Logistic Regression in Clinical Studies

Machine learning-derived peripheral blood transcriptomic biomarkers for early lung cancer diagnosis: Unveiling tumor-immune interaction mechanisms

Lung cancer continues to be the leading cause of cancer-related mortality worldwide. Early detection and a comprehensive understanding of tumor-immune interactions are crucial for improving patient outcomes. This study aimed to develop a novel biomarker panel utilizing peripheral blood transcriptomics and machine learning algorithms for early lung cancer diagnosis, while simultaneously providing insights into tumor-immune crosstalk mechanisms. Leveraging a training cohort (GSE135304), we employed multiple machine learning algorithms to formulate a Lung Cancer Diagnostic Score (LCDS) based on peripheral blood transcriptomic features. The LCDS model's performance was evaluated using the area under the receiver operating characteristic (ROC) curve (AUC) in multiple validation cohorts (GSE42834, GSE157086, and an in-house dataset). Peripheral blood samples were obtained from 20 lung cancer patients and 10 healthy control subjects, representing an in-house cohort recruited at the Sixth People's Hospital of Chengdu. We employed advanced bioinformatics techniques to explore tumor-immune interactions through comprehensive immune infiltration and pathway enrichment analyses. Initial screening identified 844 differentially expressed genes, which were subsequently refined to 87 genes using the Boruta feature selection algorithm. The random forest (RF) algorithm demonstrated the highest accuracy in constructing the LCDS model, yielding a mean AUC of 0.938. Lower LCDS values were significantly associated with elevated immune scores and increased CD4+ and CD8+ T-cell infiltration, indicative of enhanced antitumor-immune responses. Higher LCDS scores correlated with activation of hypoxia, peroxisome proliferator-activated receptor (PPAR), and Toll-like receptor (TLR) signaling pathways, as well as reduced DNA damage repair pathway scores. Our study presents a novel, machine learning-derived peripheral blood transcriptomic biomarker panel with potential applications in early lung cancer diagnosis. The LCDS model not only demonstrates high accuracy in distinguishing lung cancer patients from healthy individuals but also offers valuable insights into tumor-immune interactions and underlying cancer biology. This approach may facilitate early lung cancer detection and contribute to a deeper understanding of the molecular and cellular mechanisms underlying tumor-immune crosstalk. Furthermore, our findings on the relationship between LCDS and immune infiltration patterns may have implications for future research on therapeutic strategies targeting the immune system in lung cancer.

AI-Enhanced Prediction of Aortic Stenosis Progression: Insights From the PROGRESSA Study

Background

Aortic valve stenosis (AS) is a progressive chronic disease with progression rates that vary in patients and therefore difficult to predict.

Objectives

The aim of this study was to predict the progression of AS using comprehensive and longitudinal patient data.

Methods

Machine and deep learning algorithms were trained on a data set of 303 patients enrolled in the PROGRESSA (Metabolic Determinants of the Progression of Aortic Stenosis) study who underwent clinical and echocardiographic follow-up on an annual basis. Performance of the models was measured to predict disease progression over long (next 5 years) and short (next 2 years) terms and was compared to a standard clinical model with usually used features in clinical settings based on logistic regression.

Results

For each annual follow-up visit including baseline, we trained various supervised learning algorithms in predicting disease progression at 2- and 5-year terms. At both terms, LightGBM consistently outperformed other models with the highest average area under curves across patient visits (0.85 at 2 years, 0.83 at 5 years). Recurrent neural network-based models (Gated Recurrent Unit and Long Short-Term Memory) and XGBoost also demonstrated strong predictive capabilities, while the clinical model showed the lowest performance.

Conclusions

This study demonstrates how an artificial intelligence-guided approach in clinical routine could help enhance risk stratification of AS. It presents models based on multisource comprehensive data to predict disease progression and clinical outcomes in patients with mild-to-moderate AS at baseline.

