scholarly journals A Time-Incorporated SOFA-Based Explainable Machine Learning Model for Mortality Prediction in Critically Ill Patients

2021 ◽  
Author(s):  
Yang Liu ◽  
Kun Gao ◽  
Hongbin Deng ◽  
Tong Ling ◽  
Jiajia Lin ◽  
...  
Keyword(s):  
Machine Learning ◽  
Intensive Care ◽  
Sofa Score ◽  
Model Development ◽  
Mortality Prediction ◽  
Machine Learning Algorithms ◽  
Time Dimension ◽  
Icu Mortality ◽  
Test Set ◽  
Individual Scores

Abstract Background: Organ dysfunction (OD) assessment is essential in intensive care units (ICUs). However, no OD scoring system has so far considered the duration of OD, which is clinically relevant. This study aimed to develop and validate an ICU mortality prediction model based on the Sequential Organ Failure Assessment (SOFA) score, incorporating the time dimension with machine learning methods.Methods: Data from the eICU Collaborative Research Database and Medical Information Mart for Intensive Care (MIMIC) -III were mixed for model development, and the MIMIC-IV dataset and Nanjing Jinling Hospital Surgery ICU (SICU-JL) dataset were used for external testing. Adult patients in the ICUs for more than 72 hours were deemed eligible. The total SOFA score and individual scores were calculated every 12 hours for the first three days of ICU admission. Time-dimensional variables were derived from the consecutively recorded SOFA scores and individual scores for each organ. A modified SOFA model incorporating the time dimension (T-SOFA) was stepwise constructed to predict ICU mortality using multiple machine learning algorithms. The predictive performance was assessed with the area under the receiver operating characteristic curves (AUROC). Also, we utilized the SHapley Additive exPlanations (SHAP) algorithm for data visualization and model explainability.Results: We extracted a total of 66,709 ICU patients from the mixed datasets for model development and 15,423 patients for validation. The T-SOFA M3 that incorporated the time dimension features and age, using the XGBoost algorithm, significantly outperformed the original SOFA scores (AUROC 0.800 95% CI [0.787-0.813] vs. 0.693 95% CI [0.678-0.709], p<0.01) in the validation set. Good prediction performance was maintained for the T-SOFA M3 in test Set A and test Set B, with AUROC of 0.803, 95% CI[0.791-0.815], and 0.830, 95%CI [0.789-0.870], respectively. Significant contributors demonstrated by the SHAP analysis included total SOFA score, Respiration-score, CNS-score, age, Cardiovascular-score, and SOFA Organ dysfunction Unalleviated Time Index.Conclusions: A SOFA-based, time-incorporated prediction model was developed and validated by machine learning algorithms, showing satisfactory predictability and medical interpretability.

scholarly journals Mortality Prediction in Cerebral Hemorrhage Patients Using Machine Learning Algorithms in Intensive Care Units

2021 ◽  
Vol 11 ◽  
Author(s):  
Ximing Nie ◽  
Yuan Cai ◽  
Jingyi Liu ◽  
Xiran Liu ◽  
Jiahui Zhao ◽  
...  
Keyword(s):  
Machine Learning ◽  
Intensive Care ◽  
Random Forest ◽  
Hospital Mortality ◽  
Intensive Care Units ◽  
Cerebral Hemorrhage ◽  
Characteristic Curve ◽  
Learning Algorithms ◽  
Mortality Prediction ◽  
Machine Learning Algorithms

Objectives: This study aims to investigate whether the machine learning algorithms could provide an optimal early mortality prediction method compared with other scoring systems for patients with cerebral hemorrhage in intensive care units in clinical practice.Methods: Between 2008 and 2012, from Intensive Care III (MIMIC-III) database, all cerebral hemorrhage patients monitored with the MetaVision system and admitted to intensive care units were enrolled in this study. The calibration, discrimination, and risk classification of predicted hospital mortality based on machine learning algorithms were assessed. The primary outcome was hospital mortality. Model performance was assessed with accuracy and receiver operating characteristic curve analysis.Results: Of 760 cerebral hemorrhage patients enrolled from MIMIC database [mean age, 68.2 years (SD, ±15.5)], 383 (50.4%) patients died in hospital, and 377 (49.6%) patients survived. The area under the receiver operating characteristic curve (AUC) of six machine learning algorithms was 0.600 (nearest neighbors), 0.617 (decision tree), 0.655 (neural net), 0.671(AdaBoost), 0.819 (random forest), and 0.725 (gcForest). The AUC was 0.423 for Acute Physiology and Chronic Health Evaluation II score. The random forest had the highest specificity and accuracy, as well as the greatest AUC, showing the best ability to predict in-hospital mortality.Conclusions: Compared with conventional scoring system and the other five machine learning algorithms in this study, random forest algorithm had better performance in predicting in-hospital mortality for cerebral hemorrhage patients in intensive care units, and thus further research should be conducted on random forest algorithm.

