Development of a prediction model for hypotension after induction of anesthesia using machine learning

Changes in oxygen supply-demand balance during induction of general anesthesia: an exploratory study using remimazolam

PURPOSE

This study was performed to evaluate the changes in oxygen supply-demand balance during induction of general anesthesia using an indirect calorimeter capable of measuring oxygen consumption (VO2) and carbon dioxide production (VCO2).

METHODS

This study included patients scheduled for surgery in whom remimazolam was administered as a general anesthetic. VO2 and VCO2 were measured at different intervals: upon awakening (T1), 15 min after tracheal intubation (T2), and 1 h after T2 (T3). Oxygen delivery (DO2) was calculated simultaneously with these measurements. VO2 was ascertained using an indirect calorimeter and further calculated using vital signs, among other factors. DO2 was derived from cardiac output and arterial blood gas analysis performed with an arterial pressure-based cardiac output measurement system.

RESULTS

VO2, VCO2, and DO2 decreased significantly from T1 to T2 and T3 [VO2/body surface area (BSA) (ml/min/m2): T1, 130 (122-146); T2, 107 (83-139); T3, 97 (93-121); p = 0.011], [VCO2/BSA (ml/min/m2): T1, 115 (105-129); T2, 90 (71-107); T3, 81 (69-101); p = 0.011], [DO2/BSA (ml/min/m2): T1, 467 (395-582); T2, 347 (286-392); T3, 382 (238-414); p = 0.0020]. Among the study subjects, a subset exhibited minimal reduction in VCO2. Although the respiratory frequency was titrated on the basis of end-tidal CO2 levels, there was no significant difference between the groups.

CONCLUSION

General anesthetic induction with remimazolam decreased VO2, VCO2, and DO2.

Assessment of Blood Pressure and Heart Rate Related Variables in Acute Stroke Patients Receiving Intravenous Antihypertensive Medication Infusions

BACKGROUND

We performed an analysis of a large intensive care unit electronic database to provide preliminary estimates of various blood pressure parameters in patients with acute stroke receiving intravenous (IV) antihypertensive medication and determine the relationship with in-hospital outcomes.

METHODS

We identified the relationship between pre-treatment and post-treatment systolic blood pressure (SBP) and heart rate (HR)-related variables and in-hospital mortality and acute kidney injury in patients with acute stroke receiving IV clevidipine, nicardipine, or nitroprusside using data provided in the Medical Information Mart for Intensive Care (MIMIC) IV database.

RESULTS

A total of 1830 patients were treated with IV clevidipine (n = 64), nicardipine (n = 1623), or nitroprusside (n = 143). The standard deviations [SDs] of pre-treatment SBP (16.3 vs. 13.7, p ≤ 0.001) and post-treatment SBP (15.4 vs. 14.4, p = 0.004) were higher in patients who died compared with those who survived, particularly in patients with intracerebral hemorrhage (ICH). The mean SBP was significantly lower post treatment compared with pre-treatment values for clevidipine (130.7 mm Hg vs. 142.5 mm Hg, p = 0.006), nicardipine (132.8 mm Hg vs. 141.6 mm Hg, p ≤ 0.001), and nitroprusside (126.2 mm Hg vs. 139.6 mm Hg, p ≤ 0.001). There were no differences in mean SDs post treatment compared with pre-treatment values for clevidipine (14.5 vs. 13.5, p = 0.407), nicardipine (14.2 vs. 14.6, p = 0.142), and nitroprusside (14.8 vs. 14.8, p = 0.997). The SDs of pre-treatment and post-treatment SBP were not significantly different in patients with ischemic stroke treated with IV clevidipine, nicardipine, or nitroprusside or for patients with ICH treated with IV clevidipine or nitroprusside. However, patients with ICH treated with IV nicardipine had a significantly higher SD of post-treatment SBP (13.1 vs. 14.2, p = 0.0032).

CONCLUSIONS

We found that SBP fluctuations were associated with in-hospital mortality in patients with acute stroke. IV antihypertensive medication reduced SBP but did not reduce SBP fluctuations in this observational study. Our results highlight the need for optimizing therapeutic interventions to reduce SBP fluctuations in patients with acute stroke.

User-Centered Design of a Machine Learning Dashboard for Prediction of Postoperative Complications

BACKGROUND

Machine learning models can help anesthesiology clinicians assess patients and make clinical and operational decisions, but well-designed human-computer interfaces are necessary for machine learning model predictions to result in clinician actions that help patients. Therefore, the goal of this study was to apply a user-centered design framework to create a user interface for displaying machine learning model predictions of postoperative complications to anesthesiology clinicians.