Exploring the Impact of Model Complexity on Laryngeal Cancer Detection

Background: Laryngeal cancer accounts for a third of all head and neck malignancies, necessitating timely detection for effective treatment and enhanced patient outcomes. Machine learning shows promise in medical diagnostics, but the impact of model complexity on diagnostic efficacy in laryngeal cancer detection can be ambiguous. Methods: In this study, we examine the relationship between model sophistication and diagnostic efficacy by evaluating three approaches: Logistic Regression, a small neural network with 4 layers of neurons and a more complex convolutional neural network with 50 layers and examine their efficacy on laryngeal cancer detection on computed tomography images. Results: Logistic regression achieved 82.5% accuracy. The 4-Layer NN reached 87.2% accuracy, while ResNet-50, a deep learning architecture, achieved the highest accuracy at 92.6%. Its deep learning capabilities excelled in discerning fine-grained CT image features. Conclusion: Our study highlights the choices involved in selecting a laryngeal cancer detection model. Logistic regression is interpretable but may struggle with complex patterns. The 4-Layer NN balances complexity and accuracy. ResNet-50 excels in image classification but demands resources. This research advances understanding affect machine learning model complexity could have on learning features of laryngeal tumor features in contrast CT images for purposes of disease prediction.

Artificial intelligence approaches for tinnitus diagnosis: leveraging high-frequency audiometry data for enhanced clinical predictions

This research investigates the application of machine learning to improve the diagnosis of tinnitus using high-frequency audiometry data. A Logistic Regression (LR) model was developed alongside an Artificial Neural Network (ANN) and various baseline classifiers to identify the most effective approach for classifying tinnitus presence. The methodology encompassed data preprocessing, feature extraction focused on point detection, and rigorous model evaluation through performance metrics including accuracy, Area Under the ROC Curve (AUC), precision, recall, and F1 scores. The main findings reveal that the LR model, supported by the ANN, significantly outperformed other machine learning models, achieving an accuracy of 94.06%, an AUC of 97.06%, and high precision and recall scores. These results demonstrate the efficacy of the LR model and ANN in accurately diagnosing tinnitus, surpassing traditional diagnostic methods that rely on subjective assessments. The implications of this research are substantial for clinical audiology, suggesting that machine learning, particularly advanced models like ANNs, can provide a more objective and quantifiable tool for tinnitus diagnosis, especially when utilizing high-frequency audiometry data not typically assessed in standard hearing tests. The study underscores the potential for machine learning to facilitate earlier and more accurate tinnitus detection, which could lead to improved patient outcomes. Future work should aim to expand the dataset diversity, explore a broader range of algorithms, and conduct clinical trials to validate the models' practical utility. The research highlights the transformative potential of machine learning, including the LR model and ANN, in audiology, paving the way for advancements in the diagnosis and treatment of tinnitus.

Anti-synthetase syndrome is associated with a higher risk of hospitalization among patients with idiopathic inflammatory myopathy and COVID-19

Background

Data with fine granularity about COVID-19-related outcomes and risk factors were still limited in the idiopathic inflammatory myopathies (IIMs) population. This study aimed to investigate clinical factors associated with hospitalized and severe COVID-19 in patients with IIMs, particularly those gauged by myositis-specific antibodies.

Methods

This retrospective cohort study was conducted in the Renji IIM cohort in Shanghai, China, under an upsurge of SARS-CoV-2 omicron variant infections from December 2022 to January 2023. Clinical data were collected and analyzed by multivariable logistic regression to determine risk factors. High-dimensional flow cytometry analysis was performed to outline the immunological features.

Results

Among 463 infected patients in the eligible cohort (n=613), 65 (14.0%) were hospitalized, 19 (4.1%) suffered severe COVID-19, and 10 (2.2%) died. Older age (OR=1.59/decade, 95% CI 1.18 to 2.16, p=0.003), requiring family oxygen supplement (2.62, 1.11 to 6.19, 0.028), patients with anti-synthetase syndrome (ASyS) (2.88, 1.12 to 7.34, 0.027, vs. other dermatomyositis), higher IIM disease activity, and prednisone intake >10mg/day (5.59, 2.70 to 11.57, <0.001) were associated with a higher risk of hospitalization. Conversely, 3-dose inactivated vaccination reduced the risk of hospitalization (0.10, 0.02 to 0.40, 0.001, vs. incomplete vaccination). Janus kinase inhibitor (JAKi) pre-exposure significantly reduced the risk of severe COVID-19 in hospitalized patients (0.16, 0.04 to 0.74, 0.019, vs. csDMARDs). ASyS patients with severe COVID-19 had significantly reduced peripheral CD4+ T cells, lower CD4/CD8 ratio, and fewer naive B cells but more class-switched memory B cells compared with controls.