scholarly journals Using Machine Learning Algorithms to Predict Hospital Acquired Thrombocytopenia after Operation in the Intensive Care Unit: A Retrospective Cohort Study

Diagnostics ◽  
2021 ◽  
Vol 11 (9) ◽  
pp. 1614
Author(s):  
Yisong Cheng ◽  
Chaoyue Chen ◽  
Jie Yang ◽  
Hao Yang ◽  
Min Fu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Intensive Care Unit ◽  
Cohort Study ◽  
Intensive Care ◽  
Retrospective Cohort Study ◽  
Retrospective Cohort ◽  
Machine Learning Algorithms ◽  
Gradient Boosting ◽  
Test Set ◽  
Hospital Acquired

Hospital acquired thrombocytopenia (HAT) is a common hematological complication after surgery. This research aimed to develop and compare the performance of seven machine learning (ML) algorithms for predicting patients that are at risk of HAT after surgery. We conducted a retrospective cohort study which enrolled adult patients transferred to the intensive care unit (ICU) after surgery in West China Hospital of Sichuan University from January 2016 to December 2018. All subjects were randomly divided into a derivation set (70%) and test set (30%). ten-fold cross-validation was used to estimate the hyperparameters of ML algorithms during the training process in the derivation set. After ML models were developed, the sensitivity, specificity, area under the curve (AUC), and net benefit (decision analysis curve, DCA) were calculated to evaluate the performances of ML models in the test set. A total of 10,369 patients were included and in 1354 (13.1%) HAT occurred. The AUC of all seven ML models exceeded 0.7, the two highest were Gradient Boosting (GB) (0.834, 0.814–0.853, p < 0.001) and Random Forest (RF) (0.828, 0.807–0.848, p < 0.001). There was no difference between GB and RF (0.834 vs. 0.828, p = 0.293); however, these two were better than the remaining five models (p < 0.001). The DCA revealed that all ML models had high net benefits with a threshold probability approximately less than 0.6. In conclusion, we found that ML models constructed by multiple preoperative variables can predict HAT in patients transferred to ICU after surgery, which can improve risk stratification and guide management in clinical practice.

Development and validation of simplified machine learning algorithms to predict prognosis of hospitalized COVID-19 patients: a multi-center, retrospective study (Preprint)

2021 ◽  
Author(s):  
Fang He ◽  
John H Page ◽  
Kerry R Weinberg ◽  
Anirban Mishra
Keyword(s):  
Machine Learning ◽  
Respiratory Failure ◽  
High Risk ◽  
Learning Algorithms ◽  
Model Development ◽  
Machine Learning Algorithms ◽  
Validation Dataset ◽  
High Risk Patients ◽  
Risk Patients ◽  
Development And Validation