METHODS

Twenty-five anesthesiology clinicians (attending anesthesiologists, resident physicians, and certified registered nurse anesthetists) participated in a 3-phase study that included (phase 1) semistructured focus group interviews and a card sorting activity to characterize user workflows and needs; (phase 2) simulated patient evaluation incorporating a low-fidelity static prototype display interface followed by a semistructured interview; and (phase 3) simulated patient evaluation with concurrent think-aloud incorporating a high-fidelity prototype display interface in the electronic health record. In each phase, data analysis included open coding of session transcripts and thematic analysis.

RESULTS

During the needs assessment phase (phase 1), participants voiced that (a) identifying preventable risk related to modifiable risk factors is more important than nonpreventable risk, (b) comprehensive patient evaluation follows a systematic approach that relies heavily on the electronic health record, and (c) an easy-to-use display interface should have a simple layout that uses color and graphs to minimize time and energy spent reading it. When performing simulations using the low-fidelity prototype (phase 2), participants reported that (a) the machine learning predictions helped them to evaluate patient risk, (b) additional information about how to act on the risk estimate would be useful, and (c) correctable problems related to textual content existed. When performing simulations using the high-fidelity prototype (phase 3), usability problems predominantly related to the presentation of information and functionality. Despite the usability problems, participants rated the system highly on the System Usability Scale (mean score, 82.5; standard deviation, 10.5).

CONCLUSIONS

Incorporating user needs and preferences into the design of a machine learning dashboard results in a display interface that clinicians rate as highly usable. Because the system demonstrates usability, evaluation of the effects of implementation on both process and clinical outcomes is warranted.

Artificial intelligence and its clinical application in Anesthesiology: a systematic review

PURPOSE

Application of artificial intelligence (AI) in medicine is quickly expanding. Despite the amount of evidence and promising results, a thorough overview of the current state of AI in clinical practice of anesthesiology is needed. Therefore, our study aims to systematically review the application of AI in this context.

METHODS

A systematic review was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. We searched Medline and Web of Science for articles published up to November 2022 using terms related with AI and clinical practice of anesthesiology. Articles that involved animals, editorials, reviews and sample size lower than 10 patients were excluded. Characteristics and accuracy measures from each study were extracted.

RESULTS

A total of 46 articles were included in this review. We have grouped them into 4 categories with regard to their clinical applicability: (1) Depth of Anesthesia Monitoring; (2) Image-guided techniques related to Anesthesia; (3) Prediction of events/risks related to Anesthesia; (4) Drug administration control. Each group was analyzed, and the main findings were summarized. Across all fields, the majority of AI methods tested showed superior performance results compared to traditional methods.

CONCLUSION

AI systems are being integrated into anesthesiology clinical practice, enhancing medical professionals' skills of decision-making, diagnostic accuracy, and therapeutic response.

Prediction of Complications and Prognostication in Perioperative Medicine: A Systematic Review and PROBAST Assessment of Machine Learning Tools

BACKGROUND

The utilization of artificial intelligence and machine learning as diagnostic and predictive tools in perioperative medicine holds great promise. Indeed, many studies have been performed in recent years to explore the potential. The purpose of this systematic review is to assess the current state of machine learning in perioperative medicine, its utility in prediction of complications and prognostication, and limitations related to bias and validation.

METHODS

A multidisciplinary team of clinicians and engineers conducted a systematic review using the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) protocol. Multiple databases were searched, including Scopus, Cumulative Index to Nursing and Allied Health Literature (CINAHL), the Cochrane Library, PubMed, Medline, Embase, and Web of Science. The systematic review focused on study design, type of machine learning model used, validation techniques applied, and reported model performance on prediction of complications and prognostication. This review further classified outcomes and machine learning applications using an ad hoc classification system. The Prediction model Risk Of Bias Assessment Tool (PROBAST) was used to assess risk of bias and applicability of the studies.

RESULTS

A total of 103 studies were identified. The models reported in the literature were primarily based on single-center validations (75%), with only 13% being externally validated across multiple centers. Most of the mortality models demonstrated a limited ability to discriminate and classify effectively. The PROBAST assessment indicated a high risk of systematic errors in predicted outcomes and artificial intelligence or machine learning applications.

CONCLUSIONS

The findings indicate that the development of this field is still in its early stages. This systematic review indicates that application of machine learning in perioperative medicine is still at an early stage. While many studies suggest potential utility, several key challenges must be first overcome before their introduction into clinical practice.

EDITOR’S PERSPECTIVE

Efficacy and safety of remimazolam compared with propofol in hypertensive patients undergoing breast cancer surgery: a single-center, randomized, controlled study

BACKGROUND

Remimazolam, as a novel anesthetic, has recently been shown to improve hemodynamic stability during anesthesia induction and maintenance; however, it has not been reported in the hypertensive population. This study aimed to compare the effects of remimazolam and propofol on hemodynamic stability in hypertensive patients undergoing breast cancer surgery.

