Effect of a Machine Learning-Derived Early Warning System for Intraoperative Hypotension vs Standard Care on Depth and Duration of Intraoperative Hypotension During Elective Noncardiac Surgery: The HYPE Randomized Clinical Trial

Machine Learning and Artificial Intelligence in Surgical Research

Machine learning, a subtype of artificial intelligence, is an emerging field of surgical research dedicated to predictive modeling. From its inception, machine learning has been of interest in medical and surgical research. Built on traditional research metrics for optimal success, avenues of research include diagnostics, prognosis, operative timing, and surgical education, in a variety of surgical subspecialties. Machine learning represents an exciting and developing future in the world of surgical research that will not only allow for more personalized and comprehensive medical care.

Indicators of haemodynamic instability and left ventricular function in a porcine model of esmolol induced negative inotropy

To investigate if the Hypotension Prediction Index was an early indicator of haemodynamic instability in a negative inotropy porcine model, and to assess the correlation of commonly measured indicators of left ventricular systolic function. Eight anaesthetised pigs were volume resuscitated and then underwent an incremental infusion of esmolol hydrochloride (0-3000 mg/hr), following which it was then reduced in a stepwise manner. Full haemodynamic measurements were taken at each stage and measurements of left ventricular systolic function including left ventricular stroke work index, ejection fraction and peripheral dP/dT were obtained. At an infusion rate of 500 mg/hr of esmolol there were no significant changes in any measured variables. At 1000 mg/hr MAP was on average 11 mmHg lower (95% CI 1 to 11 mmHg, p = 0.027) with a mean of 78 mmHg, HPI increased by 33 units (95% CI 4 to 62, p = 0.026) with a mean value of 63. No other parameters showed significant change from baseline values. Subsequent increases in esmolol showed changes in all parameters except SVV, SVR and PA mean. Correlation between dP/dt and LVSWI was 0.85 (95% CI 0.77 to 0.90, p < 0.001), between LVEF and dP/dt 0.39 (95% CI 0.18 to 0.57, p < 0.001), and between LSWI and LVEF 0.41 (95% CI 0.20 to 0.59, p < 0.001). In this model haemodynamic instability induced by negative inotropy was detected by the HPI algorithm prior to any clinically significant change in commonly measured variables. In addition, the peripheral measure of left ventricular contractility dP/dt correlates well with more established measurements of LV systolic function.

Hypotension prediction index guided versus conventional goal directed therapy to reduce intraoperative hypotension during thoracic surgery: a randomized trial

PURPOSE

Intraoperative hypotension is linked to increased incidence of perioperative adverse events such as myocardial and cerebrovascular infarction and acute kidney injury. Hypotension prediction index (HPI) is a novel machine learning guided algorithm which can predict hypotensive events using high fidelity analysis of pulse-wave contour. Goal of this trial is to determine whether use of HPI can reduce the number and duration of hypotensive events in patients undergoing major thoracic procedures.

METHODS

Thirty four patients undergoing esophageal or lung resection were randomized into 2 groups -"machine learning algorithm" (AcumenIQ) and "conventional pulse contour analysis" (Flotrac). Analyzed variables were occurrence, severity and duration of hypotensive events (defined as a period of at least one minute of MAP below 65 mmHg), hemodynamic parameters at 9 different timepoints interesting from a hemodynamics viewpoint and laboratory (serum lactate levels, arterial blood gas) and clinical outcomes (duration of mechanical ventilation, ICU and hospital stay, occurrence of adverse events and in-hospital and 28-day mortality).

RESULTS

Patients in the AcumenIQ group had significantly lower area below the hypotensive threshold (AUT, 2 vs 16.7 mmHg x minutes) and time-weighted AUT (TWA, 0.01 vs 0.08 mmHg). Also, there were less patients with hypotensive events and cumulative duration of hypotension in the AcumenIQ group. No significant difference between groups was found in terms of laboratory and clinical outcomes.

CONCLUSIONS

Hemodynamic optimization guided by machine learning algorithm leads to a significant decrease in number and duration of hypotensive events compared to traditional goal directed therapy using pulse-contour analysis hemodynamic monitoring in patients undergoing major thoracic procedures. Further, larger studies are needed to determine true clinical utility of HPI guided hemodynamic monitoring.

TRIAL REGISTRATION

Date of first registration: 14/11/2022 Registration number: 04729481-3a96-4763-a9d5-23fc45fb722d.

Predicting the risk of inappropriate depth of endotracheal intubation in pediatric patients using machine learning approaches

Endotracheal tube (ET) misplacement is common in pediatric patients, which can lead to the serious complication. It would be helpful if there is an easy-to-use tool to predict the optimal ET depth considering in each patient's characteristics. Therefore, we plan to develop a novel machine learning (ML) model to predict the appropriate ET depth in pediatric patients. This study retrospectively collected data from 1436 pediatric patients aged < 7 years who underwent chest x-ray examination in an intubated state. Patient data including age, sex, height weight, the internal diameter (ID) of the ET, and ET depth were collected from electronic medical records and chest x-ray. Among these, 1436 data were divided into training (70%, n = 1007) and testing (30%, n = 429) datasets. The training dataset was used to build the appropriate ET depth estimation model, while the test dataset was used to compare the model performance with the formula-based methods such as age-based method, height-based method and tube-ID method. The rate of inappropriate ET location was significantly lower in our ML model (17.9%) compared to formula-based methods (35.7%, 62.2%, and 46.6%). The relative risk [95% confidence interval, CI] of an inappropriate ET location compared to ML model in the age-based, height-based, and tube ID-based method were 1.99 [1.56-2.52], 3.47 [2.80-4.30], and 2.60 [2.07-3.26], respectively. In addition, compared to ML model, the relative risk of shallow intubation tended to be higher in the age-based method, whereas the risk of the deep or endobronchial intubation tended to be higher in the height-based and the tube ID-based method. The use of our ML model was able to predict optimal ET depth for pediatric patients only with basic patient information and reduce the risk of inappropriate ET placement. It will be helpful to clinicians unfamiliar with pediatric tracheal intubation to determine the appropriate ET depth.

The artificial intelligence evidence-based medicine pyramid

Several studies exist in the literature regarding the exploitation of artificial intelligence in intensive care. However, an important gap between clinical research and daily clinical practice still exists that can only be bridged by robust validation studies carried out by multidisciplinary teams.

Attitudes of Anesthesiologists toward Artificial Intelligence in Anesthesia: A Multicenter, Mixed Qualitative-Quantitative Study

Artificial intelligence (AI) is predicted to play an increasingly important role in perioperative medicine in the very near future. However, little is known about what anesthesiologists know and think about AI in this context. This is important because the successful introduction of new technologies depends on the understanding and cooperation of end users. We sought to investigate how much anesthesiologists know about AI and what they think about the introduction of AI-based technologies into the clinical setting. In order to better understand what anesthesiologists think of AI, we recruited 21 anesthesiologists from 2 university hospitals for face-to-face structured interviews. The interview transcripts were subdivided sentence-by-sentence into discrete statements, and statements were then grouped into key themes. Subsequently, a survey of closed questions based on these themes was sent to 70 anesthesiologists from 3 university hospitals for rating. In the interviews, the base level of knowledge of AI was good at 86 of 90 statements (96%), although awareness of the potential applications of AI in anesthesia was poor at only 7 of 42 statements (17%). Regarding the implementation of AI in anesthesia, statements were split roughly evenly between pros (46 of 105, 44%) and cons (59 of 105, 56%). Interviewees considered that AI could usefully be used in diverse tasks such as risk stratification, the prediction of vital sign changes, or as a treatment guide. The validity of these themes was probed in a follow-up survey of 70 anesthesiologists with a response rate of 70%, which confirmed an overall positive view of AI in this group. Anesthesiologists hold a range of opinions, both positive and negative, regarding the application of AI in their field of work. Survey-based studies do not always uncover the full breadth of nuance of opinion amongst clinicians. Engagement with specific concerns, both technical and ethical, will prove important as this technology moves from research to the clinic.