Conclusion

ASyS and family oxygen supplement were first identified as risk factors for COVID-19-related hospitalization in patients with IIMs. JAKi pre-exposure might protect IIM patients against severe COVID-19 complications.

Risk factors for early ostomy complications in emergency and elective colorectal surgery: A single-center retrospective cohort study

BACKGROUND AND AIMS

The clinical significance of early ostomy complications has been emphasized worldwide, and the current evidence concerning the impact of emergency or elective surgery on ostomy complications is limited. This study aimed to investigate the effect of elective and emergency colorectal surgery on early ostomy complications and the risk factors associated with specific complications.

METHODS

A mandatory colorectal recording system for consecutive ostomy patients between 2012 and 2020 was reviewed retrospectively. Patient socio-demographics, ostomy-related variables, and early period ostomy complications were retrieved from the patient records. The chi-square test, t-test, analysis of variance (ANOVA), and logistic regression were used to analyze the data.

RESULTS

The study cohort included 872 patients. At least one or more complications developed in 573 (65.7%) patients, 356 (63.6%) in the emergency group, and 217 (69.6%) in the elective group. When comparing emergency surgery to elective surgery, necrosis (7.4% versus 3.4%, p = 0.009), mucocutaneous separation (37.2% versus 27.1%, p = 0.002), and bleeding (6.1% versus 2.1%, p = 0.003) were more prevalent. Peristomal irritant contact dermatitis (PICD) (37.3% versus 26%, p < 0.001) was more common in elective surgery. Risk factors for PICD were comorbidity (p = 0.003), malignant disease (p = 0.047), and loop ostomy (p < 0.001) in elective surgery; female sex (p = 0.025), neo-adjuvant therapy (p = 0.024), and ileostomy (p = 0.006) in emergency surgery. The height of the ostomy (less than 10 mm) was a modifiable risk factor for mucocutaneous separation in both elective surgery (p < 0.001) and emergency surgery (p = 0.045).

CONCLUSION

Early ostomy complications were more likely to occur after emergency colorectal surgery than in an elective setting. Patient- and ostomy-related risk factors for complications differed between elective and emergency surgeries.

Prediction of drinking water quality with machine learning models: A public health nursing approach

OBJECTIVE

The aim of this study is to use machine learning models to predict drinking water quality from a public health nursing approach.

DESIGN

Machine learning study.

SAMPLE

"Water Quality Dataset" was used in the study. The dataset contains physical and chemical measurements of water quality for 2400 different water bodies. The process consists of four stages: Data processing with Synthetic Minority Oversampling Technique, hyperparameter tuning with 10-fold cross-validation, modeling and comparative analysis. 80% of the dataset is allocated as training data and 20% as test data. ML models logistic regression, K-nearest neighbor, support vector machine, random forest, XGBoost, AdaBoost Classifier, Decision Tree algorithms were used for water quality prediction. Accuracy, precision, recall, F1 score and AUC performance metrics of ML models were compared. To evaluate the performance of the models, 10-fold cross-validation was used and a comparative analysis was performed. The p-values of the models were also compared.

RESULTS

N this study, where drinking water quality was predicted with seven different ML algorithms, it can be said that XGBoost and Random Forest are the best classification models in all performance metrics. There is a significant difference in all ML algorithms according to the p-value. The H0 hypothesis is accepted for these algorithms. According to the H0 hypothesis, there is no difference between actual values and predicted values.

CONCLUSION

In conclusion, the use of ML models in the prediction of drinking water quality can help nurses greatly improve access to clean water, a human right, be more knowledgeable about water quality, and protect the health of individuals.

Construction of an Early Alert System for Intradialytic Hypotension before Initiating Hemodialysis Based on Machine Learning

Introduction

Intradialytic hypotension (IDH) is prevalent and associated with high hospitalization and mortality rates. The purpose of this study was to explore the risk factors for IDH and use artificial intelligence to establish an early alert system before hemodialysis sessions to identify patients at high risk of IDH.

