Application of Artificial Intelligence to Advance Individualized Diagnosis and Treatment in Emergency and Critical Care Medicine

A special issue of Diagnostics (ISSN 2075-4418). This special issue belongs to the section "Machine Learning and Artificial Intelligence in Diagnostics".

Deadline for manuscript submissions: 31 March 2024 | Viewed by 17091

Special Issue Editor

Special Issue Information

Dear Colleagues, 

Analytics based on artificial intelligence has greatly advanced scientific research fields such as natural language processing and imaging classification. Clinical research has also been greatly influenced by artificial intelligence for diagnostics involving imaging and molecular markers. Emergency and critical care medicine faces patients with rapidly changing conditions, which require the accurate risk stratification and initiation of rescuing therapies. The key to the successful treatment of critically ill patients involves all aspects of diagnostics such as the early prediction of adverse events, correct diagnosis of causative agents and a differential diagnosis for a manifestation. Critically ill patients usually generate a large amount of data from medical devices such as bedside monitors, ventilators, and renal replacement therapy devices. Such large volumes of data are difficult to handle by human intuition. Artificial intelligence can learn complex data structures to obtain knowledge and wisdom and, thus, can have profound impacts on the management of critically ill patients. Furthermore, critically ill patients such as those with sepsis, acute respiratory distress syndrome and trauma comprise a heterogenous population. The “one-size-fit-all” paradigm may not be suitable for the management of such a heterogeneous patient population. Thus, tools from artificial intelligence can be employed to identify novel subphenotypes of these patients. These subclassifications can not only provide prognostic value for risk stratification, but also have predictive value for individualized treatment. Transcriptomes can also provide large amounts of information for the patients; artificial intelligence can greatly help to learn useful information from such highly dimensional data.

This Special Issue welcomes articles addressing, but not limited to, the following specific topics:

  • Predictive analytics for the risk stratification of emergency and critically ill patients.
  • Diagnostics for critical syndromes such as sepsis, acute respiratory failure and acute circulatory failure.
  • Biomarkers for the differentiation of critical syndromes.
  • Individualized treatment strategies for patients with rapidly changing conditions.
  • Subphenotypes of heterogenous populations in emergency and critical care settings.
  • Bioinformatics analysis with transcriptomes to develop individualized management.

Reviews, opinions, original articles and secondary analysis are welcome.

Prof. Dr. Zhongheng Zhang
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Diagnostics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • critical care
  • sepsis
  • artificial intelligence
  • predictive analytics
  • clustering
  • acute kidney injury
  • emergency medicine
  • transcriptome

Published Papers (11 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Editorial

Jump to: Research

5 pages, 523 KiB  
Editorial
Application of Artificial Intelligence to Advance Individualized Diagnosis and Treatment in Emergency and Critical Care Medicine
by Jie Yang, Bo Zhang, Xiaocong Jiang, Jiajie Huang, Yucai Hong, Hongying Ni and Zhongheng Zhang
Diagnostics 2024, 14(7), 687; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics14070687 - 25 Mar 2024
Viewed by 288
Abstract
Emergency and critical illnesses refer to severe diseases or conditions characterized by rapid changes in health that may endanger life within a short period [...] Full article
Show Figures

Figure 1

Research

Jump to: Editorial

14 pages, 1962 KiB  
Article
Assessment of Sepsis Risk at Admission to the Emergency Department: Clinical Interpretable Prediction Model
by Umran Aygun, Fatma Hilal Yagin, Burak Yagin, Seyma Yasar, Cemil Colak, Ahmet Selim Ozkan and Luca Paolo Ardigò
Diagnostics 2024, 14(5), 457; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics14050457 - 20 Feb 2024
Viewed by 744
Abstract
This study aims to develop an interpretable prediction model based on explainable artificial intelligence to predict bacterial sepsis and discover important biomarkers. A total of 1572 adult patients, 560 of whom were sepsis positive and 1012 of whom were negative, who were admitted [...] Read more.
This study aims to develop an interpretable prediction model based on explainable artificial intelligence to predict bacterial sepsis and discover important biomarkers. A total of 1572 adult patients, 560 of whom were sepsis positive and 1012 of whom were negative, who were admitted to the emergency department with suspicion of sepsis, were examined. We investigated the performance characteristics of sepsis biomarkers alone and in combination for confirmed sepsis diagnosis using Sepsis-3 criteria. Three different tree-based algorithms—Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), Adaptive Boosting (AdaBoost)—were used for sepsis prediction, and after examining comprehensive performance metrics, descriptions of the optimal model were obtained with the SHAP method. The XGBoost model achieved accuracy of 0.898 (0.868–0.929) and area under the ROC curve (AUC) of 0.940 (0.898–0.980) with a 95% confidence interval. The five biomarkers for predicting sepsis were age, respiratory rate, oxygen saturation, procalcitonin, and positive blood culture. SHAP results revealed that older age, higher respiratory rate, procalcitonin, neutrophil–lymphocyte count ratio, C-reactive protein, plaque, leukocyte particle concentration, as well as lower oxygen saturation, systolic blood pressure, and hemoglobin levels increased the risk of sepsis. As a result, the Explainable Artificial Intelligence (XAI)-based prediction model can guide clinicians in the early diagnosis and treatment of sepsis, providing more effective sepsis management and potentially reducing mortality rates and medical costs. Full article
Show Figures