BACKGROUND The current COVID-19 pandemic is unprecedented; under resource-constrained setting, predictive algorithms can help to stratify disease severity, alerting physicians of high-risk patients, however there are few risk scores derived from a substantially large EHR dataset, using simplified predictors as input. OBJECTIVE To develop and validate simplified machine learning algorithms which predicts COVID-19 adverse outcomes, to evaluate the AUC (area under the receiver operating characteristic curve), sensitivity, specificity and calibration of the algorithms, to derive clinically meaningful thresholds. METHODS We conducted machine learning model development and validation via cohort study using multi-center, patient-level, longitudinal electronic health records (EHR) from Optum® COVID-19 database which provides anonymized, longitudinal EHR from across US. The models were developed based on clinical characteristics to predict 28-day in-hospital mortality, ICU admission, respiratory failure, mechanical ventilator usages at inpatient setting. Data from patients who were admitted prior to Sep 7, 2020, is randomly sampled into development, test and validation datasets; data collected from Sep 7, 2020 through Nov 15, 2020 was reserved as prospective validation dataset. RESULTS Of 3.7M patients in the analysis, a total of 585,867 patients were diagnosed or tested positive for SARS-CoV-2; and 50,703 adult patients were hospitalized with COVID-19 between Feb 1 and Nov 15, 2020. Among the study cohort (N=50,703), there were 6,204 deaths, 9,564 ICU admissions, 6,478 mechanically ventilated or EMCO patients and 25,169 patients developed ARDS or respiratory failure within 28 days since hospital admission. The algorithms demonstrated high accuracy (AUC = 0.89 (0.89 - 0.89) on validation dataset (N=10,752)), consistent prediction through the second wave of pandemic from September to November (AUC = 0.85 (0.85 - 0.86) on post-development validation (N= 14,863)), great clinical relevance and utility. Besides, a comprehensive 386 input covariates from baseline and at admission was included in the analysis; the end-to-end pipeline automates feature selection and model development process, producing 10 key predictors as input such as age, blood urea nitrogen, oxygen saturation, which are both commonly measured and concordant with recognized risk factors for COVID-19. CONCLUSIONS The systematic approach and rigorous validations demonstrate consistent model performance to predict even beyond the time period of data collection, with satisfactory discriminatory power and great clinical utility. Overall, the study offers an accurate, validated and reliable prediction model based on only ten clinical features as a prognostic tool to stratifying COVID-19 patients into intermediate, high and very high-risk groups. This simple predictive tool could be shared with a wider healthcare community, to enable service as an early warning system to alert physicians of possible high-risk patients, or as a resource triaging tool to optimize healthcare resources. CLINICALTRIAL N/A

scholarly journals Machine Learning for Mortality Prediction in Pediatric Myocarditis

2021 ◽  
Vol 9 ◽  
Author(s):  
Fu-Sheng Chou ◽  
Laxmi V. Ghimire
Keyword(s):  
Machine Learning ◽  
Linear Regression ◽  
Regression Model ◽  
Current Knowledge ◽  
External Validation ◽  
Model Development ◽  
Kidney Injury ◽  
High Specificity ◽  
Mortality Prediction ◽  
Linear Regression Models

Background: Pediatric myocarditis is a rare disease. The etiologies are multiple. Mortality associated with the disease is 5–8%. Prognostic factors were identified with the use of national hospitalization databases. Applying these identified risk factors for mortality prediction has not been reported.Methods: We used the Kids' Inpatient Database for this project. We manually curated fourteen variables as predictors of mortality based on the current knowledge of the disease, and compared performance of mortality prediction between linear regression models and a machine learning (ML) model. For ML, the random forest algorithm was chosen because of the categorical nature of the variables. Based on variable importance scores, a reduced model was also developed for comparison.Results: We identified 4,144 patients from the database for randomization into the primary (for model development) and testing (for external validation) datasets. We found that the conventional logistic regression model had low sensitivity (~50%) despite high specificity (&gt;95%) or overall accuracy. On the other hand, the ML model struck a good balance between sensitivity (89.9%) and specificity (85.8%). The reduced ML model with top five variables (mechanical ventilation, cardiac arrest, ECMO, acute kidney injury, ventricular fibrillation) were sufficient to approximate the prediction performance of the full model.Conclusions: The ML algorithm performs superiorly when compared to the linear regression model for mortality prediction in pediatric myocarditis in this retrospective dataset. Prospective studies are warranted to further validate the applicability of our model in clinical settings.