Materials and Methods

We obtained data on 314,534 hemodialysis sessions conducted at Sichuan Provincial People's Hospital from the renal disease treatment information system. IDH was defined as a systolic blood pressure drop ≥20 mm Hg, a mean arterial pressure drop ≥10 mm Hg during dialysis, or the occurrence of clinical hypotensive events requiring nursing intervention. After pre-processing, the data were randomly divided into training (80%) and testing (20%) sets. Four interpolation methods, three feature selection methods, and 18 machine learning algorithms were used to construct predictive models. The area under the receiver operating characteristic curve (AUC) was the main indicator for evaluating the performance of the models, while Shapley Additive ExPlanation was used to explain the contribution of each variable to the best predictive model.

Results

A total of 3,906 patients and 314,534 dialysis sessions were included, of which 142,237 cases showed IDH (incidence rate, 45.2%). Nineteen parameters were identified through artificial intelligence feature screening. They included age, pre-dialysis weight, dry weight, pre-dialysis blood pressure, heart rate, prescribed ultrafiltration, blood cell counts (neutrophil, lymphocyte, monocyte, eosinophil, lymphocyte, and platelet counts), hematocrit, serum calcium, creatinine, urea, glucose, and uric acid. Random forest, gradient boosting, and logistic regression were the three best models, and the AUCs were 0.812 (95% confidence interval [CI], 0.811-0.813), 0.748 (95% CI, 0.747-0.749), and 0.743 (95% CI, 0.742-0.744), respectively.

Conclusion

Our dialysis software-based artificial intelligence alert system can be used to predict IDH occurrence, enabling the initiation of relevant interventions.

Characteristics and statistical analysis of university accidents in China from 2017 to 2021

University accidents in China are frequent, and to find out the relationship pattern of factors influencing accidents, 248 university accidents occurring within 2017-2021 were studied using difference analysis (Independent-samples T-test, Mann-Whitney U test), logistic regression analysis, and diagnostic analysis of receiver operating characteristic curves. The results show: The variability in time, space, and qualifications was statistically significant (p < 0.05), and when the number of university safety policies ≥77 would significantly reduce the frequency of university accidents, with an influence strength value of 0.884 and a diagnostic accuracy of 79.8 %. In addition, the perpetrators, the time and the location of the accidents were usually undergraduate students, first semester of university, and economically developed and educationally rich provinces, respectively, with influence strength value and diagnostic accuracy of greater than 1 and 70%, respectively. Finally, specific suggestions are offered for the future prevention and reduction of accidents at the University based on the findings of the studies.

Medication Status and Related Factors in Essential Tremor Patients: A Cross-Sectional Study in China

INTRODUCTION

Essential tremor (ET) is one of the most common movement disorders. Oral drugs play a crucial role in treating ET, with various available options such as propranolol, primidone, and topiramate. However, the medication status and related factors among Chinese ET patients are unknown yet.

METHODS

This study used the baseline data from the National Survey of Essential Tremor Plus in China cohort. ET patients with information related to medication intake were included. Medication patients were defined as patients who were taking medication at the time of the survey. We further defined recommended medication users according to Chinese guideline recommendations and clinical knowledge. We used mean and standard deviation (SD), median and interquartile range (IQR), or frequencies and percentages when appropriate for descriptive analysis. We used multivariate logistic regression analyses to explore factors related to medication intake in all ET patients and in recommended medication users.

RESULTS

Of 1,153 included ET participants, 207 (18.0%) took medication. Arotinolol (115, 55.6%) and propranolol (63, 30.4%) were the top 2 used medicines. Patients with middle school education (odds ratio 0.57, 95% confidence interval 0.39-0.83), college or higher level education (0.46, 0.28-0.76), and late-onset ET (LO-ET) (0.38, 0.23-0.63) were less likely to take medication. Patients with intention tremor (1.90, 1.38-2.62), every 10-unit increase in age (1.10, 1.00-1.21), Tremor Research Group Essential Tremor Rating Assessment Scale (TETRAS) Part 1 (1.63, 1.37-1.93), and TETRAS Part 2 (1.81, 1.48-2.22) were more likely to take medication. Among 332 recommended medication users, only 104 (31.3%) took medicine. The associations of LO-ET (0.36, 0.17-0.75), intention tremor (2.27, 1.35-3.81), TETRAS Part 1 (1.52, 1.09-2.13), and TETRAS Part 2 (1.59, 1.15-2.20) with medication were similar to all ET patients.

