Computerized Mortality Prediction for Community-acquired Pneumonia at 117 Veterans Affairs Medical Centers

Jones, Barbara E.; Jin, Ying; Nevers, McKenna; Alba, Patrick R.; He, Tao; Patterson, Olga V.; Jones, Makoto; Stevens, Vanessa; Shen, Jincheng; Humpherys, Jeffrey; Peterson, Kelly; Gundlapalli, Adi V.; Weir, Charlene R.; Dean, Nathan C.; Fine, Michael J.; Samore, Matthew; Greene, Tom

doi:10.1513/annalsats.202011-1372oc

Cited by 9 publications

(13 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Models that highlight vital signs and laboratory tests may be more valid in alerting healthcare workers to potentially modifiable organ failure than models that rely heavily on comorbidities and demographic characteristics ( Jones et al, 2021 ). Based on this spirit, our study established the accuracy of computerized prediction and revealed that the XGBoost algorithm was reliable.…”

Section: Discussionmentioning

confidence: 99%

“…In fact, a model is a summarization of the collective clinical experience of events that happen in patients with similar clinical characteristics ( Weick and Roberts, 1993 ). The value of prediction is that it places the clinical features of a new patient in the context of that clinical experience, providing a common basis for communication among clinicians, especially for those unfamiliar with each other ( Jones et al, 2021 ). Credible models are essential to providing reliable, efficient, and equitable health care, and the models we have built are paving the way for that process.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

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

Guo

Chu

et al. 2022

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

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

Guo

Chu

et al. 2022

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

show abstract

“…From our perspective, limitations especially regarding applicability in the study by Hu et al arise in view of the small case number and choice of a large variable set (76 variables). In a recently published US study, ML algorithms were applied using PSI-specific and additional variables derived from electronic health records (EHR) of 297,498 CAP patients [14]. The ML methods outperformed LR among different models in predicting 30-day mortality (AUC range 0.83-0.87).…”

Section: Existing Prediction Models and Comparisonmentioning

confidence: 99%

“…With respect to non-COVID SARI patients, several approaches for mortality prediction in patients with pneumonia in general and specifically with influenza-caused pneumonia were also reported. The methodology of those studies included different ML concepts [13][14][15][16] as well as logistic regression (LR) [14,17,18]. The authors mostly focused on developing individual risk stratification and mortality prediction models for assessing the patient's individual risk at the time point of hospital admission.…”

Section: Introductionmentioning

confidence: 99%

Machine learning-derived prediction of in-hospital mortality in patients with severe acute respiratory infection: analysis of claims data from the German-wide Helios hospital network

et al. 2022

View full text Add to dashboard Cite

Background Severe acute respiratory infections (SARI) are the most common infectious causes of death. Previous work regarding mortality prediction models for SARI using machine learning (ML) algorithms that can be useful for both individual risk stratification and quality of care assessment is scarce. We aimed to develop reliable models for mortality prediction in SARI patients utilizing ML algorithms and compare its performances with a classic regression analysis approach. Methods Administrative data (dataset randomly split 75%/25% for model training/testing) from years 2016–2019 of 86 German Helios hospitals was retrospectively analyzed. Inpatient SARI cases were defined by ICD-codes J09-J22. Three ML algorithms were evaluated and its performance compared to generalized linear models (GLM) by computing receiver operating characteristic area under the curve (AUC) and area under the precision-recall curve (AUPRC). Results The dataset contained 241,988 inpatient SARI cases (75 years or older: 49%; male 56.2%). In-hospital mortality was 11.6%. AUC and AUPRC in the testing dataset were 0.83 and 0.372 for GLM, 0.831 and 0.384 for random forest (RF), 0.834 and 0.382 for single layer neural network (NNET) and 0.834 and 0.389 for extreme gradient boosting (XGBoost). Statistical comparison of ROC AUCs revealed a better performance of NNET and XGBoost as compared to GLM. Conclusion ML algorithms for predicting in-hospital mortality were trained and tested on a large real-world administrative dataset of SARI patients and showed good discriminatory performances. Broad application of our models in clinical routine practice can contribute to patients’ risk assessment and quality management.

show abstract

“…Cooper et al constructed 11 statistical and machine learning models that predict dire outcomes for CAP patients (such as mortality or severe clinical complications) and discovered an innovative neural network learning method that induced a model using Multitask and Learning along with Rank-prop learning (MTLR) with the largest ROC area (Cooper et al, 2005). Models that highlight vital signs and laboratory tests may be more valid in alerting healthcare workers to potentially modifiable organ failure than models that rely heavily on comorbidities and demographic characteristics (Jones et al, 2021). Based on this spirit, our study established the accuracy of computerized prediction and revealed that the XGBoost algorithm was reliable.…”

Section: Discussionmentioning

confidence: 99%

Table1.DOCX

View full text Add to dashboard Cite

Computerized Mortality Prediction for Community-acquired Pneumonia at 117 Veterans Affairs Medical Centers

Cited by 9 publications

References 44 publications

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

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

Machine learning-derived prediction of in-hospital mortality in patients with severe acute respiratory infection: analysis of claims data from the German-wide Helios hospital network

Table1.DOCX

Contact Info

Product

Resources

About