Figure 1

14 pages, 2433 KiB  
Article
Machine Learning Algorithm Predicts Mortality Risk in Intensive Care Unit for Patients with Traumatic Brain Injury
by Kuan-Chi Tu, Eric nyam tee Tau, Nai-Ching Chen, Ming-Chuan Chang, Tzu-Chieh Yu, Che-Chuan Wang, Chung-Feng Liu and Ching-Lung Kuo
Diagnostics 2023, 13(18), 3016; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics13183016 - 21 Sep 2023
Viewed by 810
Abstract
Background: Numerous mortality prediction tools are currently available to assist patients with moderate to severe traumatic brain injury (TBI). However, an algorithm that utilizes various machine learning methods and employs diverse combinations of features to identify the most suitable predicting outcomes of brain [...] Read more.
Background: Numerous mortality prediction tools are currently available to assist patients with moderate to severe traumatic brain injury (TBI). However, an algorithm that utilizes various machine learning methods and employs diverse combinations of features to identify the most suitable predicting outcomes of brain injury patients in the intensive care unit (ICU) has not yet been well-established. Method: Between January 2016 and December 2021, we retrospectively collected data from the electronic medical records of Chi Mei Medical Center, comprising 2260 TBI patients admitted to the ICU. A total of 42 features were incorporated into the analysis using four different machine learning models, which were then segmented into various feature combinations. The predictive performance was assessed using the area under the curve (AUC) of the receiver operating characteristic (ROC) curve and validated using the Delong test. Result: The AUC for each model under different feature combinations ranged from 0.877 (logistic regression with 14 features) to 0.921 (random forest with 22 features). The Delong test indicated that the predictive performance of the machine learning models is better than that of traditional tools such as APACHE II and SOFA scores. Conclusion: Our machine learning training demonstrated that the predictive accuracy of the LightGBM is better than that of APACHE II and SOFA scores. These features are readily available on the first day of patient admission to the ICU. By integrating this model into the clinical platform, we can offer clinicians an immediate prognosis for the patient, thereby establishing a bridge for educating and communicating with family members. Full article
Show Figures

Figure 1

17 pages, 2829 KiB  
Article
Implementing AI Models for Prognostic Predictions in High-Risk Burn Patients
by Chin-Choon Yeh, Yu-San Lin, Chun-Chia Chen and Chung-Feng Liu
Diagnostics 2023, 13(18), 2984; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics13182984 - 18 Sep 2023
Cited by 1 | Viewed by 1336
Abstract
Background and Objectives: Burn injuries range from minor medical issues to severe, life-threatening conditions. The severity and location of the burn dictate its treatment; while minor burns might be treatable at home, severe burns necessitate medical intervention, sometimes in specialized burn centers with [...] Read more.
Background and Objectives: Burn injuries range from minor medical issues to severe, life-threatening conditions. The severity and location of the burn dictate its treatment; while minor burns might be treatable at home, severe burns necessitate medical intervention, sometimes in specialized burn centers with extended follow-up care. This study aims to leverage artificial intelligence (AI)/machine learning (ML) to forecast potential adverse effects in burn patients. Methods: This retrospective analysis considered burn patients admitted to Chi Mei Medical Center from 2010 to 2019. The study employed 14 features, comprising supplementary information like prior comorbidities and laboratory results, for building models for predicting graft surgery, a prolonged hospital stay, and overall adverse effects. Overall, 70% of the data set trained the AI models, with the remaining 30% reserved for testing. Three ML algorithms of random forest, LightGBM, and logistic regression were employed with evaluation metrics of accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curve (AUC). Results: In this research, out of 224 patients assessed, the random forest model yielded the highest AUC for predictions related to prolonged hospital stays (>14 days) at 81.1%, followed by the XGBoost (79.9%) and LightGBM (79.5%) models. Besides, the random forest model of the need for a skin graft showed the highest AUC (78.8%), while the random forest model and XGBoost model of the occurrence of adverse complications both demonstrated the highest AUC (87.2%) as well. Based on the best models with the highest AUC values, an AI prediction system is designed and integrated into hospital information systems to assist physicians in the decision-making process. Conclusions: AI techniques showcased exceptional capabilities for predicting a prolonged hospital stay, the need for a skin graft, and the occurrence of overall adverse complications for burn patients. The insights from our study fuel optimism for the inception of a novel predictive model that can seamlessly meld with hospital information systems, enhancing clinical decisions and bolstering physician–patient dialogues. Full article
Show Figures

