Towards an automated multimodal clinical decision support system at the post anesthesia care unit

Remote Monitoring and Artificial Intelligence: Outlook for 2050

Remote monitoring and artificial intelligence will become common and intertwined in anesthesiology by 2050. In the intraoperative period, technology will lead to the development of integrated monitoring systems that will integrate multiple data streams and allow anesthesiologists to track patients more effectively. This will free up anesthesiologists to focus on more complex tasks, such as managing risk and making value-based decisions. This will also enable the continued integration of remote monitoring and control towers having profound effects on coverage and practice models. In the PACU and ICU, the technology will lead to the development of early warning systems that can identify patients who are at risk of complications, enabling early interventions and more proactive care. The integration of augmented reality will allow for better integration of diverse types of data and better decision-making. Postoperatively, the proliferation of wearable devices that can monitor patient vital signs and track their progress will allow patients to be discharged from the hospital sooner and receive care at home. This will require increased use of telemedicine, which will allow patients to consult with doctors remotely. All of these advances will require changes to legal and regulatory frameworks that will enable new workflows that are different from those familiar to today's providers.

How anesthesiology can deal with innovation and new technologies?

Innovation and new technologies have always impacted significantly the anesthesiology practice all along the perioperative course, as it is recognized as one of the most transformative medical specialties specifically regarding patient's safety. Beside a number of major changes in procedures, equipment, training, and organization that aggregated to establish a strong safety culture with effective practices, anesthesiology is also a stakeholder in disruptive innovation. The present review is not exhaustive and aims to provide an overview on how innovation could change and improve anesthesiology practices through some examples as telemedicine (TM), machine learning and artificial intelligence (AI). For example, postoperative complications can be accurately predicted by AI from automated real-time electronic health record data, matching physicians' predictive accuracy. Clinical workflow could be facilitated and accelerated with mobile devices and applications, assuming that these tools should remain at the service of patients and care providers. Care providers and patients connections have improved, thanks to these digital and innovative transformations, without replacing existing relationships between them. It also should give time back to physicians and nurses to better spend it in the perioperative care, and to provide "personalized" medicine keeping a high level of standard of care.

The effect of technical filtering and clinical criteria on alert rates from continuous vital sign monitoring in the general ward

OBJECTIVES

Continuous vital sign monitoring at the general hospital ward has major potential advantages over intermittent monitoring but generates many alerts with risk of alert fatigue. We hypothesized that the number of alerts would decrease using different filters.

METHODS

This study was an exploratory analysis of the alert reducing effect from adding two different filters to continuously collected vital sign data (peripheral oxygen saturation, blood pressure, heart rate, and respiratory rate) in patients admitted after major surgery or severe medical disease. Filtered data were compared to data without artifact removal. Filter one consists of artifact removal, filter two consists of artifact removal plus duration criteria adjusted for severity of vital sign deviation. Alert thresholds were based on the National Early Warning Score (NEWS) threshold.

RESULTS

A population of 716 patients admitted for severe medical disease or major surgery with continuous wireless vital sign monitoring at the general ward with a mean monitoring time of 75.8 h, were included for the analysis. Without artifact removal, we found a median of 137 [IQR: 87-188] alerts per patient/day, artifact removal resulted in a median of 101 [IQR: 56-160] alerts per patient/day and with artifact removal combined with a duration-severity criterion, we found a median of 19 [IQR: 9-34] alerts per patient/day. Reduction of alerts was 86.4% (p < 0.001) for values without artifact removal (137 alerts) vs. the duration criteria and a reduction (19 alerts) of 81.5% (p < 0.001) for the criteria with artifact removal (101 alerts) vs. the duration criteria (19 alerts).

CONCLUSION

We conclude that a combination of artifact removal and duration-severity criteria approach substantially reduces alerts generated by continuous vital sign monitoring.

Associations between clinical interventions and transcutaneous blood gas values in postoperative patients

PURPOSE

Postoperative monitoring of circulation and respiration is pivotal to guide intervention strategies and ensure patient outcomes. Transcutaneous blood gas monitoring (TCM) may allow for noninvasive assessment of changes in cardiopulmonary function after surgery, including a more direct assessment of local micro-perfusion and metabolism. To form the basis for studies assessing the clinical impact of TCM complication detection and goal-directed-therapy, we examined the association between clinical interventions in the postoperative period and changes in transcutaneous blood gasses.