Cereal yield forecasting combining satellite drought-based indices, regional climate and weather data using machine learning approaches in Morocco

2021 ◽  
Author(s):  
El houssaine Bouras ◽  
Lionel Jarlan ◽  
Salah Er-Raki ◽  
Riad Balaghi ◽  
Abdelhakim Amazirh ◽  
...  
Keyword(s):  
Machine Learning ◽  
Regional Climate ◽  
Model Development ◽  
Machine Learning Algorithms ◽  
Weather Data ◽  
Drought Indices ◽  
Support Vector ◽  
Learning Approaches ◽  
Climate Data ◽  
Yield Forecasting

&lt;p&gt;Cereals are the main crop in Morocco. Its production exhibits a high inter-annual due to uncertain rainfall and recurrent drought periods. Considering the importance of this resource to the country's economy, it is thus important for decision makers to have reliable forecasts of the annual cereal production in order to pre-empt importation needs. In this study, we assessed the joint use of satellite-based drought indices, weather (precipitation and temperature) and climate data (pseudo-oscillation indices including NAO and the leading modes of sea surface temperature -SST- in the mid-latitude and in the tropical area) to predict cereal yields at the level of the agricultural province using machine learning algorithms (Support Vector Machine -SVM-, Random forest -FR- and eXtreme Gradient Boost -XGBoost-) in addition to Multiple Linear Regression (MLR). Also, we evaluate the models for different lead times along the growing season from January (about 5 months before harvest) to March (2 months before harvest). The results show the combination of data from the different sources outperformed the use of a single dataset; the highest accuracy being obtained when the three data sources were all considered in the model development. In addition, the results show that the models can accurately predict yields in January (5 months before harvesting) with an R&amp;#178; = 0.90 and RMSE about 3.4 Qt.ha&lt;sup&gt;-1&lt;/sup&gt;. &amp;#160;When comparing the model&amp;#8217;s performance, XGBoost represents the best one for predicting yields. Also, considering specific models for each province separately improves the statistical metrics by approximately 10-50% depending on the province with regards to one global model applied to all the provinces. The results of this study pointed out that machine learning is a promising tool for cereal yield forecasting. Also, the proposed methodology can be extended to different crops and different regions for crop yield forecasting.&lt;/p&gt;

scholarly journals Machine Learning Algorithms to Predict Recurrence within 10 Years after Breast Cancer Surgery: A Prospective Cohort Study

Cancers ◽  
2020 ◽  
Vol 12 (12) ◽  
pp. 3817
Author(s):  
Shi-Jer Lou ◽  
Ming-Feng Hou ◽  
Hong-Tai Chang ◽  
Chong-Chi Chiu ◽  
Hao-Hsien Lee ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Learning Algorithms ◽  
External Validation ◽  
Model Development ◽  
Cancer Surgery ◽  
Machine Learning Algorithms ◽  
Breast Cancer Surgery ◽  
Training Dataset

No studies have discussed machine learning algorithms to predict recurrence within 10 years after breast cancer surgery. This study purposed to compare the accuracy of forecasting models to predict recurrence within 10 years after breast cancer surgery and to identify significant predictors of recurrence. Registry data for breast cancer surgery patients were allocated to a training dataset (n = 798) for model development, a testing dataset (n = 171) for internal validation, and a validating dataset (n = 171) for external validation. Global sensitivity analysis was then performed to evaluate the significance of the selected predictors. Demographic characteristics, clinical characteristics, quality of care, and preoperative quality of life were significantly associated with recurrence within 10 years after breast cancer surgery (p < 0.05). Artificial neural networks had the highest prediction performance indices. Additionally, the surgeon volume was the best predictor of recurrence within 10 years after breast cancer surgery, followed by hospital volume and tumor stage. Accurate recurrence within 10 years prediction by machine learning algorithms may improve precision in managing patients after breast cancer surgery and improve understanding of risk factors for recurrence within 10 years after breast cancer surgery.

scholarly journals Evaluation and Identification of the Neuroprotective Compounds of Xiaoxuming Decoction by Machine Learning: A Novel Mode to Explore the Combination Rules in Traditional Chinese Medicine Prescription

2019 ◽  
Vol 2019 ◽  
pp. 1-14
Author(s):  
Shilun Yang ◽  
Yanjia Shen ◽  
Wendan Lu ◽  
Yinglin Yang ◽  
Haigang Wang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Chinese Medicine ◽  
Traditional Chinese Medicine ◽  
Cross Validation ◽  
Bayesian Models ◽  
Machine Learning Algorithms ◽  
Therapeutic Effects ◽  
Test Set ◽  
Screening Experiments ◽  
Fold Cross Validation