Intraoperative Hypotension Prediction—A Proactive Perioperative Hemodynamic Management—A Literature Review

Intraoperative hypotension (IH) is a frequent phenomenon affecting a substantial number of patients undergoing general anesthesia. The occurrence of IH is related to significant perioperative complications, including kidney failure, myocardial injury, and even increased mortality. Despite advanced hemodynamic monitoring and protocols utilizing goal directed therapy, our management is still reactive; we intervene when the episode of hypotension has already occurred. This literature review evaluated the Hypotension Prediction Index (HPI), which is designed to predict and reduce the incidence of IH. The HPI algorithm is based on a machine learning algorithm that analyzes the arterial pressure waveform as an input and the occurrence of hypotension with MAP <65 mmHg for at least 1 min as an output. There are several studies, both retrospective and prospective, showing a significant reduction in IH episodes with the use of the HPI algorithm. However, the level of evidence on the use of HPI remains very low, and further studies are needed to show the benefits of this algorithm on perioperative outcomes.

Automated prediction of extubation success in extremely preterm infants: the APEX multicenter study

BACKGROUND

Extremely preterm infants are frequently subjected to mechanical ventilation. Current prediction tools of extubation success lacks accuracy.

METHODS

Multicenter study including infants with birth weight ≤1250 g undergoing their first extubation attempt. Clinical data and cardiorespiratory signals were acquired before extubation. Primary outcome was prediction of extubation success. Automated analysis of cardiorespiratory signals, development of clinical and cardiorespiratory features, and a 2-stage Clinical Decision-Balanced Random Forest classifier were used. A leave-one-out cross-validation was done. Performance was analyzed by ROC curves and determined by balanced accuracy. An exploratory analysis was performed for extubations before 7 days of age.

RESULTS

A total of 241 infants were included and 44 failed (18%) extubation. The classifier had a balanced accuracy of 73% (sensitivity 70% [95% CI: 63%, 76%], specificity 75% [95% CI: 62%, 88%]). As an additional clinical-decision tool, the classifier would have led to an increase in extubation success from 82% to 93% but misclassified 60 infants who would have been successfully extubated. In infants extubated before 7 days of age, the classifier identified 16/18 failures (specificity 89%) and 73/105 infants with success (sensitivity 70%).

CONCLUSIONS

Machine learning algorithms may improve a balanced prediction of extubation outcomes, but further refinement and validation is required.

IMPACT

A machine learning-derived predictive model combining clinical data with automated analyses of individual cardiorespiratory signals may improve the prediction of successful extubation and identify infants at higher risk of failure with a good balanced accuracy. Such multidisciplinary approach including medicine, biomedical engineering and computer science is a step forward as current tools investigated to predict extubation outcomes lack sufficient balanced accuracy to justify their use in future trials or clinical practice. Thus, this individualized assessment can optimize patient selection for future trials of extubation readiness by decreasing exposure of low-risk infants to interventions and maximize the benefits of those at high risk.

Artificial Intelligence in Surgical Learning

(1) Background: Artificial Intelligence (AI) is transforming healthcare on all levels. While AI shows immense potential, the clinical implementation is lagging. We present a concise review of AI in surgical learning; (2) Methods: A non-systematic review of AI in surgical learning of the literature in English is provided; (3) Results: AI shows utility for all components of surgical competence within surgical learning. AI presents with great potential within robotic surgery specifically (4) Conclusions: Technology will evolve in ways currently unimaginable, presenting us with novel applications of AI and derivatives thereof. Surgeons must be open to new modes of learning to be able to implement all evidence-based applications of AI in the future. Systematic analyses of AI in surgical learning are needed.

[Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI extensionDiretrizes para relatórios de ensaios clínicos com intervenções que utilizam inteligência artificial: a extensão CONSORT-AI]

The CONSORT 2010 statement provides minimum guidelines for reporting randomized trials. Its widespread use has been instrumental in ensuring transparency in the evaluation of new interventions. More recently, there has been a growing recognition that interventions involving artificial intelligence (AI) need to undergo rigorous, prospective evaluation to demonstrate impact on health outcomes. The CONSORT-AI (Consolidated Standards of Reporting Trials-Artificial Intelligence) extension is a new reporting guideline for clinical trials evaluating interventions with an AI component. It was developed in parallel with its companion statement for clinical trial protocols: SPIRIT-AI (Standard Protocol Items: Recommendations for Interventional Trials-Artificial Intelligence). Both guidelines were developed through a staged consensus process involving literature review and expert consultation to generate 29 candidate items, which were assessed by an international multi-stakeholder group in a two-stage Delphi survey (103 stakeholders), agreed upon in a two-day consensus meeting (31 stakeholders) and refined through a checklist pilot (34 participants). The CONSORT-AI extension includes 14 new items that were considered sufficiently important for AI interventions that they should be routinely reported in addition to the core CONSORT 2010 items. CONSORT-AI recommends that investigators provide clear descriptions of the AI intervention, including instructions and skills required for use, the setting in which the AI intervention is integrated, the handling of inputs and outputs of the AI intervention, the human-AI interaction and provision of an analysis of error cases. CONSORT-AI will help promote transparency and completeness in reporting clinical trials for AI interventions. It will assist editors and peer reviewers, as well as the general readership, to understand, interpret and critically appraise the quality of clinical trial design and risk of bias in the reported outcomes.

Healthcare provider evaluation of machine learning-directed care: reactions to deployment on a randomised controlled study

OBJECTIVES

Clinical artificial intelligence and machine learning (ML) face barriers related to implementation and trust. There have been few prospective opportunities to evaluate these concerns. System for High Intensity EvaLuation During Radiotherapy (NCT03775265) was a randomised controlled study demonstrating that ML accurately directed clinical evaluations to reduce acute care during cancer radiotherapy. We characterised subsequent perceptions and barriers to implementation.

METHODS

An anonymous 7-question Likert-type scale survey with optional free text was administered to multidisciplinary staff focused on workflow, agreement with ML and patient experience.

RESULTS

59/71 (83%) responded. 81% disagreed/strongly disagreed their workflow was disrupted. 67% agreed/strongly agreed patients undergoing intervention were high risk. 75% agreed/strongly agreed they would implement the ML approach routinely if the study was positive. Free-text feedback focused on patient education and ML predictions.

CONCLUSIONS

Randomised data and firsthand experience support positive reception of clinical ML. Providers highlighted future priorities, including patient counselling and workflow optimisation.

Implemented machine learning tools to inform decision-making for patient care in hospital settings: a scoping review

OBJECTIVES

To identify ML tools in hospital settings and how they were implemented to inform decision-making for patient care through a scoping review. We investigated the following research questions: What ML interventions have been used to inform decision-making for patient care in hospital settings? What strategies have been used to implement these ML interventions?

DESIGN

A scoping review was undertaken. MEDLINE, Embase, Cochrane Central Register of Controlled Trials (CENTRAL) and the Cochrane Database of Systematic Reviews (CDSR) were searched from 2009 until June 2021. Two reviewers screened titles and abstracts, full-text articles, and charted data independently. Conflicts were resolved by another reviewer. Data were summarised descriptively using simple content analysis.

SETTING

Hospital setting.

PARTICIPANT

Any type of clinician caring for any type of patient.

INTERVENTION

Machine learning tools used by clinicians to inform decision-making for patient care, such as AI-based computerised decision support systems or "'model-based'" decision support systems.

PRIMARY AND SECONDARY OUTCOME MEASURES

Patient and study characteristics, as well as intervention characteristics including the type of machine learning tool, implementation strategies, target population. Equity issues were examined with PROGRESS-PLUS criteria.

RESULTS

After screening 17 386 citations and 3474 full-text articles, 20 unique studies and 1 companion report were included. The included articles totalled 82 656 patients and 915 clinicians. Seven studies reported gender and four studies reported PROGRESS-PLUS criteria (race, health insurance, rural/urban). Common implementation strategies for the tools were clinician reminders that integrated ML predictions (44.4%), facilitated relay of clinical information (17.8%) and staff education (15.6%). Common barriers to successful implementation of ML tools were time (11.1%) and reliability (11.1%), and common facilitators were time/efficiency (13.6%) and perceived usefulness (13.6%).