METHODS

Two-hundred adult patients who have had major surgery were enrolled prospectively and monitored with transcutaneous blood gas measurements (oxygen (TcPO2) and carbon dioxide (TcPCO2)) for 2 h in the post anaesthesia care unit, with recording of all clinical interventions. The primary outcome was changes in TcPO2, secondarily TcPCO2, from 5 min before a clinical intervention versus 5 min after, analysed with paired t-test.

RESULTS

Data from 190 patients with 686 interventions were analysed. During clinical interventions, a mean change in TcPO2 of 0.99 mmHg (95% CI-1.79-0.2, p = 0.015) and TcPCO2 of-0.67 mmHg (95% CI 0.36-0.98, p < 0.001) was detected.

CONCLUSION

Clinical interventions resulted in significant changes in transcutaneous oxygen and carbon dioxide. These findings suggest future studies to assess the clinical value of changes in transcutaneous PO2 and PCO2 in a postoperative setting.

TRIAL REGISTRY

Clinical trial number: NCT04735380.

CLINICAL TRIAL REGISTRY

https://clinicaltrials.gov/ct2/show/NCT04735380.

Exploring Artificial Intelligence in Anesthesia: A Primer on Ethics, and Clinical Applications

The field of anesthesia has always been at the forefront of innovation and technology, and the integration of Artificial Intelligence (AI) represents the next frontier in anesthesia care. The use of AI and its subtypes, such as machine learning, has the potential to improve efficiency, reduce costs, and ameliorate patient outcomes. AI can assist with decision making, but its primary advantage lies in empowering anesthesiologists to adopt a proactive approach to address clinical issues. The potential uses of AI in anesthesia can be schematically grouped into clinical decision support and pharmacologic and mechanical robotic applications. Tele-anesthesia includes strategies of telemedicine, as well as device networking, for improving logistics in the operating room, and augmented reality approaches for training and assistance. Despite the growing scientific interest, further research and validation are needed to fully understand the benefits and limitations of these applications in clinical practice. Moreover, the ethical implications of AI in anesthesia must also be considered to ensure that patient safety and privacy are not compromised. This paper aims to provide a comprehensive overview of AI in anesthesia, including its current and potential applications, and the ethical considerations that must be considered to ensure the safe and effective use of the technology.

The United Kingdom's National Early Warning Score: should everyone use it? A narrative review

This review critiques the benefits and drawbacks of the United Kingdom's National Early Warning Score (NEWS). Potential developments for the future are considered, as well as the role for NEWS in an emergency department (ED). The ability of NEWS to predict death within 24 h has been well validated in multiple clinical settings. It provides a common language for the assessment of clinical severity and can be used to trigger clinical interventions. However, it should not be used as the only metric for risk stratification as its ability to predict mortality beyond 24 h is not reliable and greatly influenced by other factors. The main drawbacks of NEWS are that measuring it requires trained professionals, it is time consuming and prone to calculation error. NEWS is recommended for use in acute UK hospitals, where it is linked to an escalation policy that reflects postgraduate experience; patients with lower NEWS are first assessed by a junior clinician and those with higher scores by more senior staff. This policy was based on expert opinion that did not consider workload implications. Nevertheless, its implementation has been shown to improve the efficient recording of vital signs. How and who should respond to different NEWS levels is uncertain and may vary according to the clinical setting and resources available. In the ED, simple triage scores which are quicker and easier to use may be more appropriate determinants of acuity. However, any alternative to NEWS should be easier and cheaper to use and provide evidence of outcome improvement.

Evaluation of medical decision support systems (DDX generators) using real medical cases of varying complexity and origin

Background

Medical decision support systems (CDSSs) are increasingly used in medicine, but their utility in daily medical practice is difficult to evaluate. One variant of CDSS is a generator of differential diagnoses (DDx generator). We performed a feasibility study on three different, publicly available data sets of medical cases in order to identify the frequency in which two different DDx generators provide helpful information (either by providing a list of differential diagnosis or recognizing the expert diagnosis if available) for a given case report.

Methods

Used data sets were n = 105 cases from a web-based forum of telemedicine with real life cases from Afghanistan (Afghan data set; AD), n = 124 cases discussed in a web-based medical forum (Coliquio data set; CD). Both websites are restricted for medical professionals only. The third data set consisted 50 special case reports published in the New England Journal of Medicine (NEJM). After keyword extraction, data were entered into two different DDx generators (IsabelHealth (IH), Memem7 (M7)) to examine differences in target diagnosis recognition and physician-rated usefulness between DDx generators.

