Development of a Probabilistic Boolean network (PBN) to model intraoperative blood pressure management.

BACKGROUND: Blood pressure is a vital sign for organ perfusion that anesthesiologists measure and modulate during surgery. However, current decision-making processes rely heavily on clinicians' experience, which can lead to variability in treatment across surgeries. With the advent of machine learning, we can now create models to predict the outcomes of interventions and guide perioperative decision-making. The first step in this process involves translating the clinical decision-making process into a framework understood by an algorithm. Probabilistic Boolean networks (PBNs) provide an information-rich approach to this problem. A PBN trends toward a steady state, and its decisions are easily understood via its Boolean predictor functions. We hypothesize that a PBN can be developed that corrects hemodynamic instability in patients by selecting clinical interventions to maintain blood pressure within a given range. METHODS: Data on patients over the age of 65 undergoing surgery with general anesthesia from 2018 to 2020 were drawn from the UF Health PRECEDE data set with IRB approval (IRB201700747). Parameters examined included heart rate, blood pressure, and frequency of medications given 15 min after anesthetic induction and 15 min before awakening. The medication frequency data were truncated into a 66/33 split for the training and validation set used in the PBN. The model was coded using Python 3 and evaluated by comparing the frequency of medications chosen by the program to the values in the testing set via linear regression analysis. RESULTS: The network developed successfully models a hemodynamically unstable patient and corrects the imbalance by administering medications. This is evidenced by the model achieving a stable, steady state matrix in all iterations. However, the model's ability to emulate clinical drug selection was variable. It was successful with its use of vasodilator selection but struggled with the appropriate selection of vasopressors. CONCLUSIONS: The PBN has demonstrated the ability to choose appropriate interventions based on a patient's current vitals. Additional work must be done to have the network emulate the frequency at which drugs are selected from in clinical practice. In its current state, the model provides an understanding of how a PBN behaves in the context of correcting hemodynamic instability and can aid in developing more robust models in the future.

A Network Analysis of Digital Clock Drawing for Command and Copy Conditions.

Graphomotor and time-based variables from the digital Clock Drawing Test (dCDT) characterize cognitive functions. However, no prior publications have quantified the strength of the associations between digital clock variables as they are produced. We hypothesized that analysis of the production of clock features and their interrelationships, as suggested, will differ between the command and copy test conditions. Older adults aged 65+ completed a digital clock drawing to command and copy conditions. Using a Bayesian hill-climbing algorithm and bootstrapping (10,000 samples), we derived directed acyclic graphs (DAGs) to examine network structure for command and copy dCDT variables. Although the command condition showed moderate associations between variables (µ|ßz|= 0.34) relative to the copy condition (µ|ßz| = 0.25), the copy condition network had more connections (18/18 versus 15/18 command). Network connectivity across command and copy was most influenced by five of the 18 variables. The direction of dependencies followed the order of instructions better in the command condition network. Digitally acquired clock variables relate to one another but differ in network structure when derived from command or copy conditions. Continued analyses of clock drawing production should improve understanding of quintessential normal features to aid in early neurodegenerative disease detection.

Antibody-based sex determination of human skeletal remains.

Assignment of biological sex to skeletal remains is critical in the accurate reconstruction of the past. Analysis of sex-chromosome encoded AMELX and AMELY peptides from the enamel protein amelogenin underpins a minimally destructive mass spectrometry (MS) method for sex determination of human remains. However, access to such specialist approaches limits applicability. As a convenient alternative, we generated antibodies that distinguish human AMELX and AMELY. Purified antibodies demonstrated high selectivity and quantitative detection against synthetic peptides by ELISA. Using acid etches of enamel from post-medieval skeletons, antibody determinations corrected osteological uncertainties and matched parallel MS, and for Bronze Age samples where only enamel was preserved, also matched MS analyses. Toward improved throughput, automated stations were applied to analyze 19th-century teeth where sex of individuals was documented, confirming MS can be bypassed. Our immunological tools should underpin development of routine, economical, high-throughput methods for sex determination, potentially even in a field setting.

Human IPSC-Derived PreBötC-Like Neurons and Development of an Opiate Overdose and Recovery Model.