CONCLUSIONS

We found limited evidence related to the implementation of ML tools to assist clinicians with patient healthcare decisions in hospital settings. Future research should examine other approaches to integrating ML into hospital clinician decisions related to patient care, and report on PROGRESS-PLUS items.

FUNDING

Canadian Institutes of Health Research (CIHR) Foundation grant awarded to SES and the CIHR Strategy for Patient Oriented-Research Initiative (GSR-154442). SCOPING REVIEW REGISTRATION: https://osf.io/e2mna.

Dry or wet? Fluid therapy in upper gastrointestinal surgery patients

A correct perioperative fluid administration represents one of the most important items proposed by the Enhanced Recovery After Surgery Society. Upper gastrointestinal (UGI) surgery patients undergoing major oncological procedures are often elderly and frail. Should we prefer a wet or a dry patient? Both conditions should probably be avoided in this surgical setting. We present a narrative review on perioperative fluid administration in UGI patients undergoing major surgery, also analyzing the role of Goal Directed therapy.

Real-world outcomes of the hypotension prediction index in the management of intraoperative hypotension during non-cardiac surgery: a retrospective clinical study

The Hypotension Prediction Index (HPI) is a validated algorithm developed by applying machine learning for predicting intraoperative arterial hypotension (IOH). We evaluated whether the HPI, combined with a personalized treatment protocol, helps to reduce IOH (depth and duration) and perioperative events in real practice. This was a single-center retrospective study including 104 consecutive adults undergoing urgent or elective non-cardiac surgery with moderate-to-high risk of bleeding, requiring invasive blood pressure and continuous cardiac output monitoring. Depending on the sensor, two comparable groups were identified: patients managed following the institutional protocol of personalized goal-directed fluid therapy (GDFT, n = 52), or this GDFT supported by the HPI (HPI, n = 52). The time-weighted average of hypotension for a mean arterial pressure < 65 mmHg (TWA_MAP<65), postoperative complications and length of hospital stay (LOS) were automatically downloaded from medical records and revised by clinicians blinded to the management received by patients. Differences in preoperative variables (i.e. physical status -ASA class-, acute kidney Injury-AKI- risk) and outcomes were analyzed using non-parametric tests with Hodges-Lehmann estimator for the median of differences. ASA class and AKI risk were similar (p = 0.749 and p = 0.837, respectively). Blood loss was also comparable (p = 0.279). HPI patients had a lower TWA_MAP<65 [0.09 mmHg (0-0.48 mmHg)] vs [0.23 mmHg (0.01 to 0.97 mmHg)], p = 0.037. Postoperative complications were less prevalent in the HPI patients (0.46 ± 0.98 vs. 0.88 ± 1.20), p = 0.035. Finally, LOS was significantly shorter among HPI patients with a median difference of 2 days (p = 0.019). The HPI combined with a GDFT protocol may help to minimize the severity of IOH during non-cardiac surgery.

Preoperative Identification of Patient-Dependent Blood Pressure Targets Associated With Low Risk of Intraoperative Hypotension During Noncardiac Surgery

BACKGROUND

Intraoperative hypotension (IOH) is strongly linked to organ system injuries and postoperative death. Blood pressure itself is a powerful predictor of IOH; however, it is unclear which pressures carry the lowest risk and may be leveraged to prevent subsequent hypotension. Our objective was to develop a model that predicts, before surgery and according to a patient's unique characteristics, which intraoperative mean arterial pressures (MAPs) between 65 and 100 mm Hg have a low risk of IOH, defined as an MAP <65 mm Hg, and may serve as testable hemodynamic targets to prevent IOH.

METHODS

Adult, noncardiac surgeries under general anesthesia at 2 tertiary care hospitals of the University of Pittsburgh Medical Center were divided into training and validation cohorts, then assigned into smaller subgroups according to preoperative risk factors. Primary outcome was hypotension risk, defined for each intraoperative MAP value from 65 to 100 mm Hg as the proportion of a value's total measurements followed by at least 1 MAP <65 mm Hg within 5 or 10 minutes, and calculated for all values in each subgroup. Five models depicting MAP-associated IOH risk were compared according to best fit across subgroups with proportions whose confidence interval was <0.05. For the best fitting model, (1) performance was validated, (2) low-risk MAP targets were identified according to applied benchmarks, and (3) preoperative risk factors were evaluated as predictors of model parameters.

RESULTS

A total of 166,091 surgeries were included, with 121,032 and 45,059 surgeries containing 5.4 million and 1.9 million MAP measurements included in the training and validation sets, respectively. Thirty-six subgroups with at least 21 eligible proportions (confidence interval <0.05) were identified, representing 92% and 94% of available MAP measurements, respectively. The exponential with theta constant model demonstrated the best fit (weighted sum of squared error 0.0005), and the mean squared error of hypotension risk per MAP did not exceed 0.01% in validation testing. MAP targets ranged between 69 and 90 mm Hg depending on the subgroup and benchmark used. Increased age, higher American Society of Anesthesiologists physical status, and female sexindependently predicted ( P < .05) hypotension risk curves with less rapid decay and higher plateaus.

CONCLUSIONS

We demonstrate that IOH risk specific to a given MAP is patient-dependent, but predictable before surgery. Our model can identify intraoperative MAP targets before surgery predicted to reduce a patient's exposure to IOH, potentially allowing clinicians to develop more personalized approaches for managing hemodynamics.

[Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI extensionDiretrizes para protocolos de ensaios clínicos com intervenções que utilizam inteligência artificial: a extensão SPIRIT-AI]

The SPIRIT 2013 statement aims to improve the completeness of clinical trial protocol reporting by providing evidence-based recommendations for the minimum set of items to be addressed. This guidance has been instrumental in promoting transparent evaluation of new interventions. More recently, there has been a growing recognition that interventions involving artificial intelligence (AI) need to undergo rigorous, prospective evaluation to demonstrate their impact on health outcomes. The SPIRIT-AI (Standard Protocol Items: Recommendations for Interventional Trials-Artificial Intelligence) extension is a new reporting guideline for clinical trial protocols evaluating interventions with an AI component. It was developed in parallel with its companion statement for trial reports: CONSORT-AI (Consolidated Standards of Reporting Trials-Artificial Intelligence). Both guidelines were developed through a staged consensus process involving literature review and expert consultation to generate 26 candidate items, which were consulted upon by an international multi-stakeholder group in a two-stage Delphi survey (103 stakeholders), agreed upon in a consensus meeting (31 stakeholders) and refined through a checklist pilot (34 participants). The SPIRIT-AI extension includes 15 new items that were considered sufficiently important for clinical trial protocols of AI interventions. These new items should be routinely reported in addition to the core SPIRIT 2013 items. SPIRIT-AI recommends that investigators provide clear descriptions of the AI intervention, including instructions and skills required for use, the setting in which the AI intervention will be integrated, considerations for the handling of input and output data, the human-AI interaction and analysis of error cases. SPIRIT-AI will help promote transparency and completeness for clinical trial protocols for AI interventions. Its use will assist editors and peer reviewers, as well as the general readership, to understand, interpret and critically appraise the design and risk of bias for a planned clinical trial.

