HTSI and derive screening strategies.

Results

Among 1951 unique patients tested, 23 (1.2% [95% confidence interval, .8%-1.8%]) had HTSI. Of those, 18 (78%) lacked a primary care physician, 5 (22%) were HIV positive, and 8 (35%) were women of reproductive age (18-49 years). CART analysis (area under the curve of 0.67) showed that using a screening strategy that measured syphilis antibodies in patients with HIV, without a primary care physician, and women of reproductive age would have identified most patients with HTSI (21/23 [91%]).

Conclusions

We show a high prevalence of HTSI in an urban ED and propose a feasible, novel screening strategy to curtail community transmission and prevent long-term complications.

Demographic and clinical characteristics associated with advanced stage colorectal cancer: a registry-based cohort study in Saudi Arabia

BACKGROUND

In Saudi Arabia, approximately one-third of colorectal cancer (CRC) patients are diagnosed at an advanced stage. Late diagnosis is often associated with a worse prognosis. Understanding the risk factors for late-stage presentation of CRC is crucial for developing targeted interventions enabling earlier detection and improved patient outcomes.

METHODS

We conducted a retrospective cohort study on 17,541 CRC patients from the Saudi Cancer Registry (1997-2017). We defined distant CRCs as late-stage and localized and regional CRCs as early-stage. To assess risk factors for late-stage CRC, we first used multivariable logistic regression, then developed a decision tree to segment regions by late-stage CRC risk, and finally used stratified logistic regression models to examine geographical and sex variations in risk factors.

RESULTS

Of all cases, 29% had a late-stage diagnosis, and 71% had early-stage CRC. Young (< 50 years) and unmarried women had an increased risk of late-stage CRC, overall and in some regions. Regional risk variations by sex were observed. Sex-related differences in late-stage rectosigmoid cancer risk were observed in specific regions but not in the overall population. Patients diagnosed after 2001 had increased risks of late-stage presentation.

CONCLUSION

Our study identified risk factors for late-stage CRC that can guide targeted early detection efforts. Further research is warranted to fully understand these relationships and develop and evaluate effective prevention strategies.

Explainable AI for CHO cell culture media optimization and prediction of critical quality attribute

Cell culture media play a critical role in cell growth and propagation by providing a substrate; media components can also modulate the critical quality attributes (CQAs). However, the inherent complexity of the cell culture media makes unraveling the impact of the various media components on cell growth and CQAs non-trivial. In this study, we demonstrate an end-to-end machine learning framework for media component selection and prediction of CQAs. The preliminary dataset for feature selection was generated by performing CHO-GS (-/-) cell culture in media formulations with varying metal ion concentrations. Acidic and basic charge variant composition of the innovator product (24.97 ± 0.54% acidic and 11.41 ± 1.44% basic) was chosen as the target variable to evaluate the media formulations. Pearson's correlation coefficient and random forest-based techniques were used for feature ranking and feature selection for the prediction of acidic and basic charge variants. Furthermore, a global interpretation analysis using SHapley Additive exPlanations was utilized to select optimal features by evaluating the contributions of each feature in the extracted vectors. Finally, the medium combinations were predicted by employing fifteen different regression models and utilizing a grid search and random search cross-validation for hyperparameter optimization. Experimental results demonstrate that Fe and Zn significantly impact the charge variant profile. This study aims to offer insights that are pertinent to both innovators seeking to establish a complete pipeline for media development and optimization and biosimilar-based manufacturers who strive to demonstrate the analytical and functional biosimilarity of their products to the innovator. KEY POINTS: • Developed a framework for optimizing media components and prediction of CQA. • SHAP enhances global interpretability, aiding informed decision-making. • Fifteen regression models were employed to predict medium combinations.

Delayed care-seeking in international migrant workers with imported malaria in China

BACKGROUND

Imported malaria cases continue to pose major challenges in China as well as in other countries that have achieved elimination. Early diagnosis and treatment of each imported malaria case is the key to successfully maintaining malaria elimination success. This study aimed to build an easy-to-use predictive nomogram to predict and intervene against delayed care-seeking among international migrant workers with imported malaria.

METHODS

A prediction model was built based on cases with imported malaria from 2012 to 2019, in Jiangsu Province, China. Routine surveillance information (e.g. sex, age, symptoms, origin country and length of stay abroad), data on the place of initial care-seeking and the gross domestic product (GDP) of the destination city were extracted. Multivariate logistic regression was performed to identify independent predictors and a nomogram was established to predict the risk of delayed care-seeking. The discrimination and calibration of the nomogram was performed using area under the curve and calibration plots. In addition, four machine learning models were used to make a comparison.

RESULTS

Of 2255 patients with imported malaria, 636 (28.2%) sought care within 24 h after symptom onset, and 577 (25.6%) sought care 3 days after symptom onset. Development of symptoms before entry into China, initial care-seeking from superior healthcare facilities and a higher GDP level of the destination city were significantly associated with delayed care-seeking among migrant workers with imported malaria. Based on these independent risk factors, an easy-to-use and intuitive nomogram was established. The calibration curves of the nomogram showed good consistency.

CONCLUSIONS

The tool provides public health practitioners with a method for the early detection of delayed care-seeking risk among international migrant workers with imported malaria, which may be of significance in improving post-travel healthcare for labour migrants, reducing the risk of severe malaria, preventing malaria reintroduction and sustaining achievements in malaria elimination.

