A hybrid hierarchical decision support system for cardiac surgical intensive care patients. Part II. Clinical implementation and evaluation

Developing a Clinical Decision Support System for Prediction Postoperative Coronary Artery Bypass Grafting Infection in Diabetic Patients

BACKGROUND

Postoperative infection in Coronary Artery Bypass Graft (CABG) is one of the most common complications for diabetic patients, due to an increase in the hospitalization and cost. To address these issues, it is necessary to apply some solutions.

OBJECTIVE

The study aimed to the development of a Clinical Decision Support System (CDSS) for predicting the CABG postoperative infection in diabetic patients.

MATERIAL AND METHODS

This developmental study is conducted on a private hospital in Tehran in 2016. From 1061 CABG surgery medical records, we selected 210 cases randomly. After data gathering, we used statistical tests for selecting related features. Then an Artificial Neural Network (ANN), which was a one-layer perceptron network model and a supervised training algorithm with gradient descent, was constructed using MATLAB software. The software was then developed and tested using the receiver operating characteristic (ROC) diagram and the confusion matrix.

RESULTS

Based on the correlation analysis, from 28 variables in the data, 20 variables had a significant relationship with infection after CABG (P<0.05). The results of the confusion matrix showed that the sensitivity of the system was 69%, and the specificity and the accuracy were 97% and 84%, respectively. The Receiver Operating Characteristic (ROC) diagram shows the appropriate performance of the CDSS.

CONCLUSION

The use of CDSS can play an important role in predicting infection after CABG in patients with diabetes. The designed software can be used as a supporting tool for physicians to predict infections caused by CABG in diabetic patients as a susceptible group. However, other factors affecting infection must also be considered for accurate prediction.

Moving from bytes to bedside: a systematic review on the use of artificial intelligence in the intensive care unit

PURPOSE

Due to the increasing demand for intensive care unit (ICU) treatment, and to improve quality and efficiency of care, there is a need for adequate and efficient clinical decision-making. The advancement of artificial intelligence (AI) technologies has resulted in the development of prediction models, which might aid clinical decision-making. This systematic review seeks to give a contemporary overview of the current maturity of AI in the ICU, the research methods behind these studies, and the risk of bias in these studies.

METHODS

A systematic search was conducted in Embase, Medline, Web of Science Core Collection and Cochrane Central Register of Controlled Trials databases to identify eligible studies. Studies using AI to analyze ICU data were considered eligible. Specifically, the study design, study aim, dataset size, level of validation, level of readiness, and the outcomes of clinical trials were extracted. Risk of bias in individual studies was evaluated by the Prediction model Risk Of Bias ASsessment Tool (PROBAST).

RESULTS

Out of 6455 studies identified through literature search, 494 were included. The most common study design was retrospective [476 studies (96.4% of all studies)] followed by prospective observational [8 (1.6%)] and clinical [10 (2%)] trials. 378 (80.9%) retrospective studies were classified as high risk of bias. No studies were identified that reported on the outcome evaluation of an AI model integrated in routine clinical practice.

CONCLUSION

The vast majority of developed ICU-AI models remain within the testing and prototyping environment; only a handful were actually evaluated in clinical practice. A uniform and structured approach can support the development, safe delivery, and implementation of AI to determine clinical benefit in the ICU.

Assessment of the time-dependent need for stay in a high dependency unit (HDU) after major surgery by using data from an anesthesia information management system

Admittance to a high dependency unit (HDU) is expensive. Patients who receive surgical treatment with 'low anterior resection of the rectum' (LAR) or 'abdominoperineal resection of the rectum' (APR) at our hospital are routinely treated in an HDU the first 16-24 h of the postoperative (PO) period. The aim of this study was to describe the extent of HDU-specific interventions given. We included patients treated with LAR or APR at the St. Olav University Hospital (Trondheim, Norway) over a 1-year period. Physiologic data and HDU-interventions recorded during the PO-period were obtained from the anesthesia information management system (AIMS). HDU-specific interventions were defined as the need for respiratory support, fluid replacement therapy >500 ml/h, vasoactive medications, or a need for high dose opioids (morphine >7.5 mg/h i.v.). Sixty-two patients were included. Most patients needed HDU-specific interventions during the first 6 h of the PO period. After this, one-third of the patients needed one or more of the HDU-specific interventions for shorter periods of time. Another one-third of the patients had a need for HDU-specific therapies for more than ten consecutive hours, primarily an infusion of nor-epinephrine. Most patients treated with LAR or APR was in need of an HDU-specific intervention during the first 6 h of the PO-period, with a marked decline after this time period. The applied methodology, using an AIMS, demonstrates that there is great variability in individual patients' postoperative needs after major surgery, and that these needs are dynamic in their nature.

Adaptive multi-infusion decision support for the multivariable circulatory management of critically ill patients

We have developed a novel adaptive multi-infusion advisory system for circulatory management of critically ill patients which co-ordinates infusion adjustments to ensure safe trajectories. This system should reduce patient hospital stay and improve patient outcome by enhancing the quality of patient circulatory control; alleviating the clinical cognitive load, giving staff more time for direct patient care, while also reducing infusion adjustment errors. We have applied three derived circulatory variables which relate to the three main types of cardiovascular infusions (inotropic, vasoactive and fluid). A lumped parameter steady flow model of the human circulatory system and the effects of cardiovascular infusions was constructed for algorithm development, clinical experts providing feedback on a representative test set of simulated patients in circulatory shock. Independent self-learning fuzzy logic controllers (SLFLC) were found to give good adaptation to variable patient infusion sensitivities. A supervisory, rule-based module co-ordinates infusion adjustments to ensure safe circulatory trajectories. Monitoring of manual infusion adjustments allows timely advice and also a critiquing capability which can train junior staff and reduce infusion adjustment errors. A physical mock circulatory loop was used to construct and test our physical advisory system. Preliminary clinical results show good clinical utility of our adaptive multi-infusion advisory system.