Do higher alarm thresholds for arterial blood pressure lead to less perioperative hypotension? A retrospective, observational cohort study

Arterial blood pressure is one of the vital signs monitored mandatory in anaesthetised patients. Even short episodes of intraoperative hypotension are associated with increased risk for postoperative organ dysfunction such as acute kidney injury and myocardial injury. Since there is little evidence whether higher alarm thresholds in patient monitors can help prevent intraoperative hypotension, we analysed the blood pressure data before (group 1) and after (group 2) the implementation of altered hypotension alarm settings. The study was conducted as a retrospective observational cohort study in a large surgical centre with 32 operating theatres. Alarm thresholds for hypotension alarm for mean arterial pressure (MAP) were altered from 60 (before) to 65 mmHg for invasive measurement and 70 mmHg for noninvasive measurement. Blood pressure data from electronic anaesthesia records of 4222 patients (1982 and 2240 in group 1 and 2, respectively) with 406,623 blood pressure values undergoing noncardiac surgery were included. We analysed (A) the proportion of blood pressure measurements below the threshold among all measurements by quasi-binomial regression and (B) whether at least one blood pressure measurement below the threshold occurred by logistic regression. Hypotension was defined as MAP < 65 mmHg. There was no significant difference in overall proportions of hypotensive episodes for mean arterial pressure before and after the adjustment of alarm settings (mean proportion of values below 65 mmHg were 6.05% in group 1 and 5.99% in group 2). The risk of ever experiencing a hypotensive episode during anaesthesia was significantly lower in group 2 with an odds ratio of 0.84 (p = 0.029). In conclusion, higher alarm thresholds do not generally lead to less hypotensive episodes perioperatively. There was a slight but significant reduction of the occurrence of intraoperative hypotension in the presence of higher thresholds for blood pressure alarms. However, this reduction only seems to be present in patients with very few hypotensive episodes.

Analysing multi-perspective patient-related data during laparoscopic gynaecology procedures

Fusing data from different medical perspectives inside the operating room (OR) sets the stage for developing intelligent context-aware systems. These systems aim to promote better awareness inside the OR by keeping every medical team well informed about the work of other teams and thus mitigate conflicts resulting from different targets. In this research, a descriptive analysis of data collected from anaesthesiology and surgery was performed to investigate the relationships between the intra-abdominal pressure (IAP) and lung mechanics for patients during laparoscopic procedures. Data of nineteen patients who underwent laparoscopic gynaecology were included. Statistical analysis of all subjects showed a strong relationship between the IAP and dynamic lung compliance (r = 0.91). Additionally, the peak airway pressure was also strongly correlated to the IAP in volume-controlled ventilated patients (r = 0.928). Statistical results obtained by this study demonstrate the importance of analysing the relationship between surgical actions and physiological responses. Moreover, these results form the basis for developing medical decision support models, e.g., automatic compensation of IAP effects on lung function.

New Developments in Continuous Hemodynamic Monitoring of the Critically Ill Patient

Hemodynamic monitoring is a cornerstone in the assessment of patients with circulatory shock. Timely recognition of hemodynamic compromise and proper optimisation is essential to ensure adequate tissue perfusion and maintain renal, hepatic, abdominal, and cerebral functions. Hemodynamic monitoring has significantly evolved since the first inception of the pulmonary artery catheter more than 50 years ago. Bedside echocardiography, when combined with noninvasive and minimally invasive technologies, provides tools to monitor and quantify the cardiac output to promptly react and improve hemodynamic management in an acute care setting. Commonly used technologies include noninvasive pulse-wave analysis, pulse-wave transit time, thoracic bioimpedance and bioreactance, esophageal Doppler, minimally invasive pulse-wave analysis, transpulmonary thermodilution, and pulmonary artery catheter. These monitoring strategies are reviewed here, along with detailed analysis of their operating mode, particularities, and limitations. The use of artificial intelligence to enhance performance and effectiveness of hemodynamic monitoring is reviewed to apprehend future possibilities.

Periprocedure Management of Blood Pressure After Acute Ischemic Stroke

The management of acute ischemic stroke primarily revolves around the timely restoration of blood flow (recanalization/reperfusion) in the occluded vessel and maintenance of cerebral perfusion through collaterals before reperfusion. Mechanical thrombectomy is the most effective treatment for acute ischemic stroke due to large vessel occlusions in appropriately selected patients. Judicious management of blood pressure before, during, and after mechanical thrombectomy is critical to ensure good outcomes by preventing progression of cerebral ischemia as well hemorrhagic conversion, in addition to optimizing systemic perfusion. While direct evidence to support specific hemodynamic targets around mechanical thrombectomy is limited, there is increasing interest in this area. Newer approaches to blood pressure management utilizing individualized cerebral autoregulation-based targets are being explored. Early efforts at utilizing machine learning to predict blood pressure treatment thresholds and therapies also seem promising; this focused review aims to provide an update on recent evidence around periprocedural blood pressure management after acute ischemic stroke, highlighting its implications for clinical practice while identifying gaps in current literature.

Artificial intelligence in critical illness and its impact on patient care: a comprehensive review

Artificial intelligence (AI) has great potential to improve the field of critical care and enhance patient outcomes. This paper provides an overview of current and future applications of AI in critical illness and its impact on patient care, including its use in perceiving disease, predicting changes in pathological processes, and assisting in clinical decision-making. To achieve this, it is important to ensure that the reasoning behind AI-generated recommendations is comprehensible and transparent and that AI systems are designed to be reliable and robust in the care of critically ill patients. These challenges must be addressed through research and the development of quality control measures to ensure that AI is used in a safe and effective manner. In conclusion, this paper highlights the numerous opportunities and potential applications of AI in critical care and provides guidance for future research and development in this field. By enabling the perception of disease, predicting changes in pathological processes, and assisting in the resolution of clinical decisions, AI has the potential to revolutionize patient care for critically ill patients and improve the efficiency of health systems.

Effect of hypotension prediction index in the prevention of intraoperative hypotension during noncardiac surgery: A systematic review

Intraoperative hypotension (IOH) is common in noncardiac surgery and is associated with serious postoperative complications. Hypotension Prediction Index (HPI) has shown high sensitivity and specificity for predicting hypotension and may reduce IOH in noncardiac surgery. We conducted a systematic review of randomized controlled trials (RCTs) to evaluate the applications and effects of HPI in reducing hypotension during noncardiac surgery. We comprehensively searched the PubMed, Embase, Cochrane Library, Google Scholar, and http://ClinicalTrials.gov databases to identify RCTs conducted before May 2022. The primary outcome measures were the time-weighted average (TWA) of hypotension and the area under the hypotensive threshold (65 mmHg). Secondary outcomes were the incidence and duration of hypotension and the percentage of hypotensive time during surgery. The Cochrane Risk of Bias (RoB) tool was used to assess the quality of selected studies. We conducted data synthesis for median differences and assessed the certainty of evidence using the Grading of Recommendations Assessment, Development, and Evaluation (GRADE) approach. We included five studies with a total of 461 patients. Limited evidence suggested that HPI-guided intraoperative hemodynamics management leads to lower a) TWA of hypotension (median of difference of medians [MDM], -0.27 mmHg; 95% confidence interval [CI], -0.38, -0.01), b) area under the hypotensive threshold (MDM, -60.28 mmHg*min; 95% CI, -74.00, -1.30), c) incidence of hypotension (MDM, -4.50; 95% CI, -5.00, -4.00), d) total duration of hypotension (MDM, -12.80 min; 95% CI, -16.11, -3.39), and e) percentage of hypotension (MDM, -5.80; 95% CI, -6.65, -4.82) than routine hemodynamic management during noncardiac surgery. However, only very low- to low-quality evidence on the benefit of intraoperative HPI-based hemodynamic management is available. Our review revealed that HPI has the potential to reduce the occurrence, duration, and severity of IOH during noncardiac surgery compared to standard intraoperative care with proper adherence to the protocol. Systematic review registration PROSPERO CRD42022333834.

External validation of a machine learning model to predict hemodynamic instability in intensive care unit

Background

Early prediction model of hemodynamic instability has the potential to improve the critical care, whereas limited external validation on the generalizability. We aimed to independently validate the Hemodynamic Stability Index (HSI), a multi-parameter machine learning model, in predicting hemodynamic instability in Asian patients.

Method

Hemodynamic instability was marked by using inotropic, vasopressor, significant fluid therapy, and/or blood transfusions. This retrospective study included among 15,967 ICU patients who aged 20 years or older (not included 20 years) and stayed in ICU for more than 6 h admitted to Taipei Veteran General Hospital (TPEVGH) between January 1, 2010, and March 31, 2020, of whom hemodynamic instability occurred in 3053 patients (prevalence = 19%). These patients in unstable group received at least one intervention during their ICU stays, and the HSI score of both stable and unstable group was calculated in every hour before intervention. The model performance was assessed using the area under the receiver operating characteristic curve (AUROC) and was compared to single indicators like systolic blood pressure (SBP) and shock index. The hemodynamic instability alarm was set by selecting optimal threshold with high sensitivity, acceptable specificity, and lead time before intervention was calculated to indicate when patients were firstly identified as high risk of hemodynamic instability.