Phytostabilization of metal(loid)s by ten emergent macrophytes following a 90-day exposure to industrially contaminated groundwater

Better understanding of macrophyte tolerance under long exposure times in real environmental matrices is crucial for phytoremediation and phytoattenuation strategies for aquatic systems. The metal(loid) attenuation ability of 10 emergent macrophyte species (Carex riparia, Cyperus longus, Cyperus rotundus, Iris pseudacorus, Juncus effusus, Lythrum salicaria, Menta aquatica, Phragmites australis, Scirpus holoschoenus, and Typha angustifolia) was investigated using real groundwater from an industrial site, over a 90-day exposure period. A "phytobial" treatment was included, with 3 plant growth-promoting rhizobacterial strains. Plants exposed to the polluted water generally showed similar or reduced aerial biomass compared to the controls, except for C. riparia. This species, along with M. aquatica, exhibited improved biomass after bioaugmentation. Phytoremediation mechanisms accounted for more than 60% of As, Cd, Cu, Ni, and Pb removal, whilst abiotic mechanisms contributed to ∼80% removal of Fe and Zn. Concentrations of metal(loid)s in the roots were generally between 10-100 times higher than in the aerial parts. The macrophytes in this work can be considered "underground attenuators", more appropriate for rhizostabilization strategies, especially L. salicaria, M. aquatica, S. holoschoenus, and T. angustifolia. For I. pseudacorus, C. longus, and C. riparia; harvesting the aerial parts could be a complementary phytoextraction approach to further remove Pb and Zn. Of all the plants, S. holoschoenus showed the best balance between biomass production and uptake of multiple metal(loid)s. Results also suggest that multiple phytostrategies may be possible for the same plant depending on the final remedial aim. Phytobial approaches need to be further assessed for each macrophyte species.

Detection of COVID-19, pneumonia, and tuberculosis from radiographs using AI-driven knowledge distillation

Chest radiography is an essential diagnostic tool for respiratory diseases such as COVID-19, pneumonia, and tuberculosis because it accurately depicts the structures of the chest. However, accurate detection of these diseases from radiographs is a complex task that requires the availability of medical imaging equipment and trained personnel. Conventional deep learning models offer a viable automated solution for this task. However, the high complexity of these models often poses a significant obstacle to their practical deployment within automated medical applications, including mobile apps, web apps, and cloud-based platforms. This study addresses and resolves this dilemma by reducing the complexity of neural networks using knowledge distillation techniques (KDT). The proposed technique trains a neural network on an extensive collection of chest X-ray images and propagates the knowledge to a smaller network capable of real-time detection. To create a comprehensive dataset, we have integrated three popular chest radiograph datasets with chest radiographs for COVID-19, pneumonia, and tuberculosis. Our experiments show that this knowledge distillation approach outperforms conventional deep learning methods in terms of computational complexity and performance for real-time respiratory disease detection. Specifically, our system achieves an impressive average accuracy of 0.97, precision of 0.94, and recall of 0.97.

Shallow and deep learning classifiers in medical image analysis

An increasingly strong connection between artificial intelligence and medicine has enabled the development of predictive models capable of supporting physicians' decision-making. Artificial intelligence encompasses much more than machine learning, which nevertheless is its most cited and used sub-branch in the last decade. Since most clinical problems can be modeled through machine learning classifiers, it is essential to discuss their main elements. This review aims to give primary educational insights on the most accessible and widely employed classifiers in radiology field, distinguishing between "shallow" learning (i.e., traditional machine learning) algorithms, including support vector machines, random forest and XGBoost, and "deep" learning architectures including convolutional neural networks and vision transformers. In addition, the paper outlines the key steps for classifiers training and highlights the differences between the most common algorithms and architectures. Although the choice of an algorithm depends on the task and dataset dealing with, general guidelines for classifier selection are proposed in relation to task analysis, dataset size, explainability requirements, and available computing resources. Considering the enormous interest in these innovative models and architectures, the problem of machine learning algorithms interpretability is finally discussed, providing a future perspective on trustworthy artificial intelligence.Relevance statement The growing synergy between artificial intelligence and medicine fosters predictive models aiding physicians. Machine learning classifiers, from shallow learning to deep learning, are offering crucial insights for the development of clinical decision support systems in healthcare. Explainability is a key feature of models that leads systems toward integration into clinical practice. Key points • Training a shallow classifier requires extracting disease-related features from region of interests (e.g., radiomics).• Deep classifiers implement automatic feature extraction and classification.• The classifier selection is based on data and computational resources availability, task, and explanation needs.

Predictive model for identifying mild cognitive impairment in patients with type 2 diabetes mellitus: A CHAID decision tree analysis

BACKGROUND

As the population ages, mild cognitive impairment (MCI) and type 2 diabetes mellitus (T2DM) become common conditions that often coexist. Evidence has shown that MCI could lead to reduced treatment compliance, medication management, and self-care ability in T2DM patients. Therefore, early identification of those with increased risk of MCI is crucial from a preventive perspective. Given the growing utilization of decision trees in prediction of health-related outcomes, this study aimed to identify MCI in T2DM patients using the decision tree approach.

METHODS

This hospital-based case-control study was performed in the Endocrinology Department of Xiangya Hospital affiliated to Central South University between March 2021 and December 2022. MCI was defined based on the Petersen criteria. Demographic characteristics, lifestyle factors, and T2DM-related information were collected. The study sample was randomly divided into the training and validation sets in a 7:3 ratio. Univariate and multivariate analyses were performed, and a decision tree model was established using the chi-square automatic interaction detection (CHAID) algorithm to identify key predictor variables associated with MCI. The area under the curve (AUC) value was used to evaluate the performance of the established decision tree model, and the performance of multivariate regression model was also evaluated for comparison.

