Predicting prognosis in COVID-19 patients using machine learning and readily available clinical data

Predicting intubation for intensive care units patients: A deep learning approach to improve patient management

OBJECTIVE

For patients in the Intensive Care Unit (ICU), the timing of intubation has a significant association with patients' outcomes. However, accurate prediction of the timing of intubation remains an unsolved challenge due to the noisy, sparse, heterogeneous, and unbalanced nature of ICU data. In this study, our objective is to develop a workflow for pre-processing ICU data and to develop a customized deep learning model to predict the need for intubation.

METHODS

To improve the prediction accuracy, we transform the intubation prediction task into a time series classification task. We carefully design a sequence of data pre-processing steps to handle the multimodal noisy data. Firstly, we discretize the sequential data and address missing data using interpolation. Next, we employ a sampling strategy to address data imbalance and standardize the data to facilitate faster model convergence. Furthermore, we employ the feature selection technique and propose an ensemble model to combine features learned by different deep learning models.

RESULTS

The performance is evaluated on Medical Information Mart for Intensive Care (MIMIC)-III, an ICU dataset. Our proposed Deep Feature Fusion method achieves an area under the curve (AUC) of the receiver operating curve (ROC) of 0.8953, surpassing the performance of other deep learning and traditional machine learning models.

CONCLUSION

Our proposed Deep Feature Fusion method proves to be a viable approach for predicting intubation and outperforms other deep learning and classical machine learning models. The study confirms that high-frequency time-varying indicators, particularly Mean Blood Pressure (MeanBP) and peripheral oxygen saturation (SpO2), are significant risk factors for predicting intubation.

Identification of Predictors for Clinical Deterioration in Patients With COVID-19 via Electronic Nursing Records: Retrospective Observational Study

BACKGROUND

Few studies have used standardized nursing records with Systematized Nomenclature of Medicine-Clinical Terms (SNOMED CT) to identify predictors of clinical deterioration.

OBJECTIVE

This study aims to standardize the nursing documentation records of patients with COVID-19 using SNOMED CT and identify predictive factors of clinical deterioration in patients with COVID-19 via standardized nursing records.

METHODS

In this study, 57,558 nursing statements from 226 patients with COVID-19 were analyzed. Among these, 45,852 statements were from 207 patients in the stable (control) group and 11,706 from 19 patients in the exacerbated (case) group who were transferred to the intensive care unit within 7 days. The data were collected between December 2019 and June 2022. These nursing statements were standardized using the SNOMED CT International Edition released on November 30, 2022. The 260 unique nursing statements that accounted for the top 90% of 57,558 statements were selected as the mapping source and mapped into SNOMED CT concepts based on their meaning by 2 experts with more than 5 years of SNOMED CT mapping experience. To identify the main features of nursing statements associated with the exacerbation of patient condition, random forest algorithms were used, and optimal hyperparameters were selected for nursing problems or outcomes and nursing procedure-related statements. Additionally, logistic regression analysis was conducted to identify features that determine clinical deterioration in patients with COVID-19.

RESULTS

All nursing statements were semantically mapped to SNOMED CT concepts for "clinical finding," "situation with explicit context," and "procedure" hierarchies. The interrater reliability of the mapping results was 87.7%. The most important features calculated by random forest were "oxygen saturation below reference range," "dyspnea," "tachypnea," and "cough" in "clinical finding," and "oxygen therapy," "pulse oximetry monitoring," "temperature taking," "notification of physician," and "education about isolation for infection control" in "procedure." Among these, "dyspnea" and "inadequate food diet" in "clinical finding" increased clinical deterioration risk (dyspnea: odds ratio [OR] 5.99, 95% CI 2.25-20.29; inadequate food diet: OR 10.0, 95% CI 2.71-40.84), and "oxygen therapy" and "notification of physician" in "procedure" also increased the risk of clinical deterioration in patients with COVID-19 (oxygen therapy: OR 1.89, 95% CI 1.25-3.05; notification of physician: OR 1.72, 95% CI 1.02-2.97).

CONCLUSIONS

The study used SNOMED CT to express and standardize nursing statements. Further, it revealed the importance of standardized nursing records as predictive variables for clinical deterioration in patients.