Results

The AUROC of HSI was 0.76 (95% CI, 0.75–0.77), which performed significantly better than shock Index (0.7; 95% CI, 0.69–0.71) and SBP (0.69; 95% CI, 0.68–0.70). By selecting 0.7 as a threshold, HSI predicted 72% of all 3053 patients who received hemodynamic interventions with 67% in specificity. Time-varying results also showed that HSI score significantly outperformed single indicators even up to 24 h before intervention. And 95% unstable patients can be identified more than 5 h in advance.

Conclusions

The HSI has acceptable discrimination but underestimates the risk of stable patients in predicting the onset of hemodynamic instability in an external cohort.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13054-022-04088-9.

Incidence, Severity and Clinical Factors Associated with Hypotension in Patients Admitted to an Intensive Care Unit: A Prospective Observational Study

Background: The majority of patients admitted to the intensive care unit (ICU) experience severe hypotension which is associated with increased morbidity and mortality. At present, prospective studies examining the incidence and severity of hypotension using continuous waveforms are missing. Methods: This study is a prospective observational cohort study in a mixed surgical and non-surgical ICU population. All patients over 18 years were included and continuous arterial pressure waveforms data were collected. Mean arterial pressure (MAP) below 65 mmHg for at least 10 s was defined as hypotension and a MAP below 45 mmHg as severe hypotension. The primary outcome was the incidence of hypotension. Secondary outcomes were the severity of hypotension expressed in time-weighted average (TWA), factors associated with hypotension, the number and duration of hypotensive events. Results: 499 patients were included. The incidence of hypotension (MAP < 65 mmHg) was 75% (376 out of 499) and 9% (46 out of 499) experienced severe hypotension. Median TWA was 0.3 mmHg [0−1.0]. Associated clinical factors were age, male sex, BMI and cardiogenic shock. There were 5 (1−12) events per patients with a median of 52 min (5−170). Conclusions: In a mixed surgical and non-surgical ICU population the incidence of hypotension is remarkably high.

The use of artificial intelligence and machine learning monitoring to safely administer a fluid-restrictive goal-directed treatment protocol to minimize the risk of transfusion during major spine surgery of a Jehovah’s Witness: a case report

Background

The Hypotension Prediction Index (HPI) displays an innovative monitoring tool which predicts intraoperative hypotension before its onset.

Case presentation

We report the case of an 84-year-old Caucasian woman undergoing major spinal surgery with no possibility for the transfer of blood products given her status as a Jehovah’s Witness. The hemodynamic treatment algorithm we employed was based on HPI and resulted in a high degree of hemodynamic stability during the surgical procedure. Further, the patient was not at risk for either hypo- or hypervolemia, conditions which might have caused dilution anemia. By using HPI as a tool for patient blood management, it was possible to reduce the incidence of intraoperative hypotension to a minimum.

Conclusions

In sum, this HPI-based treatment algorithm represents a useful application for the treatment of complex anesthesia and perioperative patient blood management. It is a simple but powerful extension of standard monitoring for the prevention of intraoperative hypotension.

Optimizing an existing prediction model for quality of life one-year post-intensive care unit: An exploratory analysis

BACKGROUND

This study aimed to improve the PREPARE model, an existing linear regression prediction model for long-term quality of life (QoL) of intensive care unit (ICU) survivors by incorporating additional ICU data from patients' electronic health record (EHR) and bedside monitors.

METHODS

The 1308 adult ICU patients, aged ≥16, admitted between July 2016 and January 2019 were included. Several regression-based machine learning models were fitted on a combination of patient-reported data and expert-selected EHR variables and bedside monitor data to predict change in QoL 1 year after ICU admission. Predictive performance was compared to a five-feature linear regression prediction model using only 24-hour data (R²  = 0.54, mean square error (MSE) = 0.031, mean absolute error (MAE) = 0.128).

RESULTS

The 67.9% of the included ICU survivors was male and the median age was 65.0 [IQR: 57.0-71.0]. Median length of stay (LOS) was 1 day [IQR 1.0-2.0]. The incorporation of the additional data pertaining to the entire ICU stay did not improve the predictive performance of the original linear regression model. The best performing machine learning model used seven features (R²  = 0.52, MSE = 0.032, MAE = 0.125). Pre-ICU QoL, the presence of a cerebro vascular accident (CVA) upon admission and the highest temperature measured during the ICU stay were the most important contributors to predictive performance. Pre-ICU QoL's contribution to predictive performance far exceeded that of the other predictors.

CONCLUSION

Pre-ICU QoL was by far the most important predictor for change in QoL 1 year after ICU admission. The incorporation of the numerous additional features pertaining to the entire ICU stay did not improve predictive performance although the patients' LOS was relatively short.

Machine learning in predicting antimicrobial resistance: a systematic review and meta-analysis

INTRODUCTION

Antimicrobial resistance (AMR) is a global health threat; rapid and timely identification of AMR improves patient prognosis and reduces inappropriate antibiotic use.

METHODS

Relevant literature in PubMed, Web of Science, Embase and Institute of Electrical and Electronics Engineers prior to 28 September 2021 was searched. Any study that deployed machine learning (ML) or a risk score as a tool to predict AMR was included in the final review; there were 25 studies that employed the ML algorithm to predict AMR.

RESULTS

Extended spectrum β-lactamases, methicillin-resistant Staphylococcus aureus (MRSA) and carbapenem resistance were the most common outcomes in studies with a specific resistance pattern. The most common algorithms in ML prediction were logistic regression (n = 14 studies), decision tree (n = 14) and random forest (n = 7). The area under the curve (AUC) range for ML prediction was 0.48-0.93. The pooled AUC for ML prediction was 0.82 (0.78-0.85). Compared with risk score, higher specificity [87% (82-91) vs. 37% (25-51)] was indicated for ML prediction, but not sensitivity [67% (62-72) vs. 73% (67-79)].

CONCLUSIONS

Machine learning might be a potential technology for AMR prediction; however, retrospective methodology for model development, nonstandard data processing and scarcity of validation in a randomised controlled trial or real-world study limit the application of these models in clinical practice.

Pressure response to fluid challenge administration in hypotensive surgical patients: a post-hoc pharmacodynamic analysis of five datasets

In this study we evaluated the effect of fluid challenge (FC) administration in elective surgical patients with low or normal blood pressure. Secondarily, we appraised the pharmacodynamic effect of FC in normotensive and hypotensive patients. We assessed five merged datasets of patients with a baseline mean arterial pressure (MAP) above or below 65 mmHg and assessed the changes of systolic, diastolic, mean and dicrotic arterial pressures, dynamic indexes of fluid responsiveness and arterial elastance over a 10-min infusion. The hemodynamic effect was assessed by considering the net area under the curve (AUC), the maximal percentage difference from baseline (d_max), the time when the maximal value was observed (t_max) and change from baseline at 5-min (d₅) after FC end. A stroke volume index increase > 10% with respect to the baseline value after FC administration indicated fluid response. Two hundred-seventeen patients were analysed [102 (47.0%) fluid responders]. On average, FC restored a MAP [Formula: see text] 65 mmHg after 5 min. The AUCs and the d_max of pressure variables and arterial elastance of hypotensive patients were all significantly greater than normotensive patients. Pressure variables and arterial elastance changes in the hypotensive group were all significantly higher at d₅ as compared to the normotensive group. In hypotensive patients, FC restores a MAP [Formula: see text] 65 mmHg after 5 min from infusion start. The hemodynamic profile of FC in hypotensive and normotensive patients is different; both the magnitude of pressure augmentation and duration is greater in the hypotensive group.

