Development and external validation of temporal fusion transformer models for continuous intraoperative blood pressure forecasting.

Background: During surgery, intraoperative hypotension is associated with postoperative morbidity and should therefore be avoided. Predicting the occurrence of hypotension in advance may allow timely interventions to prevent hypotension. Previous prediction models mostly use high-resolution waveform data, which is often not available. Methods: We utilised a novel temporal fusion transformer (TFT) algorithm to predict intraoperative blood pressure trajectories 7 min in advance. We trained the model with low-resolution data (sampled every 15 s) from 73,009 patients who were undergoing general anaesthesia for non-cardiothoracic surgery between January 1, 2017, and December 30, 2020, at the General Hospital of Vienna, Austria. The data set contained information on patient demographics, vital signs, medication, and ventilation. The model was evaluated using an internal (n = 8113) and external test set (n = 5065) obtained from the openly accessible Vital Signs Database. Findings: In the internal test set, the mean absolute error for predicting mean arterial blood pressure was 0.376 standard deviations-or 4 mmHg-and 0.622 standard deviations-or 7 mmHg-in the external test set. We also adapted the TFT model to binarily predict the occurrence of hypotension as defined by mean arterial blood pressure < 65 mmHg in the next one, three, five, and 7 min. Here, model discrimination was excellent, with a mean area under the receiver operating characteristic curve (AUROC) of 0.933 in the internal test set and 0.919 in the external test set. Interpretation: Our TFT model is capable of accurately forecasting intraoperative arterial blood pressure using only low-resolution data showing a low prediction error. When used for binary prediction of hypotension, we obtained excellent performance. Funding: No external funding.

A retrospective analysis of the need for on-site emergency physician presence and mission characteristics of a rural ground-based emergency medical service.

BACKGROUND: This study aimed to address the challenges faced by rural emergency medical services in Europe, due to an increasing number of missions and limited human resources. The primary objective was to determine the necessity of having an on-site emergency physician (EP), while the secondary objectives included analyzing the characteristics of rural EP missions. METHODS: A retrospective study was conducted, examining rural EP missions carried out between January 1st, 2017, and December 2nd, 2021 in Burgenland, Austria. The need for physical presence of an EP was classified based on the National Advisory Committee for Aeronautics (NACA) score into three categories; category A: no need for an EP (NACA 1-3); category B: need for an EP (NACA 1-3 along with additional medical interventions beyond the capabilities of emergency medical technicians); and category C: definite need for an EP (NACA 4-7). Descriptive statistics were used for analysis. RESULTS: Out of 16,971 recorded missions, 15,591 were included in the study. Approximately 32.3% of missions fell into category A, indicating that an EP's physical presence was unnecessary. The diagnoses made by telecommunicators matched those of the EPs in only 52.8% of cases. CONCLUSION: The study suggests that about a third of EP missions carried out in rural areas might not have a solid medical rationale. This underscores the importance of developing an alternative care approach for these missions. Failing to address this could put additional pressure on already stretched EMS systems, risking their collapse.

A Comparison of Five Algorithmic Methods and Machine Learning Pattern Recognition for Artifact Detection in Electronic Records of Five Different Vital Signs: A Retrospective Analysis.

BACKGROUND: Research on electronic health record physiologic data is common, invariably including artifacts. Traditionally, these artifacts have been handled using simple filter techniques. The authors hypothesized that different artifact detection algorithms, including machine learning, may be necessary to provide optimal performance for various vital signs and clinical contexts. METHODS: In a retrospective single-center study, intraoperative operating room and intensive care unit (ICU) electronic health record datasets including heart rate, oxygen saturation, blood pressure, temperature, and capnometry were included. All records were screened for artifacts by at least two human experts. Classical artifact detection methods (cutoff, multiples of SD [z-value], interquartile range, and local outlier factor) and a supervised learning model implementing long short-term memory neural networks were tested for each vital sign against the human expert reference dataset. For each artifact detection algorithm, sensitivity and specificity were calculated. RESULTS: A total of 106 (53 operating room and 53 ICU) patients were randomly selected, resulting in 392,808 data points. Human experts annotated 5,167 (1.3%) data points as artifacts. The artifact detection algorithms demonstrated large variations in performance. The specificity was above 90% for all detection methods and all vital signs. The neural network showed significantly higher sensitivities than the classic methods for heart rate (ICU, 33.6%; 95% CI, 33.1 to 44.6), systolic invasive blood pressure (in both the operating room [62.2%; 95% CI, 57.5 to 71.9] and the ICU [60.7%; 95% CI, 57.3 to 71.8]), and temperature in the operating room (76.1%; 95% CI, 63.6 to 89.7). The CI for specificity overlapped for all methods. Generally, sensitivity was low, with only the z-value for oxygen saturation in the operating room reaching 88.9%. All other sensitivities were less than 80%. CONCLUSIONS: No single artifact detection method consistently performed well across different vital signs and clinical settings. Neural networks may be a promising artifact detection method for specific vital signs.

Predicting Intraoperative Hypothermia Burden during Non-Cardiac Surgery: A Retrospective Study Comparing Regression to Six Machine Learning Algorithms.