Opioid overdose is the leading cause of drug overdose lethality, posing an urgent need for investigation. The key brain region for inspiratory rhythm regulation and opioid-induced respiratory depression (OIRD) is the preBötzinger Complex (preBötC) and current knowledge has mainly been obtained from animal systems. This study aims to establish a protocol to generate human preBötC neurons from induced pluripotent cells (iPSCs) and develop an opioid overdose and recovery model utilizing these iPSC-preBötC neurons. A de novo protocol to differentiate preBötC-like neurons from human iPSCs is established. These neurons express essential preBötC markers analyzed by immunocytochemistry and demonstrate expected electrophysiological responses to preBötC modulators analyzed by patch clamp electrophysiology. The correlation of the specific biomarkers and function analysis strongly suggests a preBötC-like phenotype. Moreover, the dose-dependent inhibition of these neurons' activity is demonstrated for four different opioids with identified IC50's comparable to the literature. Inhibition is rescued by naloxone in a concentration-dependent manner. This iPSC-preBötC mimic is crucial for investigating OIRD and combating the overdose crisis and a first step for the integration of a functional overdose model into microphysiological systems.

Increasing SARS-CoV-2 seroprevalence among UK pediatric patients on dialysis and kidney transplantation between January 2020 and August 2021.

BACKGROUND: Coronavirus disease 2019 (COVID-19) was officially declared a pandemic by the World Health Organisation (WHO) on 11 March 2020, as severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) spread rapidly across the world. We investigated the seroprevalence of anti-SARS-CoV-2 antibodies in pediatric patients on dialysis or kidney transplantation in the UK. METHODS: Excess sera samples were obtained prospectively during outpatient visits or haemodialysis sessions and analysed using a custom immunoassay calibrated with population age-matched healthy controls. Two large pediatric centres contributed samples. RESULTS: In total, 520 sera from 145 patients (16 peritoneal dialysis, 16 haemodialysis, 113 transplantation) were analysed cross-sectionally from January 2020 until August 2021. No anti-SARS-CoV-2 antibody positive samples were detected in 2020 when lockdown and enhanced social distancing measures were enacted. Thereafter, the proportion of positive samples increased from 5% (January 2021) to 32% (August 2021) following the emergence of the Alpha variant. Taking all patients, 32/145 (22%) were seropositive, including 8/32 (25%) with prior laboratory-confirmed SARS-CoV-2 infection and 12/32 (38%) post-vaccination (one of whom was also infected after vaccination). The remaining 13 (41%) seropositive patients had no known stimulus, representing subclinical cases. Antibody binding signals were comparable across patient ages and dialysis versus transplantation and highest against full-length spike protein versus spike subunit-1 and nucleocapsid protein. CONCLUSIONS: Anti-SARS-CoV-2 seroprevalence was low in 2020 and increased in early 2021. Serological surveillance complements nucleic acid detection and antigen testing to build a greater picture of the epidemiology of COVID-19 and is therefore important to guide public health responses. A higher resolution version of the Graphical abstract is available as Supplementary information.

Developing and validating a natural language processing algorithm to extract preoperative cannabis use status documentation from unstructured narrative clinical notes.

OBJECTIVE: This study aimed to develop a natural language processing algorithm (NLP) using machine learning (ML) techniques to identify and classify documentation of preoperative cannabis use status. MATERIALS AND METHODS: We developed and applied a keyword search strategy to identify documentation of preoperative cannabis use status in clinical documentation within 60 days of surgery. We manually reviewed matching notes to classify each documentation into 8 different categories based on context, time, and certainty of cannabis use documentation. We applied 2 conventional ML and 3 deep learning models against manual annotation. We externally validated our model using the MIMIC-III dataset. RESULTS: The tested classifiers achieved classification results close to human performance with up to 93% and 94% precision and 95% recall of preoperative cannabis use status documentation. External validation showed consistent results with up to 94% precision and recall. DISCUSSION: Our NLP model successfully replicated human annotation of preoperative cannabis use documentation, providing a baseline framework for identifying and classifying documentation of cannabis use. We add to NLP methods applied in healthcare for clinical concept extraction and classification, mainly concerning social determinants of health and substance use. Our systematically developed lexicon provides a comprehensive knowledge-based resource covering a wide range of cannabis-related concepts for future NLP applications. CONCLUSION: We demonstrated that documentation of preoperative cannabis use status could be accurately identified using an NLP algorithm. This approach can be employed to identify comparison groups based on cannabis exposure for growing research efforts aiming to guide cannabis-related clinical practices and policies.