Xiaoxuming decoction (XXMD), a classic traditional Chinese medicine (TCM) prescription, has been used as a therapeutic in the treatment of stroke in clinical practice for over 1200 years. However, the pharmacological mechanisms of XXMD have not yet been elucidated. The purpose of this study was to develop neuroprotective models for identifying neuroprotective compounds in XXMD against hypoxia-induced and H2O2-induced brain cell damage. In this study, a phenotype-based classification method was designed by machine learning to identify neuroprotective compounds and to clarify the compatibility of XXMD components. Four different single classifiers (AB, kNN, CT, and RF) and molecular fingerprint descriptors were used to construct stacked naïve Bayesian models. Among them, the RF algorithm had a better performance with an average MCC value of 0.725±0.014 and 0.774±0.042 from 5-fold cross-validation and test set, respectively. The probability values calculated by four models were then integrated into a stacked Bayesian model. In total, two optimal models, s-NB-1-LPFP6 and s-NB-2-LPFP6, were obtained. The two validated optimal models revealed Matthews correlation coefficients (MCC) of 0.968 and 0.993 for 5-fold cross-validation and of 0.874 and 0.959 for the test set, respectively. Furthermore, the two models were used for virtual screening experiments to identify neuroprotective compounds in XXMD. Ten representative compounds with potential therapeutic effects against the two phenotypes were selected for further cell-based assays. Among the selected compounds, two compounds significantly inhibited H2O2-induced and Na2S2O4-induced neurotoxicity simultaneously. Together, our findings suggested that machine learning algorithms such as combination Bayesian models were feasible to predict neuroprotective compounds and to preliminarily demonstrate the pharmacological mechanisms of TCM.

scholarly journals Comparison of qSOFA score, SOFA score, and SIRS criteria for the prediction of infection and mortality among surgical intermediate and intensive care patients

2020 ◽  
Vol 15 (1) ◽  
Author(s):  
Christian Koch ◽  
Fabian Edinger ◽  
Tobias Fischer ◽  
Florian Brenck ◽  
Andreas Hecker ◽  
...  
Keyword(s):  
Intensive Care ◽  
Sofa Score ◽  
Mortality Prediction ◽  
Adequate Treatment ◽  
Suspected Infection ◽  
Intensive Care Patients ◽  
Retrospective Data Analysis ◽  
Surgical Icu ◽  
Qsofa Score ◽  
Sirs Criteria

Abstract Background It is crucial to rapidly identify sepsis so that adequate treatment may be initiated. Accordingly, the Sequential Organ Failure Assessment (SOFA) and the quick SOFA (qSOFA) scores are used to evaluate intensive care unit (ICU) and non-ICU patients, respectively. As demand for ICU beds rises, the intermediate care unit (IMCU) carries greater importance as a bridge between the ICU and the regular ward. This study aimed to examine the ability of SOFA and qSOFA scores to predict suspected infection and mortality in IMCU patients. Methods Retrospective data analysis included 13,780 surgical patients treated at the IMCU, ICU, or both between January 01, 2012, and September 30, 2018. Patients were screened for suspected infection (i.e., the commencement of broad-spectrum antibiotics) and then evaluated for the SOFA score, qSOFA score, and the 1992 defined systemic inflammatory response syndrome (SIRS) criteria. Results Suspected infection was detected in 1306 (18.3%) of IMCU, 1365 (35.5%) of ICU, and 1734 (62.0%) of IMCU/ICU encounters. Overall, 458 (3.3%) patients died (IMCU 45 [0.6%]; ICU 250 [6.5%]; IMCU/ICU 163 [5.8%]). All investigated scores failed to predict suspected infection independently of the analyzed subgroup. Regarding mortality prediction, the qSOFA score performed sufficiently within the IMCU cohort (AUCROC SIRS 0.72 [0.71–0.72]; SOFA 0.52 [0.51–0.53]; qSOFA 0.82 [0.79–0.84]), while the SOFA score was predictive in patients of the IMCU/ICU cohort (AUCROC SIRS 0.54 [0.53–0.54]; SOFA 0.73 [0.70–0.77]; qSOFA 0.59 [0.58–0.59]). Conclusions None of the assessed scores was sufficiently able to predict suspected infection in surgical ICU or IMCU patients. While the qSOFA score is appropriate for mortality prediction in IMCU patients, SOFA score prediction quality is increased in critically ill patients.

Sign in / Sign up

Export Citation Format

Share Document