Figure 1

12 pages, 1554 KiB  
Article
Clinical Decision Support System to Detect the Occurrence of Ventilator-Associated Pneumonia in Pediatric Intensive Care
by Jerome Rambaud, Masoumeh Sajedi, Sally Al Omar, Maryline Chomtom, Michael Sauthier, Simon De Montigny and Philippe Jouvet
Diagnostics 2023, 13(18), 2983; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics13182983 - 18 Sep 2023
Cited by 1 | Viewed by 835
Abstract
Objectives: Ventilator-associated pneumonia (VAP) is a severe care-related disease. The Centers for Disease Control defined the diagnosis criteria; however, the pediatric criteria are mainly subjective and retrospective. Clinical decision support systems have recently been developed in healthcare to help the physician to be [...] Read more.
Objectives: Ventilator-associated pneumonia (VAP) is a severe care-related disease. The Centers for Disease Control defined the diagnosis criteria; however, the pediatric criteria are mainly subjective and retrospective. Clinical decision support systems have recently been developed in healthcare to help the physician to be more accurate for the early detection of severe pathology. We aimed at developing a predictive model to provide early diagnosis of VAP at the bedside in a pediatric intensive care unit (PICU). Methods: We performed a retrospective single-center study at a tertiary-care pediatric teaching hospital. All patients treated by invasive mechanical ventilation between September 2013 and October 2019 were included. Data were collected in the PICU electronic medical record and high-resolution research database. Development of the clinical decision support was then performed using open-access R software (Version 3.6.1®). Measurements and main results: In total, 2077 children were mechanically ventilated. We identified 827 episodes with almost 48 h of mechanical invasive ventilation and 77 patients who suffered from at least one VAP event. We split our database at the patient level in a training set of 461 patients free of VAP and 45 patients with VAP and in a testing set of 199 patients free of VAP and 20 patients with VAP. The Imbalanced Random Forest model was considered as the best fit with an area under the ROC curve from fitting the Imbalanced Random Forest model on the testing set being 0.82 (95% CI: (0.71, 0.93)). An optimal threshold of 0.41 gave a sensitivity of 79.7% and a specificity of 72.7%, with a positive predictive value (PPV) of 9% and a negative predictive value of 99%, and with an accuracy of 79.5% (95% CI: (0.77, 0.82)). Conclusions: Using machine learning, we developed a clinical predictive algorithm based on clinical data stored prospectively in a database. The next step will be to implement the algorithm in PICUs to provide early, automatic detection of ventilator-associated pneumonia. Full article
Show Figures