RESULTS

A total of 1001 participants (705 in the training set and 296 in the validation set) were included in this study. The mean age of participants in the training and validation sets was 60.2  ±  10.3 and 60.4  ±  9.5 years, respectively. There were no significant differences in the characteristics between the training and validation sets (p > .05). The CHAID decision tree analysis identified six key predictor variables associated with MCI, including age, educational level, household income, regular physical activity, diabetic nephropathy, and diabetic retinopathy. The established decision tree model had 15 nodes composed of 4 layers, and age is the most significant predictor variable. It performed well (AUC = .75 [95% confidence interval (CI): .71-.78] and .67 [95% CI: .61-.74] in the training and validation sets, respectively), was internally validated, and had comparable predictive value compared to the multivariate logistic regression model (AUC = .76 [95% CI: .72-.80] and .69 [95% CI: .62-.75] in the training and validation sets, respectively).

CONCLUSION

The established decision tree model based on age, educational level, household income, regular physical activity, diabetic nephropathy, and diabetic retinopathy performed well with comparable predictive value compared to the multivariate logistic regression model and was internally validated. Due to its superior classification accuracy and simple presentation as well as interpretation of collected data, the decision tree model is more recommended for the prediction of MCI in T2DM patients in clinical practice.

Ensemble machine learning reveals key features for diabetes duration from electronic health records

Diabetes is a metabolic disorder that affects more than 420 million of people worldwide, and it is caused by the presence of a high level of sugar in blood for a long period. Diabetes can have serious long-term health consequences, such as cardiovascular diseases, strokes, chronic kidney diseases, foot ulcers, retinopathy, and others. Even if common, this disease is uneasy to spot, because it often comes with no symptoms. Especially for diabetes type 2, that happens mainly in the adults, knowing how long the diabetes has been present for a patient can have a strong impact on the treatment they can receive. This information, although pivotal, might be absent: for some patients, in fact, the year when they received the diabetes diagnosis might be well-known, but the year of the disease unset might be unknown. In this context, machine learning applied to electronic health records can be an effective tool to predict the past duration of diabetes for a patient. In this study, we applied a regression analysis based on several computational intelligence methods to a dataset of electronic health records of 73 patients with diabetes type 1 with 20 variables and another dataset of records of 400 patients of diabetes type 2 with 49 variables. Among the algorithms applied, Random Forests was able to outperform the other ones and to efficiently predict diabetes duration for both the cohorts, with the regression performances measured through the coefficient of determination R2. Afterwards, we applied the same method for feature ranking, and we detected the most relevant factors of the clinical records correlated with past diabetes duration: age, insulin intake, and body-mass index. Our study discoveries can have profound impact on clinical practice: when the information about the duration of diabetes of patient is missing, medical doctors can use our tool and focus on age, insulin intake, and body-mass index to infer this important aspect. Regarding limitations, unfortunately we were unable to find additional dataset of EHRs of patients with diabetes having the same variables of the two analyzed here, so we could not verify our findings on a validation cohort.

Can we predict overall survival using machine learning algorithms at 3-months for brain metastases from non-small cell lung cancer after gamma knife radiosurgery?

Gamma knife radiosurgery (GRKS) is widely used for patients with brain metastases; however, predictions of overall survival (OS) within 3-months post-GKRS remain imprecise. Specifically, more than 10% of non-small cell lung cancer (NSCLC) patients died within 8 weeks of post-GKRS, indicating potential overtreatment. This study aims to predict OS within 3-months post-GKRS using machine learning algorithms, and to identify prognostic features in NSCLC patients. We selected 120 NSCLC patients who underwent GKRS at Chungbuk National University Hospital. They were randomly assigned to training group (n = 80) and testing group (n = 40) with 14 features considered. We used 3 machine learning (ML) algorithms (Decision tree, Random forest, and Boosted tree classifier) to predict OS within 3-months for NSCLC patients. And we extracted important features and permutation features. Data validation was verified by physician and medical physicist. The accuracy of the ML algorithms for predicting OS within 3-months was 77.5% for the decision tree, 72.5% for the random forest, and 70% for the boosted tree classifier. The important features commonly showed age, receiving chemotherapy, and pretreatment each algorithm. Additionally, the permutation features commonly showed tumor volume (>10 cc) and age as critical factors each algorithm. The decision tree algorithm exhibited the highest accuracy. Analysis of the decision tree visualized data revealed that patients aged (>71 years) with tumor volume (>10 cc) were increased risk of mortality within 3-months. The findings suggest that ML algorithms can effectively predict OS within 3-months and identify crucial features in NSCLC patients. For NSCLC patients with poor prognoses, old age, and large tumor volumes, GKRS may not be a desirable treatment.

Using classification trees to identify psychotherapy patients at risk for poor treatment adherence

To determine the relative importance of a wide variety of personality and psychopathology variables in influencing patients' adherence to psychotherapy treatment.

Two classification trees were trained to predict patients' (1) treatment utilization (i.e., their likelihood of missing a given appointment) and (2) termination status (i.e., their likelihood of dropping out of therapy prematurely). Each tree was then validated in an external dataset to examine performance accuracy.

Patients' social detachment was most influential in predicting their treatment utilization, followed by affective instability and activity/energy levels. Patients' interpersonal warmth was most influential in predicting their termination status, followed by levels of disordered thought and resentment. The overall accuracy rating for the tree for termination status was 71.4%, while the tree for treatment utilization had a 38.7% accuracy rating.

