Deep Learning-Based Available and Common Clinical-Related Feature Variables Robustly Predict Survival in Community-Acquired Pneumonia

The use of machine learning based models to predict the severity of community acquired pneumonia in hospitalised patients: A systematic review

Background

Community acquired pneumonia (CAP) is a common cause of hospital admission. CAP carries significant risk of adverse outcomes including organ dysfunction, intensive care unit (ICU) admission and death. Earlier admission to ICU for those with severe CAP is associated with better outcomes. Traditional prediction models are used in clinical practice to predict the severity of CAP. However, accuracy of predicting severity may be improved by using machine learning (ML) based models with added advantages of automation and speed. This systematic review evaluates the evidence base of ML-prediction tools in predicting CAP severity.

Methods

MEDLINE, EMBASE and PubMed were systematically searched for studies that used ML-based models to predict mortality and/or ICU admission in CAP patients, where a performance metric was reported.

Results

11 papers including a total of 351,365 CAP patients were included. All papers predicted severity and four predicted ICU admission. Most papers applied multiple ML algorithms to datasets and derived area under the receiver operator characteristic curve (AUROC) of 0.98 at best performance and 0.57 at worst, with a mixed performance against traditional prediction tools.

Conclusion

Although ML models showed good performance at predicting CAP severity, the variables selected for inclusion in each model varied significantly which limited comparisons between models and there was a lack of reproducible data, limiting validity. Future research should focus on validating ML predication models in multiple cohorts to derive robust, reproducible performance measures, and to demonstrate a benefit in terms of patient outcomes and resource use.

Machine learning-based model for predicting all-cause mortality in severe pneumonia

BACKGROUND

Severe pneumonia has a poor prognosis and high mortality. Current severity scores such as Acute Physiology and Chronic Health Evaluation (APACHE-II) and Sequential Organ Failure Assessment (SOFA), have limited ability to help clinicians in classification and management decisions. The goal of this study was to analyse the clinical characteristics of severe pneumonia and develop a machine learning-based mortality-prediction model for patients with severe pneumonia.

METHODS

Consecutive patients with severe pneumonia between 2013 and 2022 admitted to Beijing Chaoyang Hospital affiliated with Capital Medical University were included. In-hospital all-cause mortality was the outcome of this study. We performed a retrospective analysis of the cohort, stratifying patients into survival and non-survival groups, using mainstream machine learning algorithms (light gradient boosting machine, support vector classifier and random forest). We aimed to construct a mortality-prediction model for patients with severe pneumonia based on their accessible clinical and laboratory data. The discriminative ability was evaluated using the area under the receiver operating characteristic curve (AUC). The calibration curve was used to assess the fit goodness of the model, and decision curve analysis was performed to quantify clinical utility. By means of logistic regression, independent risk factors for death in severe pneumonia were figured out to provide an important basis for clinical decision-making.

RESULTS

A total of 875 patients were included in the development and validation cohorts, with the in-hospital mortality rate of 14.6%. The AUC of the model in the internal validation set was 0.8779 (95% CI, 0.738 to 0.974), showing a competitive discrimination ability that outperformed those of traditional clinical scoring systems, that is, APACHE-II, SOFA, CURB-65 (confusion, urea, respiratory rate, blood pressure, age ≥65 years), Pneumonia Severity Index. The calibration curve showed that the in-hospital mortality in severe pneumonia predicted by the model fit reasonably with the actual hospital mortality. In addition, the decision curve showed that the net clinical benefit was positive in both training and validation sets of hospitalised patients with severe pneumonia. Based on ensemble machine learning algorithms and logistic regression technique, the level of ferritin, lactic acid, blood urea nitrogen, creatine kinase, eosinophil and the requirement of vasopressors were identified as top independent predictors of in-hospital mortality with severe pneumonia.

CONCLUSION

A robust clinical model for predicting the risk of in-hospital mortality after severe pneumonia was successfully developed using machine learning techniques. The performance of this model demonstrates the effectiveness of these techniques in creating accurate predictive models, and the use of this model has the potential to greatly assist patients and clinical doctors in making well-informed decisions regarding patient care.