METHODS

We enrolled 120 hypertensive patients undergoing breast cancer surgery in this prospective study and randomly allocated them to remimazolam (n = 60) or propofol (n = 60) groups. Anesthesia regimens were consistent between groups, except for the administration of remimazolam and propofol. Our primary outcome was the incidence of post-induction hypotension, which was either an absolute mean arterial pressure (MAP) < 60 mmHg or a > 30% relative drop in MAP compared to baseline within 20 min of induction or from induction to the start of surgery. Secondary outcomes included minimum MAP and MAP at different time points during anesthesia, the application of vasoactive drugs, adverse events, and the patient's self-reported Quality of Recovery-40 scale for the day after surgery.

RESULTS

The incidence of post-induction hypotension was lower and the minimum MAP during induction was higher in the remimazolam group than those in the propofol group. There were no significant differences between the two groups in the remaining outcomes.

CONCLUSION

Remimazolam is safe and effective in hypertensive patients undergoing breast cancer surgery. Induction with remimazolam in hypertensive patients may result in more stable hemodynamics than propofol.

TRIAL REGISTRATION

This study was registered at the Chinese Clinical Trials Registry ( http://www.chictr.org.cn ) on 03/12/2020, with registration number ChiCTR2000040579.

Protocol for development and validation of a prediction model for post-induction hypotension in elderly patients undergoing non-cardiac surgery: a prospective cohort study

INTRODUCTION

Post-induction hypotension (PIH) is a common event in elderly surgical patients and is associated with increased postoperative morbidity and mortality. This study aims to develop and validate a PIH prediction model for elderly patients undergoing elective non-cardiac surgery to identify potential PIH in advance and help to take preventive measures.

METHODS AND ANALYSIS

A total of 938 elderly surgical patients (n=657 for development and internal validation, n=281 for temporal validation) will be continuously recruited at The First Affiliated Hospital of Soochow University in Suzhou, China. The main outcome is PIH during the first 15 min after anaesthesia induction or before skin incision (whichever occurs first). We select candidate predictors based on published literature, professional knowledge and clinical expertise. For model development, we will use the least absolute shrinkage and selection operator regression analysis and multivariable logistic regression. For internal validation, we will apply the bootstrapping technique. After model development and internal validation, temporal validation will be conducted in patients recruited in another time period. We will use the discrimination, calibration and max-rescaled Brier score in the temporal validation cohort. Furthermore, the clinical utility of the prediction model will be assessed using the decision curve analysis, and the results will be presented in a nomogram and a web-based risk calculator.

ETHICS AND DISSEMINATION

Ethical approval was obtained from the Ethics Committee of the First Affiliated Hospital of Soochow University (Approval No. 2023-012). This PIH risk prediction model will be published in a peer-reviewed journal.

TRIAL REGISTRATION NUMBER

ChiCTR2200066201.

Machine-learning-based adverse drug event prediction from observational health data: A review

Adverse drug events (ADEs) are responsible for a significant number of hospital admissions and fatalities. Machine learning models have been developed to assess the individual patient risk of having an ADE. In this article, we have reviewed studies addressing the prediction of ADEs in observational health data with machine learning. The field of individualised ADE prediction is rapidly emerging through the increasing availability of additional data modalities (e.g., genetic data, screening data, wearables data) and advanced deep learning models such as transformers. Consequently, personalised adverse drug event predictions are becoming more feasible and tangible.

Evaluation of machine learning models as decision aids for anesthesiologists

Machine Learning (ML) models have been developed to predict perioperative clinical parameters. The objective of this study was to determine if ML models can serve as decision aids to improve anesthesiologists' prediction of peak intraoperative glucose values and postoperative opioid requirements. A web-based tool was used to present actual surgical case and patient information to 10 practicing anesthesiologists. They were asked to predict peak glucose levels and post-operative opioid requirements for 100 surgical patients with and without presenting ML model estimations of peak glucose and opioid requirements. The accuracies of the anesthesiologists' estimates with and without ML estimates as reference were compared. A questionnaire was also sent to the participating anesthesiologists to obtain their feedback on ML decision support. The accuracy of peak glucose level estimates by the anesthesiologists increased from 79.0 ± 13.7% without ML assistance to 84.7 ± 11.5% (< 0.001) when ML estimates were provided as reference. The accuracy of opioid requirement estimates increased from 18% without ML assistance to 42% (p < 0.001) when ML estimates were provided as reference. When ML estimates were provided, predictions of peak glucose improved for 8 out of the 10 anesthesiologists, while predictions of opioid requirements improved for 7 of the 10 anesthesiologists. Feedback questionnaire responses revealed that the anesthesiologist primarily used the ML estimates as reference to modify their clinical judgement. ML models can improve anesthesiologists' estimation of clinical parameters. ML predictions primarily served as reference information that modified an anesthesiologist's clinical estimate.

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.