Classification trees are a practical tool for clinicians to determine patients at risk of premature termination. More research is needed to develop trees that predict treatment utilization with high accuracy across different types of patients and settings.

Evaluation of changes in glycemic control and diabetic complications over time and factors associated with the progression of diabetic complications in Japanese patients with juvenile-onset type 1 diabetes mellitus

BACKGROUND

This study aimed to evaluate the changes in glycemic control and diabetic complications over time in Japanese patients with juvenile-onset type 1 diabetes mellitus and to clarify the factors associated with the progression of diabetic complications.

METHODS

We tracked 129 patients with type 1 diabetes mellitus (21.8 ± 4.1 years old [mean ± SD] with a diabetes duration of 12.6 ± 5.7 years) for up to 19 years and analyzed data on glycated hemoglobin (HbA1c) and indicators related to the severity of diabetic complications (estimated glomerular filtration rate [eGFR], urinary albumin excretion rate [UAE], carotid intima-media thickness [CIMT], and brachial-ankle pulse wave velocity [baPWV]) using linear mixed model and decision tree analysis.

RESULTS

Although the HbA1c and UAE levels improved over time, the eGFR, CIMT, and baPWV worsened. Decision tree analysis showed that HbA1c and the glycoalbumin/HbA1c ratio for eGFR; HbA1c and systolic blood pressure for UAE; low-density lipoprotein cholesterol/high-density lipoprotein cholesterol ratio, glycoalbumin/HbA1c ratio, and body mass index (BMI) for CIMT; and HbA1c for baPWV were associated factors.

CONCLUSIONS

In this retrospective observational study, glycemic control and albuminuria improved; however, renal function and arteriosclerosis worsened over time. HbA1c levels, glycemic excursion, and blood pressure are associated with nephropathy progression. HbA1c levels, glycemic excursion, lipid levels, and BMI are associated with the progression of atherosclerosis.

Machine learning in onco-pharmacogenomics: a path to precision medicine with many challenges

Over the past two decades, Next-Generation Sequencing (NGS) has revolutionized the approach to cancer research. Applications of NGS include the identification of tumor specific alterations that can influence tumor pathobiology and also impact diagnosis, prognosis and therapeutic options. Pharmacogenomics (PGx) studies the role of inheritance of individual genetic patterns in drug response and has taken advantage of NGS technology as it provides access to high-throughput data that can, however, be difficult to manage. Machine learning (ML) has recently been used in the life sciences to discover hidden patterns from complex NGS data and to solve various PGx problems. In this review, we provide a comprehensive overview of the NGS approaches that can be employed and the different PGx studies implicating the use of NGS data. We also provide an excursus of the ML algorithms that can exert a role as fundamental strategies in the PGx field to improve personalized medicine in cancer.

A cluster-based ensemble approach for congenital heart disease prediction

BACKGROUND

One of the most prevalent birth disorders is congenital heart diseases (CHD). Although CHD risk factors have been the subject of numerous studies, their propensity to cause CHD has not been tested. Particularly few research has attempted to forecast CHD risk using population-based cross-sectional data, which is inherently imbalanced.

OBJECTIVE

The main goals of this study are to create a reliable data analysis model that can help with (i) a better understanding of congenital heart disease prediction in the presence of missing and unbalanced data and (ii) creating cohorts of expectant mothers with similar lifestyle characteristics.

METHODS

Clusters of patient cohorts are produced using the unsupervised data mining technique density-based spatial clustering of applications with noise (DBSCAN). For more accurate CHD prediction, a random forest model was trained using these clusters and their corresponding patterns. This study uses a dataset of 33,831 expectant mothers to make its prediction. Missing data were handled using the k-NN imputation approach, while extremely unbalanced data were balanced using SMOTE. These techniques are all data-driven and need little to no user or expert involvement.

RESULTS AND CONCLUSION

Using DBSCAN, three cohorts were found. The cluster information enhanced the random forest-based CHD prediction and revealed intricate factors that influence prediction accuracy. The proposed approach gave the highest results with 99 % accuracy and 0.91 AUC and performed better than the state-of-the-art methodologies. Hence, the suggested method using unsupervised learning can provide intricate information to the classifier and further enhance the performance of the classification.

Effects of lifestyle behaviours and depressed mood on sleep quality in young adults. A machine learning approach

BACKGROUND

Modern lifestyles may lead to high stress levels, frequently associated with mood disorders (e.g. depressed mood) and sleep disturbance. The objective of this study was to develop a machine learning model aimed at identifying risk factors for developing poor sleep quality in young adults.

MATERIAL AND METHODS

The sample consisted of 383 college-aged students (mean age ± SD: 21 ± 1 years; 61% males). Sleep quality, mood state, physical activity, number of sitting hours, and smartphone use were measured.

RESULTS

A decision tree algorithm distinguished participants' sleep quality with 74% accuracy using a combination of four features: depressed mood, physical activity, sitting time, and vigour. Together with depressed mood, both physical activity (>6432 metabolic equivalent tasks -METs- per week) and sedentary behaviour (sitting time greater than 7 h/day) were the primary features that could differentiate those with poor sleep quality from those with good sleep quality.

CONCLUSIONS

We provided a decision tree model with a sensitivity of 90.7% and a specificity of 54.3%, with an AUC of 0.725. These findings could promote improvements in prevention strategies and contribute to the development of meaningful and evidence-based intervention programs.