Retrospective Post-Hospitalisation COVID-19 Mortality Risk Assessment of Patients in South Africa

Background: This study explores the determinants impacting the mortality risk of COVID-19 patients following hospitalisation within South Africa's Limpopo province. Methods: Utilising a dataset comprising 388 patients, the investigation employs a frailty regression model to evaluate the influence of diverse characteristics on mortality outcomes, contrasting its performance against other parametric models based on loglikelihood measures. Results: The findings underscore diabetes and hypertension as notable contributors to heightened mortality rates, underscoring the urgency of effectively managing these comorbidities to optimise patient well-being. Additionally, regional discrepancies come to the fore, with the Capricorn district demonstrating elevated mortality risks, thereby accentuating the necessity for precisely targeted interventions. Medical interventions, particularly ventilation, emerge as pivotal factors in mitigating mortality risk. Gender-based distinctions in mortality patterns also underscore the need for bespoke patient care strategies. Conclusions: Collectively, these outcomes supply practical insights with implications for healthcare interventions, policy formulation, and clinical strategies aimed at ameliorating COVID-19 mortality risk among individuals discharged from hospitals within South Africa's Limpopo province.

Machine learning models for predicting severe COVID-19 outcomes in hospitals

The aim of this observational retrospective study is to improve early risk stratification of hospitalized Covid-19 patients by predicting in-hospital mortality, transfer to intensive care unit (ICU) and mechanical ventilation from electronic health record data of the first 24 h after admission. Our machine learning model predicts in-hospital mortality (AUC = 0.918), transfer to ICU (AUC = 0.821) and the need for mechanical ventilation (AUC = 0.654) from a few laboratory data of the first 24 h after admission. Models based on dichotomous features indicating whether a laboratory value exceeds or falls below a threshold perform nearly as good as models based on numerical features. We devise completely data-driven and interpretable machine-learning models for the prediction of in-hospital mortality, transfer to ICU and mechanical ventilation for hospitalized Covid-19 patients within 24 h after admission. Numerical values of. CRP and blood sugar and dichotomous indicators for increased partial thromboplastin time (PTT) and glutamic oxaloacetic transaminase (GOT) are amongst the best predictors.

Interpretable Machine Learning for Inpatient COVID-19 Mortality Risk Assessments: Diabetes Mellitus Exclusive Interplay

People with diabetes mellitus (DM) are at elevated risk of in-hospital mortality from coronavirus disease-2019 (COVID-19). This vulnerability has spurred efforts to pinpoint distinctive characteristics of COVID-19 patients with DM. In this context, the present article develops ML models equipped with interpretation modules for inpatient mortality risk assessments of COVID-19 patients with DM. To this end, a cohort of 156 hospitalised COVID-19 patients with pre-existing DM is studied. For creating risk assessment platforms, this work explores a pool of historical, on-admission, and during-admission data that are DM-related or, according to preliminary investigations, are exclusively attributed to the COVID-19 susceptibility of DM patients. First, a set of careful pre-modelling steps are executed on the clinical data, including cleaning, pre-processing, subdivision, and feature elimination. Subsequently, standard machine learning (ML) modelling analysis is performed on the cured data. Initially, a classifier is tasked with forecasting COVID-19 fatality from selected features. The model undergoes thorough evaluation analysis. The results achieved substantiate the efficacy of the undertaken data curation and modelling steps. Afterwards, SHapley Additive exPlanations (SHAP) technique is assigned to interpret the generated mortality risk prediction model by rating the predictors' global and local influence on the model's outputs. These interpretations advance the comprehensibility of the analysis by explaining the formation of outcomes and, in this way, foster the adoption of the proposed methodologies. Next, a clustering algorithm demarcates patients into four separate groups based on their SHAP values, providing a practical risk stratification method. Finally, a re-evaluation analysis is performed to verify the robustness of the proposed framework.

Prognostic Model of COVID-19 Severity and Survival among Hospitalized Patients Using Machine Learning Techniques

We conducted a statistical study and developed a machine learning model to triage COVID-19 patients affected during the height of the COVID-19 pandemic in Hong Kong based on their medical records and test results (features) collected during their hospitalization. The correlation between the values of these features is studied against discharge status and disease severity as a preliminary step to identify those features with a more pronounced effect on the patient outcome. Once identified, they constitute the inputs of four machine learning models, Decision Tree, Random Forest, Gradient and RUSBoosting, which predict both the Mortality and Severity associated with the disease. We test the accuracy of the models when the number of input features is varied, demonstrating their stability; i.e., the models are already highly predictive when run over a core set of (6) features. We show that Random Forest and Gradient Boosting classifiers are highly accurate in predicting patients' Mortality (average accuracy ∼99%) as well as categorize patients (average accuracy ∼91%) into four distinct risk classes (Severity of COVID-19 infection). Our methodical and broad approach combines statistical insights with various machine learning models, which paves the way forward in the AI-assisted triage and prognosis of COVID-19 cases, which is potentially generalizable to other seasonal flus.