Revolutionizing oncology care: pioneering AI models to foresee pneumonia-related mortality

BACKGROUND

Pneumonia is a leading cause of morbidity and mortality among patients with cancer, and survival time is a primary concern. Despite their importance, there is a dearth of accurate predictive models in clinical settings. This study aimed to determine the incidence of pneumonia as a cause of death in patients with cancer, analyze trends and risk factors associated with mortality, and develop corresponding predictive models.

METHODS

We included 26,938 cancer patients in the United States who died from pneumonia between 1973 and 2020, as identified through the Surveillance, Epidemiology, and End Results (SEER) program. Cox regression analysis was used to ascertain the prognostic factors for patients with cancer. The CatBoost model was constructed to predict survival rates via a cross-validation method. Additionally, our model was validated using a cohort of cancer patients from our institution and deployed via a free-access software interface.

RESULTS

The most common cancers resulting in pneumonia-related deaths were prostate (n=7300) and breast (n=5107) cancers, followed by lung and bronchus (n=2839) cancers. The top four cancer systems were digestive (n=5882), endocrine (n=5242), urologic (n=5198), and hematologic (n=3104) systems. The majority of patients were over 70 years old (57.7%), and 54.4% were male. Our CatBoost model demonstrated high precision and accuracy, outperforming other models in predicting the survival of cancer patients with pneumonia (6-month AUC=0.8384,1-year AUC=0.8255,2-year AUC=0.8039, and 3-year AUC=0.7939). The models also revealed robust performance in an external independent dataset (6-month AUC=0.689; 1-year AUC=0.838; 2-year AUC=0.834; and 3-year AUC=0.828). According to the SHAP explanation analysis, the top five factors affecting prognosis were surgery, stage, age, site, and sex; surgery was the most significant factor in both the short-term (6 months and 1 year) and long-term (2 years and 3 years) prognostic models; surgery improved patient prognosis for digestive and endocrine tumor sites with respect to both short- and long-term outcomes but decreased the prognosis of urological and hematologic tumors.

CONCLUSION

Pneumonia remains a major cause of illness and death in patients with cancer, particularly those with digestive system cancers. The early identification of risk factors and timely intervention may help mitigate the negative impact on patients' quality of life and prognosis, improve outcomes, and prevent early deaths caused by infections, which are often preventable.

Advancing risk factor identification for pediatric lobar pneumonia: the promise of machine learning technologies

Background

Community-acquired pneumonia (CAP) is a prevalent pediatric condition, and lobar pneumonia (LP) is considered a severe subtype. Early identification of LP is crucial for appropriate management. This study aimed to develop and compare machine learning models to predict LP in children with CAP.

Methods

A total of 25 clinical and laboratory variables were collected. Missing data (<2%) were imputed, and the dataset was split into training (60%) and validation (40%) sets. Univariable logistic regression and Boruta feature selection were used to identify significant predictors. Four machine learning algorithms-Logistic Regression (LR), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), and Decision Tree (DT)-were compared using area under the curve (AUC), balanced accuracy, sensitivity, specificity, and F1 score. SHAP analysis was performed to interpret the best-performing model.

Results

A total of 278 patients with CAP were included in this study, of whom 65 were diagnosed with LP. The XGBoost model demonstrated the best performance with an AUC of 0.880 (95% CI: 0.807-0.934) in the training set and 0.746 (95% CI: 0.664-0.843) in the validation set. SHAP analysis identified age, CRP, CD64 index, lymphocyte percentage, and ALB as the top five predictive factors.

Conclusion

The XGBoost model showed superior performance in predicting LP in children with CAP. The model enabled early diagnosis and risk assessment of LP, thereby facilitating appropriate clinical decision-making.