Evaluating Machine Learning Methods of Analyzing Multiclass Metabolomics

Multiclass metabolomic studies have become popular for revealing the differences in multiple stages of complex diseases, various lifestyles, or the effects of specific treatments. In multiclass metabolomics, there are multiple data manipulation steps for analyzing raw data, which consist of data filtering, the imputation of missing values, data normalization, marker identification, sample separation, classification, and so on. In each step, several to dozens of machine learning methods can be chosen for the given data set, with potentially hundreds or thousands of method combinations in the whole data processing chain. Therefore, a clear understanding of these machine learning methods is helpful for selecting an appropriate method combination for obtaining stable and reliable analytical results of specific data. However, there has rarely been an overall introduction or evaluation of these methods based on multiclass metabolomic data. Herein, detailed descriptions of these machine learning methods in multiple data manipulation steps are reviewed. Moreover, an assessment of these methods was performed using a benchmark data set for multiclass metabolomics. First, 12 imputation methods for imputing missing values were evaluated based on the PSS (Procrustes statistical shape analysis) and NRMSE (normalized root-mean-square error) values. Second, 17 normalization methods for processing multiclass metabolomic data were evaluated by applying the PMAD (pooled median absolute deviation) value. Third, different methods of identifying markers of multiclass metabolomics were evaluated based on the CWrel (relative weighted consistency) value. Fourth, nine classification methods for constructing multiclass models were assessed using the AUC (area under the curve) value. Performance evaluations of machine learning methods are highly recommended to select the most appropriate method combination before performing the final analysis of the given data. Overall, detailed descriptions and evaluation of various machine learning methods are expected to improve analyses of multiclass metabolomic data.

Prediction of Clinical Remission with Adalimumab Therapy in Patients with Ulcerative Colitis by Fourier Transform-Infrared Spectroscopy Coupled with Machine Learning Algorithms

We aimed to develop prediction models for clinical remission associated with adalimumab treatment in patients with ulcerative colitis (UC) using Fourier transform-infrared (FT-IR) spectroscopy coupled with machine learning (ML) algorithms. This prospective, observational, multicenter study enrolled 62 UC patients and 30 healthy controls. The patients were treated with adalimumab for 56 weeks, and clinical remission was evaluated using the Mayo score. Baseline fecal samples were collected and analyzed using FT-IR spectroscopy. Various data preprocessing methods were applied, and prediction models were established by 10-fold cross-validation using various ML methods. Orthogonal partial least squares-discriminant analysis (OPLS-DA) showed a clear separation of healthy controls and UC patients, applying area normalization and Pareto scaling. OPLS-DA models predicting short- and long-term remission (8 and 56 weeks) yielded area-under-the-curve values of 0.76 and 0.75, respectively. Logistic regression and a nonlinear support vector machine were selected as the best prediction models for short- and long-term remission, respectively (accuracy of 0.99). In external validation, prediction models for short-term (logistic regression) and long-term (decision tree) remission performed well, with accuracy values of 0.73 and 0.82, respectively. This was the first study to develop prediction models for clinical remission associated with adalimumab treatment in UC patients by fecal analysis using FT-IR spectroscopy coupled with ML algorithms. Logistic regression, nonlinear support vector machines, and decision tree were suggested as the optimal prediction models for remission, and these were noninvasive, simple, inexpensive, and fast analyses that could be applied to personalized treatments.

Explainability as the key ingredient for AI adoption in Industry 5.0 settings

Explainable Artificial Intelligence (XAI) has gained significant attention as a means to address the transparency and interpretability challenges posed by black box AI models. In the context of the manufacturing industry, where complex problems and decision-making processes are widespread, the XMANAI platform emerges as a solution to enable transparent and trustworthy collaboration between humans and machines. By leveraging advancements in XAI and catering the prompt collaboration between data scientists and domain experts, the platform enables the construction of interpretable AI models that offer high transparency without compromising performance. This paper introduces the approach to building the XMANAI platform and highlights its potential to resolve the "transparency paradox" of AI. The platform not only addresses technical challenges related to transparency but also caters to the specific needs of the manufacturing industry, including lifecycle management, security, and trusted sharing of AI assets. The paper provides an overview of the XMANAI platform main functionalities, addressing the challenges faced during the development and presenting the evaluation framework to measure the performance of the delivered XAI solutions. It also demonstrates the benefits of the XMANAI approach in achieving transparency in manufacturing decision-making, fostering trust and collaboration between humans and machines, improving operational efficiency, and optimizing business value.

Toward More Accessible Fully Automated 3D Volumetric MRI Decision Trees for the Differential Diagnosis of Multiple System Atrophy, Related Disorders, and Age-Matched Healthy Subjects