Prediction of Intracranial Hypertension and Brain Tissue Hypoxia Utilizing High-Resolution Data from the BOOST-II Clinical Trial

The current approach to intracranial hypertension and brain tissue hypoxia is reactive, based on fixed thresholds. We used statistical machine learning on high-frequency intracranial pressure (ICP) and partial brain tissue oxygen tension (PbtO₂) data obtained from the BOOST-II trial with the goal of constructing robust quantitative models to predict ICP/PbtO₂ crises. We derived the following machine learning models: logistic regression (LR), elastic net, and random forest. We split the data set into 70–30% for training and testing and utilized a discrete-time survival analysis framework and 5-fold hyperparameter optimization strategy for all models. We compared model performances on discrimination between events and non-events of increased ICP or low PbtO₂ with the area under the receiver operating characteristic (AUROC) curve. We further analyzed clinical utility through a decision curve analysis (DCA). When considering discrimination, the number of features, and interpretability, we identified the RF model that combined the most recent ICP reading, episode number, and longitudinal trends over the preceding 30 min as the best performing for predicting ICP crisis events within the next 30 min (AUC 0.78). For PbtO₂, the LR model utilizing the most recent reading, episode number, and longitudinal trends over the preceding 30 min was the best performing (AUC, 0.84). The DCA showed clinical usefulness for wide risk of thresholds for both ICP and PbtO₂ predictions. Acceptable alerting thresholds could range from 20% to 80% depending on a patient-specific assessment of the benefit-risk ratio of a given intervention in response to the alert.

Implementation of machine learning in the clinic: challenges and lessons in prospective deployment from the System for High Intensity EvaLuation During Radiation Therapy (SHIELD-RT) randomized controlled study

Background

Artificial intelligence (AI) and machine learning (ML) have resulted in significant enthusiasm for their promise in healthcare. Despite this, prospective randomized controlled trials and successful clinical implementation remain limited. One clinical application of ML is mitigation of the increased risk for acute care during outpatient cancer therapy. We previously reported the results of the System for High Intensity EvaLuation During Radiation Therapy (SHIELD-RT) study (NCT04277650), which was a prospective, randomized quality improvement study demonstrating that ML based on electronic health record (EHR) data can direct supplemental clinical evaluations and reduce the rate of acute care during cancer radiotherapy with and without chemotherapy. The objective of this study is to report the workflow and operational challenges encountered during ML implementation on the SHIELD-RT study.

Results

Data extraction and manual review steps in the workflow represented significant time commitments for implementation of clinical ML on a prospective, randomized study. Barriers include limited data availability through the standard clinical workflow and commercial products, the need to aggregate data from multiple sources, and logistical challenges from altering the standard clinical workflow to deliver adaptive care.

Conclusions

The SHIELD-RT study was an early randomized controlled study which enabled assessment of barriers to clinical ML implementation, specifically those which leverage the EHR. These challenges build on a growing body of literature and may provide lessons for future healthcare ML adoption.

Trial registration: NCT04277650. Registered 20 February 2020. Retrospectively registered quality improvement study.

Effective hemodynamic monitoring

Hemodynamic monitoring is the centerpiece of patient monitoring in acute care settings. Its effectiveness in terms of improved patient outcomes is difficult to quantify. This review focused on effectiveness of monitoring-linked resuscitation strategies from: (1) process-specific monitoring that allows for non-specific prevention of new onset cardiovascular insufficiency (CVI) in perioperative care. Such goal-directed therapy is associated with decreased perioperative complications and length of stay in high-risk surgery patients. (2) Patient-specific personalized resuscitation approaches for CVI. These approaches including dynamic measures to define volume responsiveness and vasomotor tone, limiting less fluid administration and vasopressor duration, reduced length of care. (3) Hemodynamic monitoring to predict future CVI using machine learning approaches. These approaches presently focus on predicting hypotension. Future clinical trials assessing hemodynamic monitoring need to focus on process-specific monitoring based on modifying therapeutic interventions known to improve patient-centered outcomes.

Hypotension Prediction Index Software to Prevent Intraoperative Hypotension during Major Non-Cardiac Surgery: Protocol for a European Multicenter Prospective Observational Registry (EU-HYPROTECT)

Background: Intraoperative hypotension is common in patients having non-cardiac surgery and associated with postoperative acute myocardial injury, acute kidney injury, and mortality. Avoiding intraoperative hypotension is a complex task for anesthesiologists. Using artificial intelligence to predict hypotension from clinical and hemodynamic data is an innovative and intriguing approach. The AcumenTM Hypotension Prediction Index (HPI) software (Edwards Lifesciences; Irvine, CA, USA) was developed using artificial intelligence—specifically machine learning—and predicts hypotension from blood pressure waveform features. We aimed to describe the incidence, duration, severity, and causes of intraoperative hypotension when using HPI monitoring in patients having elective major non-cardiac surgery. Methods: We built up a European, multicenter, prospective, observational registry including at least 700 evaluable patients from five European countries. The registry includes consenting adults (≥18 years) who were scheduled for elective major non-cardiac surgery under general anesthesia that was expected to last at least 120 min and in whom arterial catheter placement and HPI monitoring was planned. The major objectives are to quantify and characterize intraoperative hypotension (defined as a mean arterial pressure [MAP] < 65 mmHg) when using HPI monitoring. This includes the time-weighted average (TWA) MAP < 65 mmHg, area under a MAP of 65 mmHg, the number of episodes of a MAP < 65 mmHg, the proportion of patients with at least one episode (1 min or more) of a MAP < 65 mmHg, and the absolute maximum decrease below a MAP of 65 mmHg. In addition, we will assess causes of intraoperative hypotension and investigate associations between intraoperative hypotension and postoperative outcomes. Discussion: There are only sparse data on the effect of using HPI monitoring on intraoperative hypotension in patients having elective major non-cardiac surgery. Therefore, we built up a European, multicenter, prospective, observational registry to describe the incidence, duration, severity, and causes of intraoperative hypotension when using HPI monitoring in patients having elective major non-cardiac surgery.

Prediction and Prevention of Intraoperative Hypotension with the Hypotension Prediction Index: A Narrative Review

Intraoperative hypotension is common and has been associated with adverse events. Although association does not imply causation, predicting and preventing hypotension may improve postoperative outcomes. This review summarizes current evidence on the development and validation of an artificial intelligence predictive algorithm, the Hypotension Prediction (HPI) (formerly known as the Hypotension Probability Indicator). This machine learning model can arguably predict hypotension up to 15 min before its occurrence. Several validation studies, retrospective cohorts, as well as a few prospective randomized trials, have been published in the last years, reporting promising results. Larger trials are needed to definitively assess the usefulness of this algorithm in optimizing postoperative outcomes.

Personalized decision-making for acute cholecystitis: Understanding surgeon judgment

Background

There is sparse high-level evidence to guide treatment decisions for severe, acute cholecystitis (inflammation of the gallbladder). Therefore, treatment decisions depend heavily on individual surgeon judgment, which is highly variable and potentially amenable to personalized, data-driven decision support. We test the hypothesis that surgeons' treatment recommendations misalign with perceived risks and benefits for laparoscopic cholecystectomy (surgical removal) vs. percutaneous cholecystostomy (image-guided drainage).

Methods

Surgery attendings, fellows, and residents applied individual judgement to standardized case scenarios in a live, web-based survey in estimating the quantitative risks and benefits of laparoscopic cholecystectomy vs. percutaneous cholecystostomy for both moderate and severe acute cholecystitis, as well as the likelihood that they would recommend cholecystectomy.

Results

Surgeons predicted similar 30-day morbidity rates for laparoscopic cholecystectomy and percutaneous cholecystostomy. However, a greater proportion of surgeons predicted low (<50%) likelihood of full recovery following percutaneous cholecystostomy compared with cholecystectomy for both moderate (30% vs. 2%, p < 0.001) and severe (62% vs. 38%, p < 0.001) cholecystitis. Ninety-eight percent of all surgeons were likely or very likely to recommend cholecystectomy for moderate cholecystitis; only 32% recommended cholecystectomy for severe cholecystitis (p < 0.001). There were no significant differences in predicted postoperative morbidity when respondents were stratified by academic rank or self-reported ability to predict complications or make treatment recommendations.