Identification of Preanesthetic History Elements by a Natural Language Processing Engine

BACKGROUND

Methods that can automate, support, and streamline the preanesthesia evaluation process may improve resource utilization and efficiency. Natural language processing (NLP) involves the extraction of relevant information from unstructured text data. We describe the utilization of a clinical NLP pipeline intended to identify elements relevant to preoperative medical history by analyzing clinical notes. We hypothesize that the NLP pipeline would identify a significant portion of pertinent history captured by a perioperative provider.

METHODS

For each patient, we collected all pertinent notes from the institution's electronic medical record that were available no later than 1 day before their preoperative anesthesia clinic appointment. Pertinent notes included free-text notes consisting of history and physical, consultation, outpatient, inpatient progress, and previous preanesthetic evaluation notes. The free-text notes were processed by a Named Entity Recognition pipeline, an NLP machine learning model trained to recognize and label spans of text that corresponded to medical concepts. These medical concepts were then mapped to a list of medical conditions that were of interest for a preanesthesia evaluation. For each condition, we calculated the percentage of time across all patients in which (1) the NLP pipeline and the anesthesiologist both captured the condition; (2) the NLP pipeline captured the condition but the anesthesiologist did not; and (3) the NLP pipeline did not capture the condition but the anesthesiologist did.

RESULTS

A total of 93 patients were included in the NLP pipeline input. Free-text notes were extracted from the electronic medical record of these patients for a total of 9765 notes. The NLP pipeline and anesthesiologist agreed in 81.24% of instances on the presence or absence of a specific condition. The NLP pipeline identified information that was not noted by the anesthesiologist in 16.57% of instances and did not identify a condition that was noted by the anesthesiologist's review in 2.19% of instances.

CONCLUSIONS

In this proof-of-concept study, we demonstrated that utilization of NLP produced an output that identified medical conditions relevant to preanesthetic evaluation from unstructured free-text input. Automation of risk stratification tools may provide clinical decision support or recommend additional preoperative testing or evaluation. Future studies are needed to integrate these tools into clinical workflows and validate its efficacy.

Predictors of Post-induction Hypotension for Patients With Pulmonary Hypertension

Purpose The purpose is to identify predictors of post-induction hypotension (PIH) during general anesthesia in a population of patients with varying degrees of pulmonary hypertension (PH). Methods This is a single-center, retrospective, observational study of perioperative data obtained via electronic health records from patients with PH undergoing surgery over a five-year period. Baseline patient characteristics, peri-induction management variables, and pre-induction mean arterial pressure (MAP) were statistically analyzed using Kruskal-Wallis rank sum tests, Pearson's chi-squared tests, and logistic regression analysis to identify risk factors for PIH. We further assessed the relationship between PH and PIH using propensity score matching. Primary outcomes include a percent decrease in post-induction blood pressure as well as a post-induction nadir with a threshold of 55 mm Hg. Results Eight hundred fifty-seven patients in the cohort stratified by severity of PH reveal that advanced age (p < 0.001), higher BMI (P = 0.002), higher American Society of Anesthesiologists (ASA) score (P = 0.001), and renal and cardiac comorbidities (P < 0.001) are associated with PH severity. None of our tested parameters were significantly predictive for PIH in patients with PH. Right heart failure was found to be weakly and non-significantly predictive of PIH in patients with PH (P = 0.052, odds ratio [OR] = 1.116). Diabetes (P = 0.007, OR = 0.919) and maintenance of spontaneous ventilation (P = 0.012, OR = 0.925) were associated with decreased rates of PIH. Conclusion Hypotension after induction of general anesthesia in patients with PH is a serious problem, yet statistically significant risk factors were not identified. History of diabetes and preservation of spontaneous ventilation had a significant but weak effect of decreasing rates of PIH. This pilot study was limited by retrospective design and warrants further analysis with a prospective cohort.

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.

Development of a machine learning model for the prediction of the short-term mortality in patients in the intensive care unit

PURPOSE

The aim of this study was to develop and evaluate a machine learning model that predicts short-term mortality in the intensive care unit using the trends of four easy-to-collect vital signs.

MATERIALS AND METHODS

The primary training cohort included 1968 patients at the Veterans Health Service Medical Center. The external validation cohort comprised 409 patients at Seoul National University Hospital. Datasets of heart rate, systolic blood pressure, diastolic blood pressure, and peripheral capillary oxygen saturation (SpO2) measured every hour for 10 h were used. The performances of mortality prediction models generated using five machine learning algorithms, Random Forest (RF), XGboost, perceptron, convolutional neural network, and Long Short-Term Memory, were calculated and compared using area under the receiver operating characteristic curve (AUROC) values and an external validation dataset.

RESULTS

The machine learning model generated using the RF algorithm showed the best performance. Its AUROC was 0.922, which is much better than the 0.8408 of the Acute Physiology and Chronic Health Evaluation II. The machine learning model developed using SpO2 showed the best performance (AUROC, 0.89).

CONCLUSIONS

This simple yet powerful new mortality prediction model could be useful for early detection of probable mortality and appropriate medical intervention, especially in rapidly deteriorating patients.