Differentiating multiple system atrophy (MSA) from related neurodegenerative movement disorders (NMD) is challenging. MRI is widely available and automated decision-tree analysis is simple, transparent, and resistant to overfitting. Using a retrospective cohort of heterogeneous clinical MRIs broadly sourced from a tertiary hospital system, we aimed to develop readily translatable and fully automated volumetric diagnostic decision-trees to facilitate early and accurate differential diagnosis of NMDs. 3DT1 MRI from 171 NMD patients (72 MSA, 49 PSP, 50 PD) and 171 matched healthy subjects were automatically segmented using Freesurfer6.0 with brainstem module. Decision trees employing substructure volumes and a novel volumetric pons-to-midbrain ratio (3D-PMR) were produced and tenfold cross-validation performed. The optimal tree separating NMD from healthy subjects selected cerebellar white matter, thalamus, putamen, striatum, and midbrain volumes as nodes. Its sensitivity was 84%, specificity 94%, accuracy 84%, and kappa 0.69 in cross-validation. The optimal tree restricted to NMD patients selected 3D-PMR, thalamus, superior cerebellar peduncle (SCP), midbrain, pons, and putamen as nodes. It yielded sensitivities/specificities of 94/84% for MSA, 72/96% for PSP, and 73/92% PD, with 79% accuracy and 0.62 kappa. There was correct classification of 16/17 MSA, 5/8 PSP, 6/8 PD autopsy-confirmed patients, and 6/8 MRIs that preceded motor symptom onset. Fully automated decision trees utilizing volumetric MRI data distinguished NMD patients from healthy subjects and MSA from other NMDs with promising accuracy, including autopsy-confirmed and pre-symptomatic subsets. Our open-source methodology is well-suited for widespread clinical translation. Assessment in even more heterogeneous retrospective and prospective cohorts is indicated.

Moving towards more sustainable diets: Is there potential for a personalised approach in practice?

Discourse on the relationship between food production, healthy eating and sustainability has become increasingly prominent and controversial in recent years. Research groups often take one perspective when reporting on sustainable diets, and several often neglect considerations for the multiple aspects that make a diet truly sustainable, such as cultural acceptability, differences in nutritional requirements amongst the population and the efficiency of long-term dietary change. Plant-based diets are associated with lower greenhouse gas emissions (GHGEs) and have been linked with better health outcomes, including lower risk of diet-related chronic disease. However, foods associated with higher GHGE, such as lean red meat, fish and dairy, have beneficial nutritional profiles and contribute significantly to micronutrient intakes. Some research has shown that diets associated with lower GHGE can be less nutritionally adequate. Several countries now include sustainability recommendations in dietary guidelines but use vague language such as "increase" or "consume regularly" when referring to plant-based foods. General population-based nutrition advice has poor adherence and does not consider differences in nutritional needs. Although modelling studies show potential to significantly reduce environmental impact with dietary changes, personalising such dietary recommendations has not been studied. Adapting recommendations to the individual through reproducible methods of personalised nutrition has been shown to lead to more favourable and longer-lasting dietary changes compared to population-based nutrition advice. When considering sustainable healthy dietary guidelines, personalised feedback may increase the acceptability, effectiveness and nutritional adequacy of the diet. A personalised approach has the potential for delivering a new structure of more sustainable healthy food-based dietary guidelines. This review evaluates the potential to develop personalised sustainable healthy food-based dietary guidelines and discusses potential implications for policy and practice.

Predicting post-liver transplant outcomes in patients with acute-on-chronic liver failure using Expert-Augmented Machine Learning

Liver transplantation (LT) is a treatment for acute-on-chronic liver failure (ACLF), but high post-LT mortality has been reported. Existing post-LT models in ACLF have been limited. We developed an Expert-Augmented Machine Learning (EAML) model to predict post-LT outcomes. We identified ACLF patients who underwent LT in the University of California Health Data Warehouse. We applied the RuleFit machine learning (ML) algorithm to extract rules from decision trees and create intermediate models. We asked human experts to rate the rules generated by RuleFit and incorporated these ratings to generate final EAML models. We identified 1384 ACLF patients. For death at 1 year, areas under the receiver-operating characteristic curve were 0.707 (confidence interval [CI] 0.625-0.793) for EAML and 0.719 (CI 0.640-0.800) for RuleFit. For death at 90 days, areas under the receiver-operating characteristic curve were 0.678 (CI 0.581-0.776) for EAML and 0.707 (CI 0.615-0.800) for RuleFit. In pairwise comparisons, both EAML and RuleFit models outperformed cross-sectional models. Significant discrepancies between experts and ML occurred in rankings of biomarkers used in clinical practice. EAML may serve as a method for ML-guided hypothesis generation in further ACLF research.

Influence of decision-making algorithms on the diagnostic accuracy using the current classification of periodontal diseases-a randomized controlled trial

OBJECTIVES

To examine the influence of the decision-making algorithms published by Tonetti and Sanz in 2019 on the diagnostic accuracy in two differently experienced groups of dental students using the current classification of periodontal diseases.

MATERIALS AND METHODS

Eighty-three students of two different clinical experience levels were randomly allocated to control and study group, receiving the staging and grading matrix, resulting in four subgroups. All diagnosed two patient cases with corresponding periodontal charts, panoramic radiographs, and intraoral photographs. Both presented severe periodontal disease (stage III, grade C) but considerably differed in complexity and phenotype according to the current classification of periodontal diseases. Controls received the staging and grading matrix published within the classification, while study groups were additionally provided with decision-trees published by Tonetti and Sanz. Obtained data was analyzed using chi-square test, Spearman's rank correlation, and logistic regression.

RESULTS

Using the algorithms significantly enhanced the diagnostic accuracy in staging (p = 0.001*, OR = 4.425) and grading (p < 0.001**, OR = 30.303) regardless of the clinical experience. In addition, even compared to the more experienced control, less experienced students using algorithms showed significantly higher accuracy in grading (p = 0.020*). No influence on the criteria extent could be observed comparing study groups to controls.

CONCLUSION

The decision-making algorithms may enhance diagnostic accuracy in dental students using the current classification of periodontal diseases.

CLINICAL RELEVANCE

The investigated decision-making algorithms significantly increased the diagnostic accuracy of differently experienced under graduated dental students and might be beneficial in periodontal education.