Conclusions

Surgeon recommendations for severe cholecystitis were discordant with perceived risks and benefits of treatment options. Surgeons predicted greater functional recovery after cholecystectomy but less than one-third recommended cholecystectomy. These findings suggest opportunities to augment surgical decision-making with personalized, data-driven decision support.

Randomized Clinical Trials of Machine Learning Interventions in Health Care: A Systematic Review

IMPORTANCE

Despite the potential of machine learning to improve multiple aspects of patient care, barriers to clinical adoption remain. Randomized clinical trials (RCTs) are often a prerequisite to large-scale clinical adoption of an intervention, and important questions remain regarding how machine learning interventions are being incorporated into clinical trials in health care.

OBJECTIVE

To systematically examine the design, reporting standards, risk of bias, and inclusivity of RCTs for medical machine learning interventions.

EVIDENCE REVIEW

In this systematic review, the Cochrane Library, Google Scholar, Ovid Embase, Ovid MEDLINE, PubMed, Scopus, and Web of Science Core Collection online databases were searched and citation chasing was done to find relevant articles published from the inception of each database to October 15, 2021. Search terms for machine learning, clinical decision-making, and RCTs were used. Exclusion criteria included implementation of a non-RCT design, absence of original data, and evaluation of nonclinical interventions. Data were extracted from published articles. Trial characteristics, including primary intervention, demographics, adherence to the CONSORT-AI reporting guideline, and Cochrane risk of bias were analyzed.

FINDINGS

Literature search yielded 19 737 articles, of which 41 RCTs involved a median of 294 participants (range, 17-2488 participants). A total of 16 RCTS (39%) were published in 2021, 21 (51%) were conducted at single sites, and 15 (37%) involved endoscopy. No trials adhered to all CONSORT-AI standards. Common reasons for nonadherence were not assessing poor-quality or unavailable input data (38 trials [93%]), not analyzing performance errors (38 [93%]), and not including a statement regarding code or algorithm availability (37 [90%]). Overall risk of bias was high in 7 trials (17%). Of 11 trials (27%) that reported race and ethnicity data, the median proportion of participants from underrepresented minority groups was 21% (range, 0%-51%).

CONCLUSIONS AND RELEVANCE

This systematic review found that despite the large number of medical machine learning-based algorithms in development, few RCTs for these technologies have been conducted. Among published RCTs, there was high variability in adherence to reporting standards and risk of bias and a lack of participants from underrepresented minority groups. These findings merit attention and should be considered in future RCT design and reporting.

Performance of the Hypotension Prediction Index May Be Overestimated Due to Selection Bias

The Hypotension Prediction Index is a proprietary prediction model incorporated into a commercially available intraoperative hemodynamic monitoring system. The Hypotension Prediction Index uses multiple features of the arterial blood pressure waveform to predict hypotension. The index publication introducing the Hypotension Prediction Index describes the selection of training and validation data. Although precise details of the Hypotension Prediction Index algorithm are proprietary, the authors describe a selection process whereby a mean arterial pressure (MAP) less than 75 mmHg will always predict hypotension. We hypothesize that the data selection process introduced a systematic bias that resulted in an overestimation of the current MAP value's ability to predict future hypotension. Since current MAP is a predictive variable contributing to Hypotension Prediction Index, this exaggerated predictive performance likely also applies to the corresponding Hypotension Prediction Index value. Other existing validation studies appear similarly problematic, suggesting that additional validation work and, potentially, updates to the Hypotension Prediction Index model may be necessary.

Randomized Controlled Trials of Artificial Intelligence in Clinical Practice: Systematic Review

BACKGROUND

The number of artificial intelligence (AI) studies in medicine has exponentially increased recently. However, there is no clear quantification of the clinical benefits of implementing AI-assisted tools in patient care.

OBJECTIVE

This study aims to systematically review all published randomized controlled trials (RCTs) of AI-assisted tools to characterize their performance in clinical practice.

METHODS

CINAHL, Cochrane Central, Embase, MEDLINE, and PubMed were searched to identify relevant RCTs published up to July 2021 and comparing the performance of AI-assisted tools with conventional clinical management without AI assistance. We evaluated the primary end points of each study to determine their clinical relevance. This systematic review was conducted following the updated PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 guidelines.

RESULTS

Among the 11,839 articles retrieved, only 39 (0.33%) RCTs were included. These RCTs were conducted in an approximately equal distribution from North America, Europe, and Asia. AI-assisted tools were implemented in 13 different clinical specialties. Most RCTs were published in the field of gastroenterology, with 15 studies on AI-assisted endoscopy. Most RCTs studied biosignal-based AI-assisted tools, and a minority of RCTs studied AI-assisted tools drawn from clinical data. In 77% (30/39) of the RCTs, AI-assisted interventions outperformed usual clinical care, and clinically relevant outcomes improved with AI-assisted intervention in 70% (21/30) of the studies. Small sample size and single-center design limited the generalizability of these studies.

CONCLUSIONS

There is growing evidence supporting the implementation of AI-assisted tools in daily clinical practice; however, the number of available RCTs is limited and heterogeneous. More RCTs of AI-assisted tools integrated into clinical practice are needed to advance the role of AI in medicine.

TRIAL REGISTRATION

PROSPERO CRD42021286539; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=286539.

Methylation risk scores are associated with a collection of phenotypes within electronic health record systems

Inference of clinical phenotypes is a fundamental task in precision medicine, and has therefore been heavily investigated in recent years in the context of electronic health records (EHR) using a large arsenal of machine learning techniques, as well as in the context of genetics using polygenic risk scores (PRS). In this work, we considered the epigenetic analog of PRS, methylation risk scores (MRS), a linear combination of methylation states. We measured methylation across a large cohort (n = 831) of diverse samples in the UCLA Health biobank, for which both genetic and complete EHR data are available. We constructed MRS for 607 phenotypes spanning diagnoses, clinical lab tests, and medication prescriptions. When added to a baseline set of predictive features, MRS significantly improved the imputation of 139 outcomes, whereas the PRS improved only 22 (median improvement for methylation 10.74%, 141.52%, and 15.46% in medications, labs, and diagnosis codes, respectively, whereas genotypes only improved the labs at a median increase of 18.42%). We added significant MRS to state-of-the-art EHR imputation methods that leverage the entire set of medical records, and found that including MRS as a medical feature in the algorithm significantly improves EHR imputation in 37% of lab tests examined (median R² increase 47.6%). Finally, we replicated several MRS in multiple external studies of methylation (minimum p-value of 2.72 × 10⁻⁷) and replicated 22 of 30 tested MRS internally in two separate cohorts of different ethnicity. Our publicly available results and weights show promise for methylation risk scores as clinical and scientific tools.

Predicting intraoperative hypotension using deep learning with waveforms of arterial blood pressure, electroencephalogram, and electrocardiogram: Retrospective study

To develop deep learning models for predicting Interoperative hypotension (IOH) using waveforms from arterial blood pressure (ABP), electrocardiogram (ECG), and electroencephalogram (EEG), and to determine whether combination ABP with EEG or CG improves model performance. Data were retrieved from VitalDB, a public data repository of vital signs taken during surgeries in 10 operating rooms at Seoul National University Hospital from January 6, 2005, to March 1, 2014. Retrospective data from 14,140 adult patients undergoing non-cardiac surgery with general anaesthesia were used. The predictive performances of models trained with different combinations of waveforms were evaluated and compared at time points at 3, 5, 10, 15 minutes before the event. The performance was calculated by area under the receiver operating characteristic (AUROC), area under the precision-recall curve (AUPRC), sensitivity and specificity. The model performance was better in the model using both ABP and EEG waveforms than in all other models at all time points (3, 5, 10, and 15 minutes before an event) Using high-fidelity ABP and EEG waveforms, the model predicted IOH with a AUROC and AUPRC of 0.935 [0.932 to 0.938] and 0.882 [0.876 to 0.887] at 5 minutes before an IOH event. The output of both ABP and EEG was more calibrated than that using other combinations or ABP alone. The results demonstrate that a predictive deep neural network can be trained using ABP, ECG, and EEG waveforms, and the combination of ABP and EEG improves model performance and calibration.