Intraoperative Hypotension Prediction Model Based on Systematic Feature Engineering and Machine Learning

Arterial hypotension is associated with incidence of postoperative complications, such as myocardial infarction or acute kidney injury. Little research has been conducted for the real-time prediction of hypotension, even though many studies have been performed to investigate the factors which affect hypotension events. This forecasting problem is quite challenging compared to diagnosis that detects high-risk patients at current. The forecasting problem that specifies when events occur is more challenging than the forecasting problem that does not specify the event time. In this work, we challenge the forecasting problem in 5 min advance. For that, we aim to build a systematic feature engineering method that is applicable regardless of vital sign species, as well as a machine learning model based on these features for real-time predictions 5 min before hypotension. The proposed feature extraction model includes statistical analysis, peak analysis, change analysis, and frequency analysis. After applying feature engineering on invasive blood pressure (IBP), we build a random forest model to differentiate a hypotension event from other normal samples. Our model yields an accuracy of 0.974, a precision of 0.904, and a recall of 0.511 for predicting hypotensive events.

Artificial intelligence in perioperative medicine - a narrative review

Recent advancements in artificial intelligence (AI) techniques have enabled the development of accurate prediction models using clinical big data. AI models for perioperative risk stratification, intraoperative event prediction, biosignal analyses, and intensive care medicine have been developed in the field of perioperative medicine. Some of these models have been validated using external datasets and randomized controlled trials. Once these models are implemented in electronic health record systems or software medical devices, they could help anesthesiologists improve clinical outcomes by accurately predicting complications and suggesting optimal treatment strategies in real-time. This review provides an overview of the AI techniques used in perioperative medicine and a summary of the studies that have been published using these techniques. Understanding these techniques will aid in their appropriate application in clinical practice.

Artificial intelligence and telemedicine in anesthesia: potential and problems

INTRODUCTION

The application of novel technologies like Artificial Intelligence (AI), Machine Learning (ML) and telemedicine in anesthesiology could play a role in transforming the future of health care. In the present review we discuss the current applications of AI and telemedicine in anesthesiology and perioperative care, exploring their potential influence and the possible hurdles.

EVIDENCE ACQUISITION

AI technologies have the potential to deeply impact all phases of perioperative care from accurate risk prediction to operating room organization, leading to increased cost-effective care quality and better outcomes. Telemedicine is reported as a successful mean within the anaesthetic pathway, including preoperative evaluation, remote patient monitoring, and postoperative care.

EVIDENCE SYNTHESIS

The utilization of AI and telemedicine is promising encouraging results in perioperative management, nevertheless several hurdles remain to be overcome before these tools could be integrated in our daily practice.

CONCLUSIONS

AI models and telemedicine can significantly influence all phases of perioperative care, helping physicians in the development of precision medicine.

Machine learning in perioperative medicine: a systematic review

Background

Risk stratification plays a central role in anesthetic evaluation. The use of Big Data and machine learning (ML) offers considerable advantages for collection and evaluation of large amounts of complex health-care data. We conducted a systematic review to understand the role of ML in the development of predictive post-surgical outcome models and risk stratification.

Methods

Following the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) guidelines, we selected the period of the research for studies from 1 January 2015 up to 30 March 2021. A systematic search in Scopus, CINAHL, the Cochrane Library, PubMed, and MeSH databases was performed; the strings of research included different combinations of keywords: “risk prediction,” “surgery,” “machine learning,” “intensive care unit (ICU),” and “anesthesia” “perioperative.” We identified 36 eligible studies. This study evaluates the quality of reporting of prediction models using the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) checklist.

Results

The most considered outcomes were mortality risk, systemic complications (pulmonary, cardiovascular, acute kidney injury (AKI), etc.), ICU admission, anesthesiologic risk and prolonged length of hospital stay. Not all the study completely followed the TRIPOD checklist, but the quality was overall acceptable with 75% of studies (Rev #2, comm #minor issue) showing an adherence rate to TRIPOD more than 60%. The most frequently used algorithms were gradient boosting (n = 13), random forest (n = 10), logistic regression (LR; n = 7), artificial neural networks (ANNs; n = 6), and support vector machines (SVM; n = 6). Models with best performance were random forest and gradient boosting, with AUC > 0.90.

Conclusions

The application of ML in medicine appears to have a great potential. From our analysis, depending on the input features considered and on the specific prediction task, ML algorithms seem effective in outcomes prediction more accurately than validated prognostic scores and traditional statistics. Thus, our review encourages the healthcare domain and artificial intelligence (AI) developers to adopt an interdisciplinary and systemic approach to evaluate the overall impact of AI on perioperative risk assessment and on further health care settings as well.

Central Hypovolemia Detection During Environmental Stress-A Role for Artificial Intelligence?