CONCLUSION

The proportion of medication intake is low among both all ET patients and recommended medication users. The top 2 commonly used medications among all ET patients are arotinolol and propranolol. Influencing factors of medication intake are different between all ET patients and recommended medication users. Clinicians are suggested to provide counseling and education on ET medication to promote medication intake.

Predicting 7-day unplanned readmission in elderly patients with coronary heart disease using machine learning

Background

Short-term unplanned readmission is always neglected, especially for elderly patients with coronary heart disease (CHD). However, tools to predict unplanned readmission are lacking. This study aimed to establish the most effective predictive model for the unplanned 7-day readmission in elderly CHD patients using machine learning (ML) algorithms.

Methods

The detailed clinical data of elderly CHD patients were collected retrospectively. Five ML algorithms, including extreme gradient boosting (XGB), random forest, multilayer perceptron, categorical boosting, and logistic regression, were used to establish predictive models. We used the area under the receiver operating characteristic curve (AUC), accuracy, precision, recall, the F1 value, the Brier score, the area under the precision-recall curve (AUPRC), and the calibration curve to evaluate the performance of ML models. The SHapley Additive exPlanations (SHAP) value was used to interpret the best model.

Results

The final study included 834 elderly CHD patients, whose average age was 73.5 ± 8.4 years, among whom 426 (51.08%) were men and 139 had 7-day unplanned readmissions. The XGB model had the best performance, exhibiting the highest AUC (0.9729), accuracy (0.9173), F1 value (0.9134), and AUPRC (0.9766). The Brier score of the XGB model was 0.08. The calibration curve of the XGB model showed good performance. The SHAP method showed that fracture, hypertension, length of stay, aspirin, and D-dimer were the most important indicators for the risk of 7-day unplanned readmissions. The top 10 variables were used to build a compact XGB, which also showed good predictive performance.

Conclusions

In this study, five ML algorithms were used to predict 7-day unplanned readmissions in elderly patients with CHD. The XGB model had the best predictive performance and potential clinical application perspective.

Medical emergency department triage data processing using a machine-learning solution

Over the years, artificial intelligence has demonstrated its ability to overcome many challenges in our day-to-day life. The evolution of it inquired more studies about Machine Learning possible solutions for different domains, including health care. The increasing demand for artificial intelligence solutions has brought accessibility to loads of data, including clinical data. The availability of medical records facilitates new opportunities to explore Machine Learning models and their abilities to process a significant amount of data and to identify patterns with the purpose of solving a medical problem. Understanding the applicability of artificial intelligence on this type of data has to be a compelling aim for emergency medicine clinicians. This paper focuses on the general clinical problem of the complex correlation between medical records and later diagnosis and, especially, on the process of emergency department triage which uses the Emergency Severity Index (ESI) as triage protocol. This study presents a comparison between three different Machine Learning models, such as Logistic Regression, Random Forest Tree and NN-Sequentail, with the purpose of classifying patients with an emergency code. We conducted four experiments because of imbalanced data. A web-based application was developed to improve the triage process after our theoretical and exploratory results. Overall, in all experiments, the NN-Sequential model had better results, having, in the first experiment, a ROC-AUC score for each ESI emergency code of: 0.59%, 0.76%, 0.71%, 0.78% 0.64%. After applying methods to balance the data, the model yielded a ROC-AUC score for each emergency code of 0.72%, 0.75%, 0.69%, 0.74%, 0.78%. In the last experiment consisting of a three-class classification problem, the NN-Sequential and Random Forest Tree models had similar metric outcomes, and the NN-Sequential algorithm had a ROC-AUC score for each emergency code of: 0.76%, 0.72%, 0.84%. Without any doubt, our research results presented in this paper endorse this tremendous curiosity in Machine Learning applications to enrich aspects of emergency medical care by applying specific methods for processing both medical data and medical records.