The augmented value of using clinical notes in semi-automated surveillance of deep surgical site infections after colorectal surgery

BACKGROUND

In patients who underwent colorectal surgery, an existing semi-automated surveillance algorithm based on structured data achieves high sensitivity in detecting deep surgical site infections (SSI), however, generates a significant number of false positives. The inclusion of unstructured, clinical narratives to the algorithm may decrease the number of patients requiring manual chart review. The aim of this study was to investigate the performance of this semi-automated surveillance algorithm augmented with a natural language processing (NLP) component to improve positive predictive value (PPV) and thus workload reduction (WR).

METHODS

Retrospective, observational cohort study in patients who underwent colorectal surgery from January 1, 2015, through September 30, 2020. NLP was used to detect keyword counts in clinical notes. Several NLP-algorithms were developed with different count input types and classifiers, and added as component to the original semi-automated algorithm. Traditional manual surveillance was compared with the NLP-augmented surveillance algorithms and sensitivity, specificity, PPV and WR were calculated.

RESULTS

From the NLP-augmented models, the decision tree models with discretized counts or binary counts had the best performance (sensitivity 95.1% (95%CI 83.5-99.4%), WR 60.9%) and improved PPV and WR by only 2.6% and 3.6%, respectively, compared to the original algorithm.

CONCLUSIONS

The addition of an NLP component to the existing algorithm had modest effect on WR (decrease of 1.4-12.5%), at the cost of sensitivity. For future implementation it will be a trade-off between optimal case-finding techniques versus practical considerations such as acceptability and availability of resources.

Validity of Diagnostic Support Model for Attention Deficit Hyperactivity Disorder: A Machine Learning Approach

An accurate and early diagnosis of attention deficit hyperactivity disorder can improve health outcomes and prevent unnecessary medical expenses. This study developed a diagnostic support model using a machine learning approach to effectively screen individuals for attention deficit hyperactivity disorder. Three models were developed: a logistic regression model, a classification and regression tree (CART), and a neural network. The models were assessed by using a receiver operating characteristic analysis. In total, 74 participants were enrolled into the disorder group, while 21 participants were enrolled in the control group. The sensitivity and specificity of each model, indicating the rate of true positive and true negative results, respectively, were assessed. The CART model demonstrated a superior performance compared to the other two models, with region values of receiver operating characteristic analyses in the following order: CART (0.848) > logistic regression model (0.826) > neural network (0.67). The sensitivity and specificity of the CART model were 78.8% and 50%, respectively. This model can be applied to other neuroscience research fields, including the diagnoses of autism spectrum disorder, Tourette syndrome, and dementia. This will enhance the effect and practical value of our research.

Machine learning-based prediction models for home discharge in patients with COVID-19: Development and evaluation using electronic health records

OBJECTIVE

This study aimed to develop and validate predictive models using electronic health records (EHR) data to determine whether hospitalized COVID-19-positive patients would be admitted to alternative medical care or discharged home.

METHODS

We conducted a retrospective cohort study using deidentified data from the University of Florida Health Integrated Data Repository. The study included 1,578 adult patients (≥18 years) who tested positive for COVID-19 while hospitalized, comprising 960 (60.8%) female patients with a mean (SD) age of 51.86 (18.49) years and 618 (39.2%) male patients with a mean (SD) age of 54.35 (18.48) years. Machine learning (ML) model training involved cross-validation to assess their performance in predicting patient disposition.

RESULTS

We developed and validated six supervised ML-based prediction models (logistic regression, Gaussian Naïve Bayes, k-nearest neighbors, decision trees, random forest, and support vector machine classifier) to predict patient discharge status. The models were evaluated based on the area under the receiver operating characteristic curve (ROC-AUC), precision, accuracy, F1 score, and Brier score. The random forest classifier exhibited the highest performance, achieving an accuracy of 0.84 and an AUC of 0.72. Logistic regression (accuracy: 0.85, AUC: 0.71), k-nearest neighbor (accuracy: 0.84, AUC: 0.63), decision tree (accuracy: 0.84, AUC: 0.61), Gaussian Naïve Bayes (accuracy: 0.84, AUC: 0.66), and support vector machine classifier (accuracy: 0.84, AUC: 0.67) also demonstrated valuable predictive capabilities.

SIGNIFICANCE

This study's findings are crucial for efficiently allocating healthcare resources during pandemics like COVID-19. By harnessing ML techniques and EHR data, we can create predictive tools to identify patients at greater risk of severe symptoms based on their medical histories. The models developed here serve as a foundation for expanding the toolkit available to healthcare professionals and organizations. Additionally, explainable ML methods, such as Shapley Additive Explanations, aid in uncovering underlying data features that inform healthcare decision-making processes.

A multistart tabu search-based method for feature selection in medical applications

In the design of classification models, irrelevant or noisy features are often generated. In some cases, there may even be negative interactions among features. These weaknesses can degrade the performance of the models. Feature selection is a task that searches for a small subset of relevant features from the original set that generate the most efficient models possible. In addition to improving the efficiency of the models, feature selection confers other advantages, such as greater ease in the generation of the necessary data as well as clearer and more interpretable models. In the case of medical applications, feature selection may help to distinguish which characteristics, habits, and factors have the greatest impact on the onset of diseases. However, feature selection is a complex task due to the large number of possible solutions. In the last few years, methods based on different metaheuristic strategies, mainly evolutionary algorithms, have been proposed. The motivation of this work is to develop a method that outperforms previous methods, with the benefits that this implies especially in the medical field. More precisely, the present study proposes a simple method based on tabu search and multistart techniques. The proposed method was analyzed and compared to other methods by testing their performance on several medical databases. Specifically, eight databases belong to the well-known repository of the University of California in Irvine and one of our own design were used. In these computational tests, the proposed method outperformed other recent methods as gauged by various metrics and classifiers. The analyses were accompanied by statistical tests, the results of which showed that the superiority of our method is significant and therefore strengthened these conclusions. In short, the contribution of this work is the development of a method that, on the one hand, is based on different strategies than those used in recent methods, and on the other hand, improves the performance of these methods.