Results

Both DDx generators detected the target diagnosis equally successfully (all cases: M7, 83/170 (49%); IH 90/170 (53%), NEJM: M7, 28/50 (56%); IH, 34/50 (68%); differences n.s.). Differences occurred in AD, where detection of an expert diagnosis was less successful with IH than with M7 (29.7% vs. 54.1%, p = 0.003). In contrast, in CD IH performed significantly better than M7 (73.9% vs. 32.6%, p = 0.021). Congruent identification of target diagnosis occurred in only 46/170 (27.1%) of cases. However, a qualitative analysis of the DDx results revealed useful complements from using the two systems in parallel.

Conclusion

Both DDx systems IsabelHealth and Memem7 provided substantial help in finding a helpful list of differential diagnoses or identifying the target diagnosis either in standard cases or complicated and rare cases. Our pilot study highlights the need for different levels of complexity and types of real-world medical test cases, as there are significant differences between DDx generators away from traditional case reports. Combining different results from DDx generators seems to be a possible approach for future review and use of the systems.

Erroneous data: The Achilles' heel of AI and personalized medicine

This paper reviews dilemmas and implications of erroneous data for clinical implementation of AI. It is well-known that if erroneous and biased data are used to train AI, there is a risk of systematic error. However, even perfectly trained AI applications can produce faulty outputs if fed with erroneous inputs. To counter such problems, we suggest 3 steps: (1) AI should focus on data of the highest quality, in essence paraclinical data and digital images, (2) patients should be granted simple access to the input data that feed the AI, and granted a right to request changes to erroneous data, and (3) automated high-throughput methods for error-correction should be implemented in domains with faulty data when possible. Also, we conclude that erroneous data is a reality even for highly reputable Danish data sources, and thus, legal framework for the correction of errors is universally needed.

Explainable machine learning for real-time deterioration alert prediction to guide pre-emptive treatment

The Electronic Medical Record (EMR) provides an opportunity to manage patient care efficiently and accurately. This includes clinical decision support tools for the timely identification of adverse events or acute illnesses preceded by deterioration. This paper presents a machine learning-driven tool developed using real-time EMR data for identifying patients at high risk of reaching critical conditions that may demand immediate interventions. This tool provides a pre-emptive solution that can help busy clinicians to prioritize their efforts while evaluating the individual patient risk of deterioration. The tool also provides visualized explanation of the main contributing factors to its decisions, which can guide the choice of intervention. When applied to a test cohort of 18,648 patient records, the tool achieved 100% sensitivity for prediction windows 2–8 h in advance for patients that were identified at 95%, 85% and 70% risk of deterioration.

Prediction of severe adverse event from vital signs for post-operative patients

Monitoring post-operative patients is important for preventing severe adverse events (SAE), which increases morbidity and mortality. Conventional bedside monitoring system has demonstrated the difficulty in long term monitoring of those patients because majority of them are ambulatory. With development of wearable system and advanced data analytics, those patients would benefit greatly from continuous and predictive monitoring. In this study, we aim to predict SAE based on monitoring of vital signs. Heart rate, respiration rate, and blood oxygen saturation were continuously acquired by wearable devices and blood pressure was measured intermittently from 453 post-operative patients. SAEs from various complications were extracted from patients' database. The trends of vital signs were first extracted with moving average. Then four descriptive statistics were calculated from trend of each modality as features. Finally, a machine learning approach based on support vector machine was employed for prediction of SAE. It has shown the averaged accuracy of 89%, sensitivity of 80%, specificity of 93% and the area under receiver operating characteristic curve (AUROC) of 93%. These findings are promising and demonstrate the feasibility of predicting SAE from vital signs acquired with wearable devices and measured intermittently.

Machine Learning-Based Early Warning Systems for Clinical Deterioration: Systematic Scoping Review

Background

Timely identification of patients at a high risk of clinical deterioration is key to prioritizing care, allocating resources effectively, and preventing adverse outcomes. Vital signs–based, aggregate-weighted early warning systems are commonly used to predict the risk of outcomes related to cardiorespiratory instability and sepsis, which are strong predictors of poor outcomes and mortality. Machine learning models, which can incorporate trends and capture relationships among parameters that aggregate-weighted models cannot, have recently been showing promising results.