Figure 1

12 pages, 5711 KiB  
Article
Video-Based versus On-Site Neonatal Pain Assessment in Neonatal Intensive Care Units: The Impact of Video-Based Neonatal Pain Assessment in Real-World Scenario on Pain Diagnosis and Its Artificial Intelligence Application
by Xiaofei Chen, Huaiyu Zhu, Linli Mei, Qi Shu, Xiaoying Cheng, Feixiang Luo, Yisheng Zhao, Shuohui Chen and Yun Pan
Diagnostics 2023, 13(16), 2661; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics13162661 - 12 Aug 2023
Viewed by 1238
Abstract
Background: Neonatal pain assessment (NPA) represents a huge global problem of essential importance, as a timely and accurate assessment of neonatal pain is indispensable for implementing pain management. Purpose: To investigate the consistency of pain scores derived through video-based NPA (VB-NPA) and on-site [...] Read more.
Background: Neonatal pain assessment (NPA) represents a huge global problem of essential importance, as a timely and accurate assessment of neonatal pain is indispensable for implementing pain management. Purpose: To investigate the consistency of pain scores derived through video-based NPA (VB-NPA) and on-site NPA (OS-NPA), providing the scientific foundation and feasibility of adopting VB-NPA results in a real-world scenario as the gold standard for neonatal pain in clinical studies and labels for artificial intelligence (AI)-based NPA (AI-NPA) applications. Setting: A total of 598 neonates were recruited from a pediatric hospital in China. Methods: This observational study recorded 598 neonates who underwent one of 10 painful procedures, including arterial blood sampling, heel blood sampling, fingertip blood sampling, intravenous injection, subcutaneous injection, peripheral intravenous cannulation, nasopharyngeal suctioning, retention enema, adhesive removal, and wound dressing. Two experienced nurses performed OS-NPA and VB-NPA at a 10-day interval through double-blind scoring using the Neonatal Infant Pain Scale to evaluate the pain level of the neonates. Intra-rater and inter-rater reliability were calculated and analyzed, and a paired samples t-test was used to explore the bias and consistency of the assessors’ pain scores derived through OS-NPA and VB-NPA. The impact of different label sources was evaluated using three state-of-the-art AI methods trained with labels given by OS-NPA and VB-NPA, respectively. Results: The intra-rater reliability of the same assessor was 0.976–0.983 across different times, as measured by the intraclass correlation coefficient. The inter-rater reliability was 0.983 for single measures and 0.992 for average measures. No significant differences were observed between the OS-NPA scores and the assessment of an independent VB-NPA assessor. The different label sources only caused a limited accuracy loss of 0.022–0.044 for the three AI methods. Conclusion: VB-NPA in a real-world scenario is an effective way to assess neonatal pain due to its high intra-rater and inter-rater reliability compared to OS-NPA and could be used for the labeling of large-scale NPA video databases for clinical studies and AI training. Full article
Show Figures

Figure 1

12 pages, 1804 KiB  
Article
Exploiting Machine Learning Technologies to Study the Compound Effects of Serum Creatinine and Electrolytes on the Risk of Acute Kidney Injury in Intensive Care Units
by Hsin-Hung Liu, Yu-Tseng Wang, Meng-Han Yang, Wei-Shu Kevin Lin and Yen-Jen Oyang
Diagnostics 2023, 13(15), 2551; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics13152551 - 31 Jul 2023
Viewed by 856
Abstract
Assessing the risk of acute kidney injury (AKI) has been a challenging issue for clinicians in intensive care units (ICUs). In recent years, a number of studies have been conducted to investigate the associations between several serum electrolytes and AKI. Nevertheless, the compound [...] Read more.
Assessing the risk of acute kidney injury (AKI) has been a challenging issue for clinicians in intensive care units (ICUs). In recent years, a number of studies have been conducted to investigate the associations between several serum electrolytes and AKI. Nevertheless, the compound effects of serum creatinine, blood urea nitrogen (BUN), and clinically relevant serum electrolytes have yet to be comprehensively investigated. Accordingly, we initiated this study aiming to develop machine learning models that illustrate how these factors interact with each other. In particular, we focused on ICU patients without a prior history of AKI or AKI-related comorbidities. With this practice, we were able to examine the associations between the levels of serum electrolytes and renal function in a more controlled manner. Our analyses revealed that the levels of serum creatinine, chloride, and magnesium were the three major factors to be monitored for this group of patients. In summary, our results can provide valuable insights for developing early intervention and effective management strategies as well as crucial clues for future investigations of the pathophysiological mechanisms that are involved. In future studies, subgroup analyses based on different causes of AKI should be conducted to further enhance our understanding of AKI. Full article
Show Figures