Explainable semi-supervised deep learning shows that dementia is associated with small, avocado-shaped clocks with irregularly placed hands.

The clock drawing test is a simple and inexpensive method to screen for cognitive frailties, including dementia. In this study, we used the relevance factor variational autoencoder (RF-VAE), a deep generative neural network, to represent digitized clock drawings from multiple institutions using an optimal number of disentangled latent factors. The model identified unique constructional features of clock drawings in a completely unsupervised manner. These factors were examined by domain experts to be novel and not extensively examined in prior research. The features were informative, as they distinguished dementia from non-dementia patients with an area under receiver operating characteristic (AUC) of 0.86 singly, and 0.96 when combined with participants' demographics. The correlation network of the features depicted the "typical dementia clock" as having a small size, a non-circular or "avocado-like" shape, and incorrectly placed hands. In summary, we report a RF-VAE network whose latent space encoded novel constructional features of clocks that classify dementia from non-dementia patients with high performance.

Applications of Artificial Intelligence in the Radiology Roundtrip: Process Streamlining, Workflow Optimization, and Beyond.

There are many impactful applications of artificial intelligence (AI) in the electronic radiology roundtrip and the patient's journey through the healthcare system that go beyond diagnostic applications. These tools have the potential to improve quality and safety, optimize workflow, increase efficiency, and increase patient satisfaction. In this article, we review the role of AI for process improvement and workflow enhancement which includes applications beginning from the time of order entry, scan acquisition, applications supporting the image interpretation task, and applications supporting tasks after image interpretation such as result communication. These non-diagnostic workflow and process optimization tasks are an important part of the arsenal of potential AI tools that can streamline day to day clinical practice and patient care.

Overtriage, Undertriage, and Value of Care after Major Surgery: An Automated, Explainable Deep Learning-Enabled Classification System.

BACKGROUND: In single-institution studies, overtriaging low-risk postoperative patients to ICUs has been associated with a low value of care; undertriaging high-risk postoperative patients to general wards has been associated with increased mortality and morbidity. This study tested the reproducibility of an automated postoperative triage classification system to generating an actionable, explainable decision support system. STUDY DESIGN: This longitudinal cohort study included adults undergoing inpatient surgery at two university hospitals. Triage classifications were generated by an explainable deep learning model using preoperative and intraoperative electronic health record features. Nearest neighbor algorithms identified risk-matched controls. Primary outcomes were mortality, morbidity, and value of care (inverted risk-adjusted mortality/total direct costs). RESULTS: Among 4,669 ICU admissions, 237 (5.1%) were overtriaged. Compared with 1,021 control ward admissions, overtriaged admissions had similar outcomes but higher costs ($15.9K [interquartile range $9.8K to $22.3K] vs $10.7K [$7.0K to $17.6K], p < 0.001) and lower value of care (0.2 [0.1 to 0.3] vs 1.5 [0.9 to 2.2], p < 0.001). Among 8,594 ward admissions, 1,029 (12.0%) were undertriaged. Compared with 2,498 control ICU admissions, undertriaged admissions had longer hospital length-of-stays (6.4 [3.4 to 12.4] vs 5.4 [2.6 to 10.4] days, p < 0.001); greater incidence of hospital mortality (1.7% vs 0.7%, p = 0.03), cardiac arrest (1.4% vs 0.5%, p = 0.04), and persistent acute kidney injury without renal recovery (5.2% vs 2.8%, p = 0.002); similar costs ($21.8K [$13.3K to $34.9K] vs $21.9K [$13.1K to $36.3K]); and lower value of care (0.8 [0.5 to 1.3] vs 1.2 [0.7 to 2.0], p < 0.001). CONCLUSIONS: Overtriage was associated with low value of care; undertriage was associated with both low value of care and increased mortality and morbidity. The proposed framework for generating automated postoperative triage classifications is reproducible.

Predictive Modeling for Readmission to Intensive Care: A Systematic Review.