Clinical Implication of the Acumen Hypotension Prediction Index for Reducing Intraoperative Haemorrhage in Patients Undergoing Lumbar Spinal Fusion Surgery: A Prospective Randomised Controlled Single-Blinded Trial

We investigated the clinical implication of the Hypotension Prediction Index (HPI) in decreasing amount of surgical haemorrhage and requirements of blood transfusion compared to the conventional method (with vs. without HPI monitoring). A prospective, randomised controlled-trial of 19- to 73-year-old patients (n = 76) undergoing elective lumbar spinal fusion surgery was performed. According to the exclusion criteria, the patients were divided into the non-HPI (n = 33) and HPI (n = 35) groups. The targeted-induced hypotension systolic blood pressure was 80−100 mmHg (in both groups), with HPI > 85 (in the HPI group). Intraoperative bleeding was lower in the HPI group (299.3 ± 219.8 mL) than in the non-HPI group (532 ± 232.68 mL) (p = 0.001). The non-HPI group had a lower level of haemoglobin at the end of the surgery with a larger decline in levels. The incidence of postoperative transfusion of red blood cells was higher in the non-HPI group than in the HPI group (9 (27.3%) vs. 1 (2.9%)). The use of HPI monitoring may play a role in providing timely haemodynamic information that leads to improving the quality of induced hypotension care and to ameliorate intraoperative surgical blood loss and postoperative demand for blood transfusion in patients undergoing lumbar fusion surgery.

The future of Cardiothoracic surgery in Artificial intelligence

Humans' great and quick technological breakthroughs in the previous decade have undoubtedly influenced how surgical procedures are executed in the operating room. AI is becoming incredibly influential for surgical decision-making to help surgeons make better projections about the implications of surgical operations by considering different sources of data such as patient health conditions, disease natural history, patient values, and finance. Although the application of artificial intelligence in healthcare settings is rapidly increasing, its mainstream application in clinical practice remains limited. The use of machine learning algorithms in thoracic surgery is extensive, including different clinical stages. By leveraging techniques such as machine learning, computer vision, and robotics, AI may play a key role in diagnostic augmentation, operative management, pre-and post-surgical patient management, and upholding safety standards. AI, particularly in complex surgical procedures such as cardiothoracic surgery, may be a significant help to surgeons in executing more intricate surgeries with greater success, fewer complications, and ensuring patient safety, while also providing resources for robust research and better dissemination of knowledge. In this paper, we present an overview of AI applications in thoracic surgery and its related components, including contemporary projects and technology that use AI in cardiothoracic surgery and general care. We also discussed the future of AI and how high-tech operating rooms will use human-machine collaboration to improve performance and patient safety, as well as its future directions and limitations. It is vital for the surgeons to keep themselves acquainted with the latest technological advancement in AI order to grasp this technology and easily integrate it into clinical practice when it becomes accessible. This review is a great addition to literature, keeping practicing and aspiring surgeons up to date on the most recent advances in AI and cardiothoracic surgery.

•

This literature review tells about the role of Artificial Intelligence in Cardiothoracic Surgery.

•

Discussed the future of AI and how high-tech operating rooms will use human-machine collaboration to improve performance and patient safety, as well as its future directions and limitations.

•

Vital for the surgeons to keep themselves acquainted with the latest technological advancement in AI order to grasp this technology and easily integrate it into clinical practice when it becomes accessible.

Assessment of Lung Cancer Risk Among Smokers for Whom Annual Screening Is Not Recommended

Importance

The US Preventive Services Task Force does not recommend annual lung cancer screening with low-dose computed tomography (LDCT) for adults aged 50 to 80 years who are former smokers with 20 or more pack-years of smoking who quit 15 or more years ago or current smokers with less than 20 pack-years of smoking.

Objective

To determine the risk of lung cancer in older smokers for whom LDCT screening is not recommended.

Design, Settings, and Participants

This cohort study used the Cardiovascular Health Study (CHS) data sets obtained from the National Heart, Lung and Blood Institute, which also sponsored the study. The CHS enrolled 5888 community-dwelling individuals aged 65 years and older in the US from June 1989 to June 1993 and collected extensive baseline data on smoking history. The current analysis was restricted to 4279 individuals free of cancer who had baseline data on pack-year smoking history and duration of smoking cessation. The current analysis was conducted from January 7, 2022, to May 25, 2022.

Exposures

Current and prior tobacco use.

Main Outcomes and Measures

Incident lung cancer during a median (IQR) of 13.3 (7.9-18.8) years of follow-up (range, 0 to 22.6) through December 31, 2011. A Fine-Gray subdistribution hazard model was used to estimate incidence of lung cancer in the presence of competing risk of death. Cox cause-specific hazard regression models were used to estimate hazard ratios (HRs) and 95% CIs for incident lung cancer.

Results

There were 4279 CHS participants (mean [SD] age, 72.8 [5.6] years; 2450 [57.3%] women; 663 [15.5%] African American, 3585 [83.8%] White, and 31 [0.7%] of other race or ethnicity) included in the current analysis. Among the 861 nonheavy smokers (<20 pack-years), the median (IQR) pack-year smoking history was 7.6 (3.3-13.5) pack-years for the 615 former smokers with 15 or more years of smoking cessation, 10.0 (5.3-14.9) pack-years for the 146 former smokers with less than 15 years of smoking cessation, and 11.4 (7.3-14.4) pack-years for the 100 current smokers. Among the 1445 heavy smokers (20 or more pack-years), the median (IQR) pack-year smoking history was 34.8 (26.3-48.0) pack-years for the 516 former smokers with 15 or more years of smoking cessation, 48.0 (35.0-70.0) pack-years for the 497 former smokers with less than 15 years of smoking cessation, and 48.8 (31.6-57.0) pack-years for the 432 current smokers. Incident lung cancer occurred in 10 of 1973 never smokers (0.5%), 5 of 100 current smokers with less than 20 pack-years of smoking (5.0%), and 26 of 516 former smokers with 20 or more pack-years of smoking with 15 or more years of smoking cessation (5.0%). Compared with never smokers, cause-specific HRs for incident lung cancer in the 2 groups for whom LDCT is not recommended were 10.54 (95% CI, 3.60-30.83) for the current nonheavy smokers and 11.19 (95% CI, 5.40-23.21) for the former smokers with less than 15 years of smoking cessation; age, sex, and race-adjusted HRs were 10.06 (95% CI, 3.41-29.70) for the current nonheavy smokers and 10.22 (4.86-21.50) for the former smokers with less than 15 years of smoking cessation compared with never smokers.

Conclusions and Relevance

The findings of this cohort study suggest that there is a high risk of lung cancer among smokers for whom LDCT screening is not recommended, suggesting that prediction models are needed to identify high-risk subsets of these smokers for screening.

Artificial Intelligence (AI) and Internet of Medical Things (IoMT) Assisted Biomedical Systems for Intelligent Healthcare

Artificial intelligence (AI) is a modern approach based on computer science that develops programs and algorithms to make devices intelligent and efficient for performing tasks that usually require skilled human intelligence. AI involves various subsets, including machine learning (ML), deep learning (DL), conventional neural networks, fuzzy logic, and speech recognition, with unique capabilities and functionalities that can improve the performances of modern medical sciences. Such intelligent systems simplify human intervention in clinical diagnosis, medical imaging, and decision-making ability. In the same era, the Internet of Medical Things (IoMT) emerges as a next-generation bio-analytical tool that combines network-linked biomedical devices with a software application for advancing human health. In this review, we discuss the importance of AI in improving the capabilities of IoMT and point-of-care (POC) devices used in advanced healthcare sectors such as cardiac measurement, cancer diagnosis, and diabetes management. The role of AI in supporting advanced robotic surgeries developed for advanced biomedical applications is also discussed in this article. The position and importance of AI in improving the functionality, detection accuracy, decision-making ability of IoMT devices, and evaluation of associated risks assessment is discussed carefully and critically in this review. This review also encompasses the technological and engineering challenges and prospects for AI-based cloud-integrated personalized IoMT devices for designing efficient POC biomedical systems suitable for next-generation intelligent healthcare.