Figure 1

12 pages, 1445 KiB  
Article
Applicability of American College of Radiology Appropriateness Criteria Decision-Making Model for Acute Appendicitis Diagnosis in Children
by Ozum Tuncyurek, Koray Kadam, Berna Uzun and Dilber Uzun Ozsahin
Diagnostics 2022, 12(12), 2915; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics12122915 - 23 Nov 2022
Cited by 2 | Viewed by 1056
Abstract
Acute appendicitis is one of the most common causes of abdominal pain in the emergency department and the most common surgical emergency reason for children younger than 15 years of age, which could be enormously dangerous when ruptured. The choice of radiological approach [...] Read more.
Acute appendicitis is one of the most common causes of abdominal pain in the emergency department and the most common surgical emergency reason for children younger than 15 years of age, which could be enormously dangerous when ruptured. The choice of radiological approach is very important for the diagnosis. In this way, unnecessary surgery is avoided. The aim of this study was to examine the validity of the American College of Radiology appropriateness criteria for radiological imaging in diagnosing acute appendicitis with multivariate decision criteria. In our study, pediatric patients who presented to the emergency department with abdominal pain were grouped according to the Appendicitis Inflammatory Response (AIR) score and the choice of radiological examinations was evaluated with fuzzy-based Preference Ranking Organization Method for Enrichment Evaluation (PROMETHEE) and with the fuzzy-based Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) model for the validation of the results. As a result of this study, non-contrast computed tomography (CT) was recommended as the first choice for patients with low AIR score (where Φnet=0.0733) and with high AIR scores (where Φnet=0.0702) while ultrasound (US) examination was ranked third in patients with high scores. While computed tomography is at the forefront with many criteria used in the study, it is still a remarkable practice that US examination is in the first place in daily routine. Even though there are studies showing the strengths of these tools, this study is unique in that it provides analytical ranking results for this complex decision-making issue and shows the strengths and weaknesses of each alternative for different scenarios, even considering vague information for the acute appendicitis diagnosis in children for different scenarios. Full article
Show Figures

Figure 1

19 pages, 3984 KiB  
Article
Prognostic Model of ICU Admission Risk in Patients with COVID-19 Infection Using Machine Learning
by Khandaker Reajul Islam, Jaya Kumar, Toh Leong Tan, Mamun Bin Ibne Reaz, Tawsifur Rahman, Amith Khandakar, Tariq Abbas, Md. Sakib Abrar Hossain, Susu M. Zughaier and Muhammad E. H. Chowdhury
Diagnostics 2022, 12(9), 2144; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics12092144 - 03 Sep 2022
Cited by 4 | Viewed by 1834
Abstract
With the onset of the COVID-19 pandemic, the number of critically sick patients in intensive care units (ICUs) has increased worldwide, putting a burden on ICUs. Early prediction of ICU requirement is crucial for efficient resource management and distribution. Early-prediction scoring systems for [...] Read more.
With the onset of the COVID-19 pandemic, the number of critically sick patients in intensive care units (ICUs) has increased worldwide, putting a burden on ICUs. Early prediction of ICU requirement is crucial for efficient resource management and distribution. Early-prediction scoring systems for critically ill patients using mathematical models are available, but are not generalized for COVID-19 and Non-COVID patients. This study aims to develop a generalized and reliable prognostic model for ICU admission for both COVID-19 and non-COVID-19 patients using best feature combination from the patient data at admission. A retrospective cohort study was conducted on a dataset collected from the pulmonology department of Moscow City State Hospital between 20 April 2020 and 5 June 2020. The dataset contains ten clinical features for 231 patients, of whom 100 patients were transferred to ICU and 131 were stable (non-ICU) patients. There were 156 COVID positive patients and 75 non-COVID patients. Different feature selection techniques were investigated, and a stacking machine learning model was proposed and compared with eight different classification algorithms to detect risk of need for ICU admission for both COVID-19 and non-COVID patients combined and COVID patients alone. C-reactive protein (CRP), chest computed tomography (CT), lung tissue affected (%), age, admission to hospital, and fibrinogen parameters at hospital admission were found to be important features for ICU-requirement risk prediction. The best performance was produced by the stacking approach, with weighted precision, sensitivity, F1-score, specificity, and overall accuracy of 84.45%, 84.48%, 83.64%, 84.47%, and 84.48%, respectively, for both types of patients, and 85.34%, 85.35%, 85.11%, 85.34%, and 85.35%, respectively, for COVID-19 patients only. The proposed work can help doctors to improve management through early prediction of the risk of need for ICU admission of patients during the COVID-19 pandemic, as the model can be used for both types of patients. Full article
Show Figures