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

The recent COVID-19 pandemic has affected health systems across the world. Especially, Intensive Care Units (ICUs) have played a pivotal role in the treatment of critically-ill patients. At the same time however, the increasing number of admissions due to the vast prevalence of the virus have caused several problems for ICU wards such as overburdening of staff and shortages of medical resources. These issues might have affected the quality of healthcare services provided directly impacting a patient's survival. The objective of this research is to leverage Machine Learning (ML) on hospital data in order to support hospital managers and practitioners with the treatment of COVID-19 patients. This is accomplished by providing more detailed inference about a patient's likelihood of ICU admission, mortality and in case of hospitalization the length of stay (LOS). In this pursuit, the outcome variables are in three separate models predicted by five different ML algorithms: eXtreme Gradient Boosting (XGB), K-Nearest Neighbor (KNN), Random Forest (RF), bagged-CART (b-CART), and LogitBoost (LB). With the exception of KNN, the studied models show good predictive capabilities when evaluating relevant accuracy scores, such as area under the curve. By implementing an ensemble stacking approach (either a Neural Net or a General Linear Model) on top of the aforementioned ML algorithms the performance is further boosted. Ultimately, for the prediction of admission to the ICU, the ensemble stacking via a Neural Net achieved the best result with an accuracy of over 95%. For mortality at the ICU, the vanilla XGB performed slightly better (1% difference with the meta-model). To predict large length of stays both ensemble stacking approaches yield comparable results. Besides it direct implications for managing COVID-19 patients, the approach presented serves as an example how data can be employed in future pandemics or crises.

Risk of Death in Comorbidity Subgroups of Hospitalized COVID-19 Patients Inferred by Routine Laboratory Markers of Systemic Inflammation on Admission: A Retrospective Study

Our study objective was to construct models using 20 routine laboratory parameters on admission to predict disease severity and mortality risk in a group of 254 hospitalized COVID-19 patients. Considering the influence of confounding factors in this single-center study, we also retrospectively assessed the correlations between the risk of death and the routine laboratory parameters within individual comorbidity subgroups. In multivariate regression models and by ROC curve analysis, a model of three routine laboratory parameters (AUC 0.85; 95% CI: 0.79–0.91) and a model of six laboratory factors (AUC 0.86; 95% CI: 0.81–0.91) were able to predict severity and mortality of COVID-19, respectively, compared with any other individual parameter. Hierarchical cluster analysis showed that inflammatory laboratory markers grouped together in three distinct clusters including positive correlations: WBC with NEU, NEU with neutrophil-to-lymphocyte ratio (NLR), NEU with systemic immune-inflammation index (SII), NLR with SII and platelet-to-lymphocyte ratio (PLR) with SII. When analyzing the routine laboratory parameters in the subgroups of comorbidities, the risk of death was associated with a common set of laboratory markers of systemic inflammation. Our results have shown that a panel of several routine laboratory parameters recorded on admission could be helpful for early evaluation of the risk of disease severity and mortality in COVID-19 patients. Inflammatory markers for mortality risk were similar in the subgroups of comorbidities, suggesting the limited effect of confounding factors in predicting COVID-19 mortality at admission.

Machine learning-based in-hospital mortality prediction of HIV/AIDS patients with Talaromyces marneffei infection in Guangxi, China

Objective

Talaromycosis is a serious regional disease endemic in Southeast Asia. In China, Talaromyces marneffei (T. marneffei) infections is mainly concentrated in the southern region, especially in Guangxi, and cause considerable in-hospital mortality in HIV-infected individuals. Currently, the factors that influence in-hospital death of HIV/AIDS patients with T. marneffei infection are not completely clear. Existing machine learning techniques can be used to develop a predictive model to identify relevant prognostic factors to predict death and appears to be essential to reducing in-hospital mortality.

Methods

We prospectively enrolled HIV/AIDS patients with talaromycosis in the Fourth People’s Hospital of Nanning, Guangxi, from January 2012 to June 2019. Clinical features were selected and used to train four different machine learning models (logistic regression, XGBoost, KNN, and SVM) to predict the treatment outcome of hospitalized patients, and 30% internal validation was used to evaluate the performance of models. Machine learning model performance was assessed according to a range of learning metrics, including area under the receiver operating characteristic curve (AUC). The SHapley Additive exPlanations (SHAP) tool was used to explain the model.