The first step to exercise is preceded by the required assumption of the upright body position, which itself involves physical activity. The gravitational displacement of blood from the chest to the lower parts of the body elicits a fall in central blood volume (CBV), which corresponds to the fraction of thoracic blood volume directly available to the left ventricle. The reduction in CBV and stroke volume (SV) in response to postural stress, post-exercise, or to blood loss results in reduced left ventricular filling, which may manifest as orthostatic intolerance. When termination of exercise removes the leg muscle pump function, CBV is no longer maintained. The resulting imbalance between a reduced cardiac output (CO) and a still enhanced peripheral vascular conductance may provoke post-exercise hypotension (PEH). Instruments that quantify CBV are not readily available and to express which magnitude of the CBV in a healthy subject should remains difficult. In the physiological laboratory, the CBV can be modified by making use of postural stressors, such as lower body "negative" or sub-atmospheric pressure (LBNP) or passive head-up tilt (HUT), while quantifying relevant biomedical parameters of blood flow and oxygenation. Several approaches, such as wearable sensors and advanced machine-learning techniques, have been followed in an attempt to improve methodologies for better prediction of outcomes and to guide treatment in civil patients and on the battlefield. In the recent decade, efforts have been made to develop algorithms and apply artificial intelligence (AI) in the field of hemodynamic monitoring. Advances in quantifying and monitoring CBV during environmental stress from exercise to hemorrhage and understanding the analogy between postural stress and central hypovolemia during anesthesia offer great relevance for healthy subjects and clinical populations.

Predicting anesthetic infusion events using machine learning

Recently, research has been conducted to automatically control anesthesia using machine learning, with the aim of alleviating the shortage of anesthesiologists. In this study, we address the problem of predicting decisions made by anesthesiologists during surgery using machine learning; specifically, we formulate a decision making problem by increasing the flow rate at each time point in the continuous administration of analgesic remifentanil as a supervised binary classification problem. The experiments were conducted to evaluate the prediction performance using six machine learning models: logistic regression, support vector machine, random forest, LightGBM, artificial neural network, and long short-term memory (LSTM), using 210 case data collected during actual surgeries. The results demonstrated that when predicting the future increase in flow rate of remifentanil after 1 min, the model using LSTM was able to predict with scores of 0.659 for sensitivity, 0.732 for specificity, and 0.753 for ROC-AUC; this demonstrates the potential to predict the decisions made by anesthesiologists using machine learning. Furthermore, we examined the importance and contribution of the features of each model using Shapley additive explanations-a method for interpreting predictions made by machine learning models. The trends indicated by the results were partially consistent with known clinical findings.

‘Exploring socioeconomic status as a global determinant of COVID-19 prevalence, using statistical, exploratory data analytic, and supervised machine learning techniques.’ (Preprint)

Background

The COVID-19 pandemic represents the most unprecedented global challenge in recent times. As the global community attempts to manage the pandemic in the long term, it is pivotal to understand what factors drive prevalence rates and to predict the future trajectory of the virus.

Objective

This study had 2 objectives. First, it tested the statistical relationship between socioeconomic status and COVID-19 prevalence. Second, it used machine learning techniques to predict cumulative COVID-19 cases in a multicountry sample of 182 countries. Taken together, these objectives will shed light on socioeconomic status as a global risk factor of the COVID-19 pandemic.

Methods

This research used exploratory data analysis and supervised machine learning methods. Exploratory analysis included variable distribution, variable correlations, and outlier detection. Following this, the following 3 supervised regression techniques were applied: linear regression, random forest, and adaptive boosting (AdaBoost). Results were evaluated using k-fold cross-validation and subsequently compared to analyze algorithmic suitability. The analysis involved 2 models. First, the algorithms were trained to predict 2021 COVID-19 prevalence using only 2020 reported case data. Following this, socioeconomic indicators were added as features and the algorithms were trained again. The Human Development Index (HDI) metrics of life expectancy, mean years of schooling, expected years of schooling, and gross national income were used to approximate socioeconomic status.

Results

All variables correlated positively with the 2021 COVID-19 prevalence, with R² values ranging from 0.55 to 0.85. Using socioeconomic indicators, COVID-19 prevalence was predicted with a reasonable degree of accuracy. Using 2020 reported case rates as a lone predictor to predict 2021 prevalence rates, the average predictive accuracy of the algorithms was low (R²=0.543). When socioeconomic indicators were added alongside 2020 prevalence rates as features, the average predictive performance improved considerably (R²=0.721) and all error statistics decreased. Thus, adding socioeconomic indicators alongside 2020 reported case data optimized the prediction of COVID-19 prevalence to a considerable degree. Linear regression was the strongest learner with R²=0.693 on the first model and R²=0.763 on the second model, followed by random forest (0.481 and 0.722) and AdaBoost (0.454 and 0.679). Following this, the second model was retrained using a selection of additional COVID-19 risk factors (population density, median age, and vaccination uptake) instead of the HDI metrics. However, average accuracy dropped to 0.649, which highlights the value of socioeconomic status as a predictor of COVID-19 cases in the chosen sample.

