Using machine learning in prediction of ICU admission, mortality, and length of stay in the early stage of admission of COVID-19 patients

Predictive Modeling of COVID-19 Intensive Care Unit Patient Flows and Nursing Complexity: A Monte Carlo Simulation Study

This study aimed to develop a Monte Carlo simulation model to forecast the number of ICU beds needed for COVID-19 patients and the subsequent nursing complexity in a French teaching hospital during the first and second pandemic outbreaks. The model used patient data from March 2020 to September 2021, including age, sex, ICU length of stay, and number of patients on mechanical ventilation or extracorporeal membrane oxygenation. Nursing complexity was assessed using a simple scale with three levels based on patient status. The simulation was performed 1000 times to generate a scenario, and the mean outcome was compared with the observed outcome. The model also allowed for a 7-day forecast of ICU occupancy. The simulation output had a good fit with the actual data, with an R2 of 0.998 and a root mean square error of 0.22. The study demonstrated the usefulness of the Monte Carlo simulation model for predicting the demand for ICU beds and could help optimize resource allocation during a pandemic. The model's extrinsic validity was confirmed using open data from the French Public Health Authority. This study provides a valuable tool for healthcare systems to anticipate and manage surges in ICU demand during pandemics.

PSO-XnB: a proposed model for predicting hospital stay of CAD patients

Coronary artery disease poses a significant challenge in decision-making when predicting the length of stay for a hospitalized patient. This study presents a predictive model-a Particle Swarm Optimized-Enhanced NeuroBoost-that combines the deep autoencoder with an eXtreme gradient boosting model optimized using particle swarm optimization. The model uses a fuzzy set of rules to categorize the length of stay into four distinct classes, followed by data preparation and preprocessing. In this study, the dimensionality of the data is reduced using deep neural autoencoders. The reconstructed data obtained from autoencoders is given as input to an eXtreme gradient boosting model. Finally, the model is tuned with particle swarm optimization to obtain optimal hyperparameters. With the proposed technique, the model achieved superior performance with an overall accuracy of 98.8% compared to traditional ensemble models and past research works. The model also scored highest in other metrics such as precision, recall, and particularly F1 scores for all categories of hospital stay. These scores validate the suitability of our proposed model in medical healthcare applications.

Machine learning algorithms to uncover risk factors of breast cancer: insights from a large case-control study

Introduction

This large case-control study explored the application of machine learning models to identify risk factors for primary invasive incident breast cancer (BC) in the Iranian population. This study serves as a bridge toward improved BC prevention, early detection, and management through the identification of modifiable and unmodifiable risk factors.

Methods

The dataset includes 1,009 cases and 1,009 controls, with comprehensive data on lifestyle, health-behavior, reproductive and sociodemographic factors. Different machine learning models, namely Random Forest (RF), Neural Networks (NN), Bootstrap Aggregating Classification and Regression Trees (Bagged CART), and Extreme Gradient Boosting Tree (XGBoost), were employed to analyze the data.

Results

The findings highlight the significance of a chest X-ray history, deliberate weight loss, abortion history, and post-menopausal status as predictors. Factors such as second-hand smoking, lower education, menarche age (>14), occupation (employed), first delivery age (18-23), and breastfeeding duration (>42 months) were also identified as important predictors in multiple models. The RF model exhibited the highest Area Under the Curve (AUC) value of 0.9, as indicated by the Receiver Operating Characteristic (ROC) curve. Following closely was the Bagged CART model with an AUC of 0.89, while the XGBoost model achieved a slightly lower AUC of 0.78. In contrast, the NN model demonstrated the lowest AUC of 0.74. On the other hand, the RF model achieved an accuracy of 83.9% and a Kappa coefficient of 67.8% and the XGBoost, achieved a lower accuracy of 82.5% and a lower Kappa coefficient of 0.6.

Conclusion

This study could be beneficial for targeted preventive measures according to the main risk factors for BC among high-risk women.

Predicting intensive care need for COVID-19 patients using deep learning on chest radiography

Purpose

Image-based prediction of coronavirus disease 2019 (COVID-19) severity and resource needs can be an important means to address the COVID-19 pandemic. In this study, we propose an artificial intelligence/machine learning (AI/ML) COVID-19 prognosis method to predict patients' needs for intensive care by analyzing chest X-ray radiography (CXR) images using deep learning.

Approach

The dataset consisted of 8357 CXR exams from 5046 COVID-19-positive patients as confirmed by reverse transcription polymerase chain reaction (RT-PCR) tests for the SARS-CoV-2 virus with a training/validation/test split of 64%/16%/20% on a by patient level. Our model involved a DenseNet121 network with a sequential transfer learning technique employed to train on a sequence of gradually more specific and complex tasks: (1) fine-tuning a model pretrained on ImageNet using a previously established CXR dataset with a broad spectrum of pathologies; (2) refining on another established dataset to detect pneumonia; and (3) fine-tuning using our in-house training/validation datasets to predict patients' needs for intensive care within 24, 48, 72, and 96 h following the CXR exams. The classification performances were evaluated on our independent test set (CXR exams of 1048 patients) using the area under the receiver operating characteristic curve (AUC) as the figure of merit in the task of distinguishing between those COVID-19-positive patients who required intensive care following the imaging exam and those who did not.

Results

Our proposed AI/ML model achieved an AUC (95% confidence interval) of 0.78 (0.74, 0.81) when predicting the need for intensive care 24 h in advance, and at least 0.76 (0.73, 0.80) for 48 h or more in advance using predictions based on the AI prognostic marker derived from CXR images.

Conclusions

This AI/ML prediction model for patients' needs for intensive care has the potential to support both clinical decision-making and resource management.

TT@MHA: A Machine Learning-based Webpage Tool for Discriminating Thalassemia Trait from Microcytic Hypochromic Anemia Patients

BACKGROUND

Iron deficiency anemia (IDA) and thalassemia trait (TT) are the most common causes of microcytic hypochromic anemia (MHA) and are endemic in lower resource settings and rural areas with poor medical infrastructure. Accurate discrimination between IDA and TT is an essential issue for MHA patients. Although various discriminant formulas have been reported, distinguishing between IDA and TT is still a challenging problem due to the diversity of anemic populations.

METHODS

We retrospectively collected laboratory data from 798 MHA patients. High proportions of α-TT (43.33%) and TT concomitant with IDA (TT&IDA) patients (14.04%) were found among TT patients. Five machine learning (ML) approaches, including Liner SVC (L-SVC), support vector machine learning (SVM), Extreme gradient boosting (XGB), Logistic Regression (LR), and Random Forest (RF), were applied to develop a discriminant model. Performance was assessed and compared with six existing discriminant formulas.

RESULTS

The RF model was chosen as the discriminant algorithm, namely TT@MHA. TT@MHA was tested in an interlaboratory cohort with a sensitivity, specificity, accuracy, and AUC of 91.91%, 91.00%, 91.53%, and 0.942, respectively. A webpage tool of TT@MHA (https://dxonline.deepwise.com/prediction/index.html?baseUrl=%2Fapi%2F&id=26408&topicName=undefined&from=share&platformType=wisdom) was developed to facilitate the healthcare providers in rural areas.

CONCLUSION

The ML-based TT@MHA algorithm, with high sensitivity and specificity, could help discriminate TT patients from MHA patients, especially in populations with high proportions of α-TT patients and TT&IDA patients. Moreover, a user-friendly webpage tool for TT@MHA could facilitate healthcare providers in rural areas where advanced technologies are not accessible.