To evaluate the methodologic rigor and predictive performance of models predicting ICU readmission; to understand the characteristics of ideal prediction models; and to elucidate relationships between appropriate triage decisions and patient outcomes. DATA SOURCES: PubMed, Web of Science, Cochrane, and Embase. STUDY SELECTION: Primary literature that reported the development or validation of ICU readmission prediction models within from 2010 to 2021. DATA EXTRACTION: Relevant study information was extracted independently by two authors using the Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies checklist. Bias was evaluated using the Prediction model Risk Of Bias ASsessment Tool. Data sources, modeling methodology, definition of outcomes, performance, and risk of bias were critically evaluated to elucidate relevant relationships. DATA SYNTHESIS: Thirty-three articles describing models were included. Six studies had a high overall risk of bias due to improper inclusion criteria or omission of critical analysis details. Four other studies had an unclear overall risk of bias due to lack of detail describing the analysis. Overall, the most common (50% of studies) source of bias was the filtering of candidate predictors via univariate analysis. The poorest performing models used existing clinical risk or acuity scores such as Acute Physiologic Assessment and Chronic Health Evaluation II, Sequential Organ Failure Assessment, or Stability and Workload Index for Transfer as the sole predictor. The higher-performing ICU readmission prediction models used homogenous patient populations, specifically defined outcomes, and routinely collected predictors that were analyzed over time. CONCLUSIONS: Models predicting ICU readmission can achieve performance advantages by using longitudinal time series modeling, homogenous patient populations, and predictor variables tailored to those populations.

Building an automated, machine learning-enabled platform for predicting post-operative complications.

Objective. In 2019, the University of Florida College of Medicine launched theMySurgeryRiskalgorithm to predict eight major post-operative complications using automatically extracted data from the electronic health record.Approach. This project was developed in parallel with our Intelligent Critical Care Center and represents a culmination of efforts to build an efficient and accurate model for data processing and predictive analytics.Main Results and Significance. This paper discusses how our model was constructed and improved upon. We highlight the consolidation of the database, processing of fixed and time-series physiologic measurements, development and training of predictive models, and expansion of those models into different aspects of patient assessment and treatment. We end by discussing future directions of the model.

Early reduction in postoperative pain is associated with improved long-term function after shoulder arthroplasty: a retrospective case series.

PURPOSE: Mixed modalities are frequently utilized in total shoulder arthroplasty (TSA) to control pain, improve patient satisfaction, reduce narcotics use and facilitate earlier discharge. We investigate the relationship between early postoperative pain control and long-term functional outcomes after shoulder arthroplasty. METHODS: A retrospective review identified 294 patients (314 shoulders) who underwent anatomic or reverse TSA and received a continuous cervical paravertebral nerve block perioperatively. Opioid and non-opioid analgesics were also available to the patients in an "as needed" capacity to augment perioperative pain control. In addition to demographic and surgical characteristics, the impact on functional outcomes of relative pain (i.e., a patient's subjective pain relative to the entire cohort), pain gradient (i.e., the slope of a patient's subjective pain), and opioid consumption during the first 24 h postoperatively were assessed. Shoulder function was assessed using validated outcome measures collected at 2 year follow-up. Outcomes were measured using American Shoulder and Elbow Surgeons questionnaire (ASES), Shoulder Pain and Disability Index (SPADI), SPADI-130, Raw and Normalized Constant Score, SST-12 and UCLA score. RESULTS: Patients younger than 65, females, reverse TSA, revisions, and preoperative opioid users had worse functional outcomes. On univariate analysis, increased pain perioperatively (> 50% percentile relative pain) was associated with decreased function at 2 years when analyzed with all seven outcome scores (P < .001 for all), reaching minimal clinically important difference (MCID) using the Constant Score. On multivariate analysis, increased pain in the first 24 h postoperatively (assessed on a continuous scale) was independently associated with worse ASES, SPADI, and SPADI-130 scores. Intraoperative ketamine administration and opioid consumption in the 24 h postoperative period did not influence long-term shoulder function. CONCLUSION: Patients reporting reduced pain after TSA demonstrated improved shoulder function with the Constant score at 2 years postoperatively in both univariate and multivariate analysis. Larger-scale investigation may be warranted to see if this is true for other functional outcome measures. LEVEL OF EVIDENCE: III, treatment study.

Postoperative Overtriage to an Intensive Care Unit Is Associated With Low Value of Care.