Conclusions

The results show that socioeconomic status is an important variable to consider in future epidemiological modeling, and highlights the reality of the COVID-19 pandemic as a social phenomenon and a health care phenomenon. This paper also puts forward new considerations about the application of statistical and machine learning techniques to understand and combat the COVID-19 pandemic.

Early intraoperative hypotension and its associated factors among surgical patients undergoing surgery under general anesthesia: An observational study

Background

Early intraoperative hypotension (eIOH) is a common complication of general anesthesia and is significantly associated with postoperative morbidity and mortality. The incidence of eIOH was high, especially in resource-limited settings. Identifying the factors associated with the occurrence of eIOH might allow avoidance and planning of a timely treatment of it.

Objective

To assess the incidence of early intraoperative hypotension and its associated factors among surgical patients undergoing Surgical procedures under general anesthesia at XX Comprehensive Specialized Hospital, North-central Ethiopia, 2021.

Methods

A total of 424 surgical patients under general anesthesia were included in this prospective observational study. The data were collected by a structured questionnaire. Variables with p-values of less than 0.2 in the bivariable logistic regression were fitted to multivariable logistic regression. Data was presented in odds ratios with a 95% confidence interval. Descriptive statistics were used to summarize data.

Results

The incidence of early intra-operative hypotension (eIOH) was 21.2%. In this study older age (age≥ 60 years) (AOR: 2.063 (95% CI;1.194, 3.563)), ASA physical status (AOR: (II2.259 (95% CI;1.229, 4.153)), III(AOR: 2.810 (95% CI;1.319, 5.986)), a BMI of 25–29.9 kg/m2 (AOR: 2.098 (1.128, 3.901), a BMI of ≥30 kg/m2 (AOR: 3.090 (95% CI;1.324, 7.210)), emergency surgical procedures (AOR: 2.215 (95% CI;1.287, 3.810)), the estimated blood loss greater than 500 ml (AOR: 2.510 (95% CI;1.478, 4.261)) were found to be independent factors of eIOH.

Conclusion

This study revealed that the incidence of eIOH was high (21.2%). Older age, ASA II and III, BMI ≥25, emergency surgical procedures, and a significant amount of blood loss (EBL ≥500 ml) were the main predictors of an increased occurrence of eIOH.

•

Early intraoperative hypotension is associated with postoperative morbidity and mortality.

•

Emergency surgical procedures, and a significant amount of blood loss are the main predictors of an increased occurrence of eIOH.

•

Thyroidectomy has a relatively short duration and less amount of estimated blood loss when compared to major surgical procedures.

•

The occurrence of eIOH after general anesthesia for general surgery is a common problem.

•

Arterial hypotension in patients undergoing surgery under general anesthesia usually described by the very general term intraoperative hypotension.

Development of a random forest model for hypotension prediction after anesthesia induction for cardiac surgery

BACKGROUND

Hypotension after the induction of anesthesia is known to be associated with various adverse events. The involvement of a series of factors makes the prediction of hypotension during anesthesia quite challenging.

AIM

To explore the ability and effectiveness of a random forest (RF) model in the prediction of post-induction hypotension (PIH) in patients undergoing cardiac surgery.

METHODS

Patient information was obtained from the electronic health records of the Second Affiliated Hospital of Hainan Medical University. The study included patients, ≥ 18 years of age, who underwent cardiac surgery from December 2007 to January 2018. An RF algorithm, which is a supervised machine learning technique, was employed to predict PIH. Model performance was assessed by the area under the curve (AUC) of the receiver operating characteristic. Mean decrease in the Gini index was used to rank various features based on their importance.

RESULTS

Of the 3030 patients included in the study, 1578 (52.1%) experienced hypotension after the induction of anesthesia. The RF model performed effectively, with an AUC of 0.843 (0.808-0.877) and identified mean blood pressure as the most important predictor of PIH after anesthesia. Age and body mass index also had a significant impact.

CONCLUSION

The generated RF model had high discrimination ability for the identification of individuals at high risk for a hypotensive event during cardiac surgery. The study results highlighted that machine learning tools confer unique advantages for the prediction of adverse post-anesthesia events.