Deep Learning Models to Predict Fatal Pneumonia Using Chest X-Ray Images

Background and Aims. Chest X-ray (CXR) is indispensable to the assessment of severity, diagnosis, and management of pneumonia. Deep learning is an artificial intelligence (AI) technology that has been applied to the interpretation of medical images. This study investigated the feasibility of classifying fatal pneumonia based on CXR images using deep learning models on publicly available platforms. Methods. CXR images of patients with pneumonia at diagnosis were labeled as fatal or nonfatal based on medical records. We applied CXR images from 1031 patients with nonfatal pneumonia and 243 patients with fatal pneumonia for training and self-evaluation of the deep learning models. All labeled CXR images were randomly allocated to the training, validation, and test datasets of deep learning models. Data augmentation techniques were not used in this study. We created two deep learning models using two publicly available platforms. Results. The first model showed an area under the precision-recall curve of 0.929 with a sensitivity of 50.0% and a specificity of 92.4% for classifying fatal pneumonia. We evaluated the performance of our deep learning models using sensitivity, specificity, PPV, negative predictive value (NPV), accuracy, and F1 score. Using the external validation test dataset of 100 CXR images, the sensitivity, specificity, accuracy, and F1 score were 68.0%, 86.0%, 77.0%, and 74.7%, respectively. In the original dataset, the performance of the second model showed a sensitivity, specificity, and accuracy of 39.6%, 92.8%, and 82.7%, respectively, while external validation showed values of 38.0%, 92.0%, and 65.0%, respectively. The F1 score was 52.1%. These results were comparable to those obtained by respiratory physicians and residents. Conclusions. The deep learning models yielded good accuracy in classifying fatal pneumonia. By further improving the performance, AI could assist physicians in the severity assessment of patients with pneumonia.

Incorporation of Suppression of Tumorigenicity 2 into Random Survival Forests for Enhancing Prediction of Short-Term Prognosis in Community-ACQUIRED Pneumonia

(1) Background: Biomarker and model development can help physicians adjust the management of patients with community-acquired pneumonia (CAP) by screening for inpatients with a low probability of cure early in their admission; (2) Methods: We conducted a 30-day cohort study of newly admitted adult CAP patients over 20 years of age. Prognosis models to predict the short-term prognosis were developed using random survival forest (RSF) method; (3) Results: A total of 247 adult CAP patients were studied and 208 (84.21%) of them reached clinical stability within 30 days. The soluble form of suppression of tumorigenicity-2 (sST2) was an independent predictor of clinical stability and the addition of sST2 to the prognosis model could improve the performance of the prognosis model. The C-index of the RSF model for predicting clinical stability was 0.8342 (95% CI, 0.8086–0.8598), which is higher than 0.7181 (95% CI, 0.6933–0.7429) of CURB 65 score, 0.8025 (95% CI, 0.7776–8274) of PSI score, and 0.8214 (95% CI, 0.8080–0.8348) of cox regression. In addition, the RSF model was associated with adverse clinical events during hospitalization, ICU admissions, and short-term mortality; (4) Conclusions: The RSF model by incorporating sST2 was more accurate than traditional methods in assessing the short-term prognosis of CAP patients.

Performance of Machine Learning Algorithms for Predicting Adverse Outcomes in Community-Acquired Pneumonia

Background: The ability to assess adverse outcomes in patients with community-acquired pneumonia (CAP) could improve clinical decision-making to enhance clinical practice, but the studies remain insufficient, and similarly, few machine learning (ML) models have been developed.

Objective: We aimed to explore the effectiveness of predicting adverse outcomes in CAP through ML models.

Methods: A total of 2,302 adults with CAP who were prospectively recruited between January 2012 and March 2015 across three cities in South America were extracted from DryadData. After a 70:30 training set: test set split of the data, nine ML algorithms were executed and their diagnostic accuracy was measured mainly by the area under the curve (AUC). The nine ML algorithms included decision trees, random forests, extreme gradient boosting (XGBoost), support vector machines, Naïve Bayes, K-nearest neighbors, ridge regression, logistic regression without regularization, and neural networks. The adverse outcomes included hospital admission, mortality, ICU admission, and one-year post-enrollment status.

Results: The XGBoost algorithm had the best performance in predicting hospital admission. Its AUC reached 0.921, and accuracy, precision, recall, and F1-score were better than those of other models. In the prediction of ICU admission, a model trained with the XGBoost algorithm showed the best performance with AUC 0.801. XGBoost algorithm also did a good job at predicting one-year post-enrollment status. The results of AUC, accuracy, precision, recall, and F1-score indicated the algorithm had high accuracy and precision. In addition, the best performance was seen by the neural network algorithm when predicting death (AUC 0.831).

Conclusions: ML algorithms, particularly the XGBoost algorithm, were feasible and effective in predicting adverse outcomes of CAP patients. The ML models based on available common clinical features had great potential to guide individual treatment and subsequent clinical decisions.