Objective

This study aimed to identify, summarize, and evaluate the available research, current state of utility, and challenges with machine learning–based early warning systems using vital signs to predict the risk of physiological deterioration in acutely ill patients, across acute and ambulatory care settings.

Methods

PubMed, CINAHL, Cochrane Library, Web of Science, Embase, and Google Scholar were searched for peer-reviewed, original studies with keywords related to “vital signs,” “clinical deterioration,” and “machine learning.” Included studies used patient vital signs along with demographics and described a machine learning model for predicting an outcome in acute and ambulatory care settings. Data were extracted following PRISMA, TRIPOD, and Cochrane Collaboration guidelines.

Results

We identified 24 peer-reviewed studies from 417 articles for inclusion; 23 studies were retrospective, while 1 was prospective in nature. Care settings included general wards, intensive care units, emergency departments, step-down units, medical assessment units, postanesthetic wards, and home care. Machine learning models including logistic regression, tree-based methods, kernel-based methods, and neural networks were most commonly used to predict the risk of deterioration. The area under the curve for models ranged from 0.57 to 0.97.

Conclusions

In studies that compared performance, reported results suggest that machine learning–based early warning systems can achieve greater accuracy than aggregate-weighted early warning systems but several areas for further research were identified. While these models have the potential to provide clinical decision support, there is a need for standardized outcome measures to allow for rigorous evaluation of performance across models. Further research needs to address the interpretability of model outputs by clinicians, clinical efficacy of these systems through prospective study design, and their potential impact in different clinical settings.

Predicting Acute Kidney Injury after Cardiac Surgery by Machine Learning Approaches

Cardiac surgery-associated AKI (CSA-AKI) is common after cardiac surgery and has an adverse impact on short- and long-term mortality. Early identification of patients at high risk of CSA-AKI by applying risk prediction models allows clinicians to closely monitor these patients and initiate effective preventive and therapeutic approaches to lessen the incidence of AKI. Several risk prediction models and risk assessment scores have been developed for CSA-AKI. However, the definition of AKI and the variables utilized in these risk scores differ, making general utility complex. Recently, the utility of artificial intelligence coupled with machine learning, has generated much interest and many studies in clinical medicine, including CSA-AKI. In this article, we discussed the evolution of models established by machine learning approaches to predict CSA-AKI.

Detection and Comparative Analysis of Methylomic Biomarkers of Rheumatoid Arthritis

Rheumatoid arthritis (RA) is a common autoimmune disorder influenced by both genetic and environmental factors. To investigate possible contributions of DNA methylation to the etiology of RA with minimum confounding genetic heterogeneity, we investigated genome-wide DNA methylation in disease-discordant monozygotic twin pairs. This study hypothesized that methylomic biomarkers might facilitate accurate RA detection. A comprehensive series of biomarker detection algorithms were utilized to find the best methylomic biomarkers for detecting RA patients using the methylomic data of the peripheral blood samples. The best model achieved 100.00% in accuracy (Acc) with 81 methylomic biomarkers and a 10-fold cross-validation (10FCV) strategy. Some of the methylomic biomarkers were experimentally confirmed to be associated with the onset or development of RA. It is also interesting to observe that many of the detected biomarkers were from chromosome Y, supporting the knowledge that RA has a significant gender discrepancy.

Rapid System Review Score-A Tool to Measure Predictive Interventions in Patients Admitted to the Postanesthesia Care Unit

PURPOSE

The Rapid System Review (RSR) score was developed to predict the number of postanesthesia care unit (PACU) interventions. We hypothesized that if RSR score was <0, no PACU interventions were expected; however as the RSR score increased, the number of PACU interventions would also increase.

DESIGN

Observational clinical study.

METHODS

The RSR score was tabulated as 0 to 3, 4 to 6, 7 to 9, 10 to 12, and 13 to 15. The corresponding number of PACU interventions was expected to be 1 to 3, 4 to 6, 7 to 9, 10 to 12, and 13 to 15.

FINDINGS

The Pearson correlation coefficient comparing RSR score and PACU interventions was 0.9 (P < 0.0001). The result was statistically significant.

CONCLUSIONS

These results suggest that as RSR score changes, the number of interventions would also alter proportionally.