Exploring patient medication adherence and data mining methods in clinical big data: A contemporary review

BACKGROUND

Increasingly, patient medication adherence data are being consolidated from claims databases and electronic health records (EHRs). Such databases offer an indirect avenue to gauge medication adherence in our data-rich healthcare milieu. The surge in data accessibility, coupled with the pressing need for its conversion to actionable insights, has spotlighted data mining, with machine learning (ML) emerging as a pivotal technique. Nonadherence poses heightened health risks and escalates medical costs. This paper elucidates the synergistic interaction between medical database mining for medication adherence and the role of ML in fostering knowledge discovery.

METHODS

We conducted a comprehensive review of EHR applications in the realm of medication adherence, leveraging ML techniques. We expounded on the evolution and structure of medical databases pertinent to medication adherence and harnessed both supervised and unsupervised ML paradigms to delve into adherence and its ramifications.

RESULTS

Our study underscores the applications of medical databases and ML, encompassing both supervised and unsupervised learning, for medication adherence in clinical big data. Databases like SEER and NHANES, often underutilized due to their intricacies, have gained prominence. Employing ML to excavate patient medication logs from these databases facilitates adherence analysis. Such findings are pivotal for clinical decision-making, risk stratification, and scholarly pursuits, aiming to elevate healthcare quality.

CONCLUSION

Advanced data mining in the era of big data has revolutionized medication adherence research, thereby enhancing patient care. Emphasizing bespoke interventions and research could herald transformative shifts in therapeutic modalities.

Discovery of novel JAK1 inhibitors through combining machine learning, structure-based pharmacophore modeling and bio-evaluation

BACKGROUND

Janus kinase 1 (JAK1) plays a critical role in most cytokine-mediated inflammatory, autoimmune responses and various cancers via the JAK/STAT signaling pathway. Inhibition of JAK1 is therefore an attractive therapeutic strategy for several diseases. Recently, high-performance machine learning techniques have been increasingly applied in virtual screening to develop new kinase inhibitors. Our study aimed to develop a novel layered virtual screening method based on machine learning (ML) and pharmacophore models to identify the potential JAK1 inhibitors.

METHODS

Firstly, we constructed a high-quality dataset comprising 3834 JAK1 inhibitors and 12,230 decoys, followed by establishing a series of classification models based on a combination of three molecular descriptors and six ML algorithms. To further screen potential compounds, we constructed several pharmacophore models based on Hiphop and receptor-ligand algorithms. We then used molecular docking to filter the recognized compounds. Finally, the binding stability and enzyme inhibition activity of the identified compounds were assessed by molecular dynamics (MD) simulations and in vitro enzyme activity tests.

RESULTS

The best performance ML model DNN-ECFP4 and two pharmacophore models Hiphop3 and 6TPF 08 were utilized to screen the ZINC database. A total of 13 potentially active compounds were screened and the MD results demonstrated that all of the above molecules could bind with JAK1 stably in dynamic conditions. Among the shortlisted compounds, the four purchasable compounds demonstrated significant kinase inhibition activity, with Z-10 being the most active (IC50 = 194.9 nM).

CONCLUSION

The current study provides an efficient and accurate integrated model. The hit compounds were promising candidates for the further development of novel JAK1 inhibitors.

A Data-Driven Approach to Refine Predictions of Differentiated Thyroid Cancer Outcomes: A Prospective Multicenter Study

CONTEXT

The risk stratification of patients with differentiated thyroid cancer (DTC) is crucial in clinical decision making. The most widely accepted method to assess risk of recurrent/persistent disease is described in the 2015 American Thyroid Association (ATA) guidelines. However, recent research has focused on the inclusion of novel features or questioned the relevance of currently included features.

OBJECTIVE

To develop a comprehensive data-driven model to predict persistent/recurrent disease that can capture all available features and determine the weight of predictors.

METHODS

In a prospective cohort study, using the Italian Thyroid Cancer Observatory (ITCO) database (NCT04031339), we selected consecutive cases with DTC and at least early follow-up data (n = 4773; median follow-up 26 months; interquartile range, 12-46 months) at 40 Italian clinical centers. A decision tree was built to assign a risk index to each patient. The model allowed us to investigate the impact of different variables in risk prediction.

RESULTS

By ATA risk estimation, 2492 patients (52.2%) were classified as low, 1873 (39.2%) as intermediate, and 408 as high risk. The decision tree model outperformed the ATA risk stratification system: the sensitivity of high-risk classification for structural disease increased from 37% to 49%, and the negative predictive value for low-risk patients increased by 3%. Feature importance was estimated. Several variables not included in the ATA system significantly impacted the prediction of disease persistence/recurrence: age, body mass index, tumor size, sex, family history of thyroid cancer, surgical approach, presurgical cytology, and circumstances of the diagnosis.

CONCLUSION

Current risk stratification systems may be complemented by the inclusion of other variables in order to improve the prediction of treatment response. A complete dataset allows for more precise patient clustering.