Figure 1

12 pages, 3999 KiB  
Article
Artificial Intelligence Based Pain Assessment Technology in Clinical Application of Real-World Neonatal Blood Sampling
by Xiaoying Cheng, Huaiyu Zhu, Linli Mei, Feixiang Luo, Xiaofei Chen, Yisheng Zhao, Shuohui Chen and Yun Pan
Diagnostics 2022, 12(8), 1831; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics12081831 - 29 Jul 2022
Cited by 4 | Viewed by 2234
Abstract
Background: Accurate neonatal pain assessment (NPA) is the key to neonatal pain management, yet it is a challenging task for medical staff. This study aimed to analyze the clinical practicability of the artificial intelligence based NPA (AI-NPA) tool for real-world blood sampling. Method: [...] Read more.
Background: Accurate neonatal pain assessment (NPA) is the key to neonatal pain management, yet it is a challenging task for medical staff. This study aimed to analyze the clinical practicability of the artificial intelligence based NPA (AI-NPA) tool for real-world blood sampling. Method: We performed a prospective study to analyze the consistency of the NPA results given by a self-developed automated NPA system and nurses’ on-site NPAs (OS-NPAs) for 232 newborns during blood sampling in neonatal wards, where the neonatal infant pain scale (NIPS) was used for evaluation. Spearman correlation analysis and the degree of agreement of the pain score and pain grade derived by the NIPS were applied for statistical analysis. Results: Taking the OS-NPA results as the gold standard, the accuracies of the NIPS pain score and pain grade given by the automated NPA system were 88.79% and 95.25%, with kappa values of 0.92 and 0.90 (p < 0.001), respectively. Conclusion: The results of the automated NPA system for real-world neonatal blood sampling are highly consistent with the results of the OS-NPA. Considering the great advantages of automated NPA systems in repeatability, efficiency, and cost, it is worth popularizing the AI technique in NPA for precise and efficient neonatal pain management. Full article
Show Figures

Figure 1

13 pages, 1728 KiB  
Article
Establishment of ICU Mortality Risk Prediction Models with Machine Learning Algorithm Using MIMIC-IV Database
by Ke Pang, Liang Li, Wen Ouyang, Xing Liu and Yongzhong Tang
Diagnostics 2022, 12(5), 1068; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics12051068 - 24 Apr 2022
Cited by 4 | Viewed by 4159
Abstract
Objective: The mortality rate of critically ill patients in ICUs is relatively high. In order to evaluate patients’ mortality risk, different scoring systems are used to help clinicians assess prognosis in ICUs, such as the Acute Physiology and Chronic Health Evaluation III (APACHE [...] Read more.
Objective: The mortality rate of critically ill patients in ICUs is relatively high. In order to evaluate patients’ mortality risk, different scoring systems are used to help clinicians assess prognosis in ICUs, such as the Acute Physiology and Chronic Health Evaluation III (APACHE III) and the Logistic Organ Dysfunction Score (LODS). In this research, we aimed to establish and compare multiple machine learning models with physiology subscores of APACHE III—namely, the Acute Physiology Score III (APS III)—and LODS scoring systems in order to obtain better performance for ICU mortality prediction. Methods: A total number of 67,748 patients from the Medical Information Database for Intensive Care (MIMIC-IV) were enrolled, including 7055 deceased patients, and the same number of surviving patients were selected by the random downsampling technique, for a total of 14,110 patients included in the study. The enrolled patients were randomly divided into a training dataset (n = 9877) and a validation dataset (n = 4233). Fivefold cross-validation and grid search procedures were used to find and evaluate the best hyperparameters in different machine learning models. Taking the subscores of LODS and the physiology subscores that are part of the APACHE III scoring systems as input variables, four machine learning methods of XGBoost, logistic regression, support vector machine, and decision tree were used to establish ICU mortality prediction models, with AUCs as metrics. AUCs, specificity, sensitivity, positive predictive value, negative predictive value, and calibration curves were used to find the best model. Results: For the prediction of mortality risk in ICU patients, the AUC of the XGBoost model was 0.918 (95%CI, 0.915–0.922), and the AUCs of logistic regression, SVM, and decision tree were 0.872 (95%CI, 0.867–0.877), 0.872 (95%CI, 0.867–0.877), and 0.852 (95%CI, 0.847–0.857), respectively. The calibration curves of logistic regression and support vector machine performed better than the other two models in the ranges 0–40% and 70%–100%, respectively, while XGBoost performed better in the range of 40–70%. Conclusions: The mortality risk of ICU patients can be better predicted by the characteristics of the Acute Physiology Score III and the Logistic Organ Dysfunction Score with XGBoost in terms of ROC curve, sensitivity, and specificity. The XGBoost model could assist clinicians in judging in-hospital outcome of critically ill patients, especially in patients with a more uncertain survival outcome. Full article
Show Figures

Figure 1

Back to TopTop