Which model is superior in predicting ICU survival: artificial intelligence versus conventional approaches

Machine learning algorithm for predict the in-hospital mortality in critically ill patients with congestive heart failure combined with chronic kidney disease

BACKGROUND

The objective of this study was to develop and validate a machine learning (ML) model for predict in-hospital mortality among critically ill patients with congestive heart failure (CHF) combined with chronic kidney disease (CKD).

METHODS

After employing least absolute shrinkage and selection operator regression for feature selection, six distinct methodologies were employed in the construction of the model. The selection of the optimal model was based on the area under the curve (AUC). Furthermore, the interpretation of the chosen model was facilitated through the utilization of SHapley Additive exPlanation (SHAP) values and the Local Interpretable Model-Agnostic Explanations (LIME) algorithm.

RESULTS

This study collected data and enrolled 5041 patients on CHF combined with CKD from 2008 to 2019, utilizing the Medical Information Mart for Intensive Care Unit. After selection, 22 of the 47 variables collected post-intensive care unit admission were identified as mortality-associated and subsequently utilized in the development of ML models. Among the six models generated, the eXtreme Gradient Boosting (XGBoost) model demonstrated the highest AUC at 0.837. Notably, the SHAP values highlighted the sequential organ failure assessment score, age, simplified acute physiology score II, and urine output as the four most influential variables in the XGBoost model. In addition, the LIME algorithm explains the individualized predictions.

CONCLUSIONS

In conclusion, our study accomplished the successful development and validation of ML models for predicting in-hospital mortality in critically ill patients with CHF combined with CKD. Notably, the XGBoost model emerged as the most efficacious among all the ML models employed.

Prediction of acute methanol poisoning prognosis using machine learning techniques

Methanol poisoning is a global public health concern, especially prevalent in developing nations. This study focuses on predicting the severity of methanol intoxication using machine learning techniques, aiming to improve early identification and prognosis assessment. The study, conducted at Loghman Hakim Hospital in Tehran, Iran. The data pertaining to individuals afflicted with methanol poisoning was retrieved retrospectively and divided into training and test groups at a ratio of 70:30. The selected features were then inputted into various machine learning methods. The models were implemented using the Scikit-learn library in the Python programming language. Ultimately, the efficacy of the developed models was assessed through ten-fold cross-validation techniques and specific evaluation criteria, with a confidence level of 95%. A total number of 897 patients were included and divided in three groups including without sequel (n = 573), with sequel (n = 234), and patients who died (n = 90). The two-step feature selection was yielded 43 features in first step and 23 features in second step. In best model (Gradient Boosting Classifier) test dataset metric by 32 features younger age, higher methanol ingestion, respiratory symptoms, lower GCS scores, type of visual symptom, duration of therapeutic intervention, ICU admission, and elevated CPK levels were among the most important features predicting the prognosis of methanol poisoning. The Gradient Boosting Classifier demonstrated the highest predictive capability, achieving AUC values of 0.947 and 0.943 in the test dataset with 43 and 23 features, respectively. This research introduces a machine learning-driven prognostic model for methanol poisoning, demonstrating superior predictive capabilities compared to traditional statistical methods. The identified features provide valuable insights for early intervention and personalized treatment strategies.

The Evolution and Future of Intensive Care Management in the Era of Telecritical Care and Artificial Intelligence

Critical care practice has been embodied in the healthcare system since the institutionalization of intensive care units (ICUs) in the late '50s. Over time, this sector has experienced many changes and improvements in providing immediate and dedicated healthcare as patients requiring intensive care are often frail and critically ill with high mortality and morbidity rates. These changes were aided by innovations in diagnostic, therapeutic, and monitoring technologies, as well as the implementation of evidence-based guidelines and organizational structures within the ICU. In this review, we examine these changes in intensive care management over the past 40 years and their impact on the quality of care available to patients. Moreover, the current state of intensive care management is characterized by a multidisciplinary approach and the use of innovative technologies and research databases. Advancements such as telecritical care and artificial intelligence are being increasingly explored, especially since the COVID-19 pandemic, to reduce the length of hospitalization and ICU mortality. With these advancements in intensive care and ever-changing patient needs, critical care experts, hospital managers, and policymakers must also explore appropriate organizational structures and future enhancements within the ICU.