Performance evaluation of machine learning models on large dataset of android applications reviews

With an ever-increasing number of mobile users, the development of mobile applications (apps) has become a potential market during the past decade. Billions of users download mobile apps for divergent use from Google Play Store, fulfill tasks and leave comments about their experience. Such reviews are replete with a variety of feedback that serves as a guide for the improvement of existing apps and intuition for novel mobile apps. However, application reviews are challenging and very broad to approach. Such reviews, when segregated into different classes guide the user in the selection of suitable apps. This study proposes a framework for analyzing the sentiment of reviews for apps of eight different categories like shopping, sports, casual, etc. A large dataset is scrapped comprising 251661 user reviews with the help of 'Regular Expression' and 'Beautiful Soup'. The framework follows the use of different machine learning models along with the term frequency-inverse document frequency (TF-IDF) for feature extraction. Extensive experiments are performed using preprocessing steps, as well as, the stats feature of app reviews to evaluate the performance of the models. Results indicate that combining the stats feature with TF-IDF shows better performance and the support vector machine obtains the highest accuracy. Experimental results can potentially be used by other researchers to select appropriate models for the analysis of app reviews. In addition, the provided dataset is large, diverse, and balanced with eight categories and 59 app reviews and provides the opportunity to analyze reviews using state-of-the-art approaches.

Machine learning models for predicting survival in patients with ampullary adenocarcinoma

Objective

The aim of this study was to predict the long-term survival probability of patients with ampullary adenocarcinoma (AAC), which would provide a theoretical basis for the long-term care of these patients.

Methods

Data on patients with AAC during 2004–2015 were obtained from the Surveillance, Epidemiology, and End Results database, which were split at a 7:3 ratio into two independent cohorts: training and testing cohorts. Differences in survival between the two groups were tested using the Kaplan–Meier estimator and log-rank test methods. We constructed six survival analysis methods: the American Joint Committee on Cancer TNM stage, Cox Proportional Hazards regression, CoxTime, DeepSurv, XGBoost Survival Embeddings, and Random Survival Forest. The performances of these models were evaluated using the C-index, receiver operating characteristic (ROC), and calibration curves.

Results

This study included 2,935 patients with AAC. Univariate Cox regression analyses of the training cohort indicated that race, marital status at diagnosis, scope of regional lymph node surgery, tumor grade, summary stage, American Joint Committee on Cancer stage, TNM stage T, and TNM stage N were important factors affecting survival (P ​< ​0.05). The results of the C-index indicated that DeepSurv performed the best among the six models, with the highest C-index of 0.731. The areas under the ROC curves of the DeepSurv model at the 1-year, 3-year, 5-year, and 10-year time points were 0.823, 0.786, 0.803, and 0.813, respectively. The calibration curve indicated that DeepSurv performed well, with good calibration.

Conclusions

Machine learning models such as DeepSurv have a stronger performance in the survival analysis of patients with AAC.

Coronary Artery Disease Detection Model Based on Class Balancing Methods and LightGBM Algorithm

Coronary artery disease (CAD) is a disease with high mortality and disability. By 2019, there were 197 million CAD patients in the world. Additionally, the number of disability-adjusted life years (DALYs) owing to CAD reached 182 million. It is widely known that the early and accurate diagnosis of CAD is the most efficient method to reduce the damage of CAD. In medical practice, coronary angiography is considered to be the most reliable basis for CAD diagnosis. However, unfortunately, due to the limitation of inspection equipment and expert resources, many low- and middle-income countries do not have the ability to perform coronary angiography. This has led to a large loss of life and medical burden. Therefore, many researchers expect to realize the accurate diagnosis of CAD based on conventional medical examination data with the help of machine learning and data mining technology. The goal of this study is to propose a model for early, accurate and rapid detection of CAD based on common medical test data. This model took the classical logistic regression algorithm, which is the most commonly used in medical model research as the classifier. The advantages of feature selection and feature combination of tree models were used to solve the problem of manual feature engineering in logical regression. At the same time, in order to solve the class imbalance problem in Z-Alizadeh Sani dataset, five different class balancing methods were applied to balance the dataset. In addition, according to the characteristics of the dataset, we also adopted appropriate preprocessing methods. These methods significantly improved the classification performance of logistic regression classifier in terms of accuracy, recall, precision, F1 score, specificity and AUC when used for CAD detection. The best accuracy, recall, F1 score, precision, specificity and AUC were 94.7%, 94.8%, 94.8%, 95.3%, 94.5% and 0.98, respectively. Experiments and results have confirmed that, according to common medical examination data, our proposed model can accurately identify CAD patients in the early stage of CAD. Our proposed model can be used to help clinicians make diagnostic decisions in clinical practice.