Results

A total of 1927 HIV/AIDS patients with T. marneffei infection were included. The average in-hospital mortality rate was 13.3% (256/1927) from 2012 to 2019. The most common complications/coinfections were pneumonia (68.9%), followed by oral candida (47.5%), and tuberculosis (40.6%). Deceased patients showed higher CD4/CD8 ratios, aspartate aminotransferase (AST) levels, creatinine levels, urea levels, uric acid (UA) levels, lactate dehydrogenase (LDH) levels, total bilirubin levels, creatine kinase levels, white blood-cell counts (WBC) counts, neutrophil counts, procaicltonin levels and C-reactive protein (CRP) levels and lower CD3⁺ T-cell count, CD8⁺ T-cell count, and lymphocyte counts, platelet (PLT), high-density lipoprotein cholesterol (HDL), hemoglobin (Hb) levels than those of surviving patients. The predictive XGBoost model exhibited 0.71 sensitivity, 0.99 specificity, and 0.97 AUC in the training dataset, and our outcome prediction model provided robust discrimination in the testing dataset, showing an AUC of 0.90 with 0.69 sensitivity and 0.96 specificity. The other three models were ruled out due to poor performance. Septic shock and respiratory failure were the most important predictive features, followed by uric acid, urea, platelets, and the AST/ALT ratios.

Conclusion

The XGBoost machine learning model is a good predictor in the hospitalization outcome of HIV/AIDS patients with T. marneffei infection. The model may have potential application in mortality prediction and high-risk factor identification in the talaromycosis population.

Talaromyces marneffei can cause a fatal deeply disseminated fungal infection- talaromycosis. It is widely distributed in Southeast Asia and spreading globally, the disease is insidious and responsible for significant deaths. Clinicians need easy-to-use tools to make decisions on which patients are at a higher risk of dying after infecting T. marneffei. In this study, conducted in Southern China, we have evolved XGBoost machine learning model. 15 clinical indicators and laboratory measures were used to estimate a patient’s risk of dying in the hospital due to the T. marneffei infection. The study showed that the machine learning model has good predictive ability when tested in an internal testing population of patients. We expect that the model could help clinicians assess a patient’s risk of death in just the time of admission to help decide on early treatment timing of high-risk patients who are likely to die.

A robust and parsimonious machine learning method to predict ICU admission of COVID-19 patients

In this article, we discuss the development of prognostic machine learning (ML) models for COVID-19 progression, by focusing on the task of predicting ICU admission within (any of) the next 5 days. On the basis of 6,625 complete blood count (CBC) tests from 1,004 patients, of which 18% were admitted to intensive care unit (ICU), we created four ML models, by adopting a robust development procedure which was designed to minimize risks of bias and over-fitting, according to reference guidelines. The best model, a support vector machine, had an AUC of .85, a Brier score of .14, and a standardized net benefit of .69: these scores indicate that the model performed well over a variety of prediction criteria. We also conducted an interpretability study to back up our findings, showing that the data on which the developed model is based is consistent with the current medical literature. This also demonstrates that CBC data and ML methods can be used to predict COVID-19 patients' ICU admission at a relatively low cost: in particular, since CBC data can be quickly obtained by means of routine blood exams, our models could be used in resource-constrained settings and provide health practitioners with rapid and reliable indications.

Application of machine learning in the fight against the COVID-19 pandemic: A review

Introduction: Machine learning (ML) plays a significant role in the fight against the COVID-19 (officially known as SARS-CoV-2) pandemic. ML techniques enable the rapid detection of patterns and trends in large datasets. Therefore, ML provides efficient methods to generate knowledge from structured and unstructured data. This potential is particularly significant when the pandemic affects all aspects of human life. It is necessary to collect a large amount of data to identify methods to prevent the spread of infection, early detection, reduction of consequences, and finding appropriate medicine. Modern information and communication technologies (ICT) such as the Internet of Things (IoT) allow the collection of large amounts of data from various sources. Thus, we can create predictive ML-based models for assessments, predictions, and decisions. Methods: This is a review article based on previous studies and scientifically proven knowledge. In this paper, bibliometric data from authoritative databases of research publications (Web of Science, Scopus, PubMed) are combined for bibliometric analyses in the context of ML applications for COVID-19. Aim: This paper reviews some ML-based applications used for mitigating COVID-19. We aimed to identify and review ML potentials and solutions for mitigating the COVID-19 pandemic as well as to present some of the most commonly used ML techniques, algorithms, and datasets applied in the context of COVID-19. Also, we provided some insights into specific emerging ideas and open issues to facilitate future research. Conclusion: ML is an effective tool for diagnosing and early detection of symptoms, predicting the spread of a pandemic, developing medicines and vaccines, etc.