Precision oncology: Artificial intelligence, circulating cell-free DNA, and the minimally invasive detection of pancreatic cancer-A pilot study

BACKGROUND

Pancreatic cancer (PC) is among the most lethal cancers. The lack of effective tools for early detection results in late tumor detection and, consequently, high mortality rate. Precision oncology aims to develop targeted individual treatments based on advanced computational approaches of omics data. Biomarkers, such as global alteration of cytosine (CpG) methylation, can be pivotal for these objectives. In this study, we performed DNA methylation profiling of pancreatic cancer patients using circulating cell-free DNA (cfDNA) and artificial intelligence (AI) including Deep Learning (DL) for minimally invasive detection to elucidate the epigenetic pathogenesis of PC.

METHODS

The Illumina Infinium HD Assay was used for genome-wide DNA methylation profiling of cfDNA in treatment-naïve patients. Six AI algorithms were used to determine PC detection accuracy based on cytosine (CpG) methylation markers. Additional strategies for minimizing overfitting were employed. The molecular pathogenesis was interrogated using enrichment analysis.

RESULTS

In total, we identified 4556 significantly differentially methylated CpGs (q-value < 0.05; Bonferroni correction) in PC versus controls. Highly accurate PC detection was achieved with all 6 AI platforms (Area under the receiver operator characteristics curve [0.90-1.00]). For example, DL achieved AUC (95% CI): 1.00 (0.95-1.00), with a sensitivity and specificity of 100%. A separate modeling approach based on logistic regression-based yielded an AUC (95% CI) 1.0 (1.0-1.0) with a sensitivity and specificity of 100% for PC detection. The top four biological pathways that were epigenetically altered in PC and are known to be linked with cancer are discussed.

CONCLUSION

Using a minimally invasive approach, AI, and epigenetic analysis of circulating cfDNA, high predictive accuracy for PC was achieved. From a clinical perspective, our findings suggest that that early detection leading to improved overall survival may be achievable in the future.

Prediction of acute organophosphate poisoning severity using machine learning techniques

Poisoning with organophosphate compounds is a significant public health risk, especially in developing countries. Considering the importance of early and accurate prediction of organophosphate poisoning prognosis, the aim of this study was to develop a machine learning-based prediction model to predict the severity of organophosphate poisoning. The data of patients with organophosphate poisoning were retrospectively extracted and split into training and test sets in a ratio of 70:30. The feature selection was done by least absolute shrinkage and selection operator method. Selected features were fed into five machine learning techniques, including Histogram Boosting Gradient, eXtreme Gradient Boosting, K-Nearest Neighborhood, Support Vector Machine (SVM) (kernel = linear), and Random Forest. The Scikit-learn library in Python programming language was used to implement the models. Finally, the performance of developed models was measured using ten-fold cross-validation methods and some evaluation criteria with 95 % confidence intervals. A total of 1237 patients were used to train and test the machine learning models. According to the criteria determining severe organophosphate poisoning, 732 patients were assigned to group 1 (patients with mild to moderate poisoning) and 505 patients were assigned to group 2 (patients with severe poisoning). With an AUC value of 0.907 (95 % CI 0.89-0.92), the model developed using XGBoost outperformed other models. Feature importance evaluation found that venous blood gas-pH, white blood cells, and plasma cholinesterase activity were the top three variables that contribute the most to the prediction performance of the prognosis in patients with organophosphate poisoning. XGBoost model yield an accuracy of 90.1 % (95 % CI 0.891-0.918), specificity of 91.4 % (95 % CI 0.90-0.92), a sensitivity of 89.5 % (95 % CI 0.87-0.91), F-measure of 91.2 % (95 % CI 0.90-0.921), and Kappa statistic of 91.2 % (95 % CI 0.90-0.92). The machine learning-based prediction models can accurately predict the severity of organophosphate poisoning. Based on feature selection techniques, the most important predictors of organophosphate poisoning were VBG-pH, white blood cell count, plasma cholinesterase activity, VBG-BE, and age. The best algorithm with the highest predictive performance was the XGBoost classifier.