Artificial intelligence and machine learning-aided drug discovery in central nervous system diseases: State-of-the-arts and future directions

Neurological disorders significantly outnumber diseases in other therapeutic areas. However, developing drugs for central nervous system (CNS) disorders remains the most challenging area in drug discovery, accompanied with the long timelines and high attrition rates. With the rapid growth of biomedical data enabled by advanced experimental technologies, artificial intelligence (AI) and machine learning (ML) have emerged as an indispensable tool to draw meaningful insights and improve decision making in drug discovery. Thanks to the advancements in AI and ML algorithms, now the AI/ML-driven solutions have an unprecedented potential to accelerate the process of CNS drug discovery with better success rate. In this review, we comprehensively summarize AI/ML-powered pharmaceutical discovery efforts and their implementations in the CNS area. After introducing the AI/ML models as well as the conceptualization and data preparation, we outline the applications of AI/ML technologies to several key procedures in drug discovery, including target identification, compound screening, hit/lead generation and optimization, drug response and synergy prediction, de novo drug design, and drug repurposing. We review the current state-of-the-art of AI/ML-guided CNS drug discovery, focusing on blood-brain barrier permeability prediction and implementation into therapeutic discovery for neurological diseases. Finally, we discuss the major challenges and limitations of current approaches and possible future directions that may provide resolutions to these difficulties.

Systematic literature review of machine learning methods used in the analysis of real-world data for patient-provider decision making

BACKGROUND

Machine learning is a broad term encompassing a number of methods that allow the investigator to learn from the data. These methods may permit large real-world databases to be more rapidly translated to applications to inform patient-provider decision making.

METHODS

This systematic literature review was conducted to identify published observational research of employed machine learning to inform decision making at the patient-provider level. The search strategy was implemented and studies meeting eligibility criteria were evaluated by two independent reviewers. Relevant data related to study design, statistical methods and strengths and limitations were identified; study quality was assessed using a modified version of the Luo checklist.

RESULTS

A total of 34 publications from January 2014 to September 2020 were identified and evaluated for this review. There were diverse methods, statistical packages and approaches used across identified studies. The most common methods included decision tree and random forest approaches. Most studies applied internal validation but only two conducted external validation. Most studies utilized one algorithm, and only eight studies applied multiple machine learning algorithms to the data. Seven items on the Luo checklist failed to be met by more than 50% of published studies.

CONCLUSIONS

A wide variety of approaches, algorithms, statistical software, and validation strategies were employed in the application of machine learning methods to inform patient-provider decision making. There is a need to ensure that multiple machine learning approaches are used, the model selection strategy is clearly defined, and both internal and external validation are necessary to be sure that decisions for patient care are being made with the highest quality evidence. Future work should routinely employ ensemble methods incorporating multiple machine learning algorithms.

The role of artificial intelligence in surgical patient perioperative management

Perioperative medicine is a patient-centered, multidisciplinary and integrated clinical practice that starts from the moment of contemplation of surgery until full recovery. Every perioperative phase (preoperative, intraoperative and postoperative) must be studied and planned in order to optimize the entire patient management. Perioperative optimization does not only concern a short-term outcome improvement, but it has also a strong impact on long term survival. Clinical cases variability leads to the collection and analysis of a huge amount of different data, coming from multiple sources, making perioperative management standardization very difficult. Artificial Intelligence (AI) can play a primary role in this challenge, helping human mind in perioperative practice planning and decision-making process. AI refers to the ability of a computer system to perform functions and reasoning typical of the human mind; Machine Learning (ML) could play a fundamental role in presurgical planning, during intraoperative phase and postoperative management. Perioperative medicine is the cornerstone of surgical patient management and the tools deriving from the application of AI seem very promising as a support in optimizing the management of each individual patient. Despite the increasing help that will derive from the use of AI tools, the uniqueness of the patient and the particularity of each individual clinical case will always keep the role of the human mind central in clinical and perioperative management. The role of the physician, who must analyze the outputs provided by AI by following his own experience and knowledge, remains and will always be essential.

Comparative Analysis on Machine Learning and Deep Learning to Predict Post-Induction Hypotension

Hypotensive events in the initial stage of anesthesia can cause serious complications in the patients after surgery, which could be fatal. In this study, we intended to predict hypotension after tracheal intubation using machine learning and deep learning techniques after intubation one minute in advance. Meta learning models, such as random forest, extreme gradient boosting (Xgboost), and deep learning models, especially the convolutional neural network (CNN) model and the deep neural network (DNN), were trained to predict hypotension occurring between tracheal intubation and incision, using data from four minutes to one minute before tracheal intubation. Vital records and electronic health records (EHR) for 282 of 319 patients who underwent laparoscopic cholecystectomy from October 2018 to July 2019 were collected. Among the 282 patients, 151 developed post-induction hypotension. Our experiments had two scenarios: using raw vital records and feature engineering on vital records. The experiments on raw data showed that CNN had the best accuracy of 72.63%, followed by random forest (70.32%) and Xgboost (64.6%). The experiments on feature engineering showed that random forest combined with feature selection had the best accuracy of 74.89%, while CNN had a lower accuracy of 68.95% than that of the experiment on raw data. Our study is an extension of previous studies to detect hypotension before intubation with a one-minute advance. To improve accuracy, we built a model using state-of-art algorithms. We found that CNN had a good performance, but that random forest had a better performance when combined with feature selection. In addition, we found that the examination period (data period) is also important.