BACKGROUND: Inadvertent intraoperative hypothermia is a common complication that affects patient comfort and morbidity. As the development of hypothermia is a complex phenomenon, predicting it using machine learning (ML) algorithms may be superior to logistic regression. METHODS: We performed a single-center retrospective study and assembled a feature set comprised of 71 variables. The primary outcome was hypothermia burden, defined as the area under the intraoperative temperature curve below 37 °C over time. We built seven prediction models (logistic regression, extreme gradient boosting (XGBoost), random forest (RF), multi-layer perceptron neural network (MLP), linear discriminant analysis (LDA), k-nearest neighbor (KNN), and Gaussian naïve Bayes (GNB)) to predict whether patients would not develop hypothermia or would develop mild, moderate, or severe hypothermia. For each model, we assessed discrimination (F1 score, area under the receiver operating curve, precision, recall) and calibration (calibration-in-the-large, calibration intercept, calibration slope). RESULTS: We included data from 87,116 anesthesia cases. Predicting the hypothermia burden group using logistic regression yielded a weighted F1 score of 0.397. Ranked from highest to lowest weighted F1 score, the ML algorithms performed as follows: XGBoost (0.44), RF (0.418), LDA (0.406), LDA (0.4), KNN (0.362), and GNB (0.32). CONCLUSIONS: ML is suitable for predicting intraoperative hypothermia and could be applied in clinical practice.

Development of a Reinforcement Learning Algorithm to Optimize Corticosteroid Therapy in Critically Ill Patients with Sepsis.

BACKGROUND: The optimal indication, dose, and timing of corticosteroids in sepsis is controversial. Here, we used reinforcement learning to derive the optimal steroid policy in septic patients based on data on 3051 ICU admissions from the AmsterdamUMCdb intensive care database. METHODS: We identified septic patients according to the 2016 consensus definition. An actor-critic RL algorithm using ICU mortality as a reward signal was developed to determine the optimal treatment policy from time-series data on 277 clinical parameters. We performed off-policy evaluation and testing in independent subsets to assess the algorithm's performance. RESULTS: Agreement between the RL agent's policy and the actual documented treatment reached 59%. Our RL agent's treatment policy was more restrictive compared to the actual clinician behavior: our algorithm suggested withholding corticosteroids in 62% of the patient states, versus 52% according to the physicians' policy. The 95% lower bound of the expected reward was higher for the RL agent than clinicians' historical decisions. ICU mortality after concordant action in the testing dataset was lower both when corticosteroids had been withheld and when corticosteroids had been prescribed by the virtual agent. The most relevant variables were vital parameters and laboratory values, such as blood pressure, heart rate, leucocyte count, and glycemia. CONCLUSIONS: Individualized use of corticosteroids in sepsis may result in a mortality benefit, but optimal treatment policy may be more restrictive than the routine clinical practice. Whilst external validation is needed, our study motivates a 'precision-medicine' approach to future prospective controlled trials and practice.

"Loved ones are not 'visitors' in a patient's life"-The importance of including loved ones in the patient's hospital stay: An international Twitter study of #HospitalsTalkToLovedOnes in times of COVID-19.

Background: Hospitals are institutions whose primary task is to treat patients. Family-centered care, which considers loved ones as equal partners in patient care, has been gaining recognition in the adult care setting. Our aim was to record experiences of and opinions on communication between hospital-based healthcare providers and patients' loved ones, related but not limited to the rigorous mitigation measures implemented during the COVID-19 pandemic. Methods: The Twitter profile @HospitalsTalkTo and hashtag #HospitalsTalkToLovedOnes were created to interact with the Twitter public between 7 June 2021 and 7 February 2022. Conversations surrounding #HospitalsTalkToLovedOnes were extracted and subjected to natural language processing analysis using term frequency and Markov chain analysis. Qualitative thematic analysis was performed on the 10% most interacted tweets and of tweets mentioning "COVID" from a personal experience-based subset. Results: We collected 4412 unique tweets made or interacted by 7040 Twitter users from 142 different countries. The most frequent words were patient, hospital, care, family, loved and communication. Thematic analysis revealed the importance of communication between patients, patients' loved ones and hospitals; showed that patients and their loved ones need support during a patient's hospital journey; and that pediatric care should be the gold standard for adult care. Visitation restrictions due to COVID-19 are just one barrier to communication, others are a lack of phone signal, no space or time for asking questions, and a complex medical system. We formulate 3 recommendations to improve the inclusion of loved ones into the patient's hospital stay. Conclusions: "Loved ones are not 'visitors' in a patient's life". Irrespective of COVID-19, patient's loved ones need to be included during the patient's hospital journey. Transparent communication and patient empowerment increase patient safety and improve the hospital experience for both the patients and their loved ones. Our findings underline the need for the concept of family-centered care to finally be implemented in adult nursing clinical practice.

Neutron Radiography and Tomography of the Drying Process of Screed Samples.

The moisture content of screed samples is an essential parameter in the construction industry, since the screed must dry to a certain level of moisture content to be ready for covering. This paper introduces neutron radiography (NR) and neutron tomography (NT) as new, non-destructive techniques for analysing the drying characteristics of screed. Our NR analyses evaluate the results of the established methods while offering much higher spatial resolution of 200 µm, thereby facilitating a two- and three-dimensional understanding of screed's drying behaviour. Because of NR's exceptionally high sensitivity regarding the total cross section of hydrogen the precise moisture content of screed samples is obtainable, resulting in new observations. The current methods to measure moisture content comprise the 'calcium carbide method', the 'Darr method', and electrical sensor systems.