OBJECTIVE: We test the hypothesis that for low-acuity surgical patients, postoperative intensive care unit (ICU) admission is associated with lower value of care compared with ward admission. BACKGROUND: Overtriaging low-acuity patients to ICU consumes valuable resources and may not confer better patient outcomes. Associations among postoperative overtriage, patient outcomes, costs, and value of care have not been previously reported. METHODS: In this longitudinal cohort study, postoperative ICU admissions were classified as overtriaged or appropriately triaged according to machine learning-based patient acuity assessments and requirements for immediate postoperative mechanical ventilation or vasopressor support. The nearest neighbors algorithm identified risk-matched control ward admissions. The primary outcome was value of care, calculated as inverse observed-to-expected mortality ratios divided by total costs. RESULTS: Acuity assessments had an area under the receiver operating characteristic curve of 0.92 in generating predictions for triage classifications. Of 8592 postoperative ICU admissions, 423 (4.9%) were overtriaged. These were matched with 2155 control ward admissions with similar comorbidities, incidence of emergent surgery, immediate postoperative vital signs, and do not resuscitate order placement and rescindment patterns. Compared with controls, overtraiged admissions did not have a lower incidence of any measured complications. Total costs for admission were $16.4K for overtriage and $15.9K for controls ( P =0.03). Value of care was lower for overtriaged admissions [2.9 (2.0-4.0)] compared with controls [24.2 (14.1-34.5), P <0.001]. CONCLUSIONS: Low-acuity postoperative patients who were overtriaged to ICUs had increased total costs, no improvements in outcomes, and received low-value care.

Cysteine-Selective Modification of Peptides and Proteins via Desulfurative C-C Bond Formation.

The site-selective modification of peptides and proteins facilitates the preparation of targeted therapeutic agents and tools to interrogate biochemical pathways. Among the numerous bioconjugation techniques developed to install groups of interest, those that generate C(sp3 )-C(sp3 ) bonds are significantly underrepresented despite affording proteolytically stable, biogenic linkages. Herein, a visible-light-mediated reaction is described that enables the site-selective modification of peptides and proteins via desulfurative C(sp3 )-C(sp3 ) bond formation. The reaction is rapid and high yielding in peptide systems, with comparable translation to proteins. Using this chemistry, a range of moieties is installed into model systems and an effective PTM-mimic is successfully integrated into a recombinantly expressed histone.

Humoral and cellular immunity in patients with rare autoimmune rheumatic diseases following SARS-CoV-2 vaccination.

OBJECTIVES: Coronavirus 2019 vaccine responses in rare autoimmune rheumatic diseases (RAIRDs) remain poorly understood; in particular there is little known about whether people develop effective T cell responses. We conducted an observational study to evaluate the short-term humoral and cell-mediated T cell response after the second severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) vaccination in RAIRD patients compared with healthy controls (HCs). METHODS: Blood samples were collected after the second dose and anti-spike, anti-nucleocapsid antibody levels and SARS-CoV-2-specific T cell responses were measured and compared with those of HCs. Activation-induced marker and deep phenotyping assays were used to identify differences in T cells between high and no/low antibody groups, followed by multidimensional clustering. RESULTS: A total of 50 patients with RAIRDs were included (31 with AAV, 4 with other systemic vasculitis, 9 with SLE and 6 with myositis). The median anti-spike levels were significantly lower in RAIRD patients compared with HCs (P < 0.0001). Fifteen (33%) patients had undetectable levels and 26 (57%) had levels lower than the lowest HC. Rituximab in the last 12 months (P = 0.003) was associated with reduced immunogenicity compared with a longer pre-vaccination period. There was a significant difference in B cell percentages (P = 0.03) and spike-specific CD4+ T cells (P = 0.02) between no/low antibody vs high antibody groups. Patients in the no/low antibody group had a higher percentage of terminally differentiated (exhausted) T cells. CONCLUSIONS: Following two doses, most RAIRD patients have lower antibody levels than the lowest HC and lower anti-spike T cells. RAIRD patients with no/low antibodies have diminished numbers and poor quality of memory T cells that lack proliferative and functional capacities.

Antibody response to four doses of SARS-CoV-2 vaccine in rare autoimmune rheumatic diseases: an observational study.

Objective: Antibody responses to coronavirus disease 2019 (COVID-19) vaccines are reduced among immunocompromised patients but are not well quantified among people with rare disease. We conducted an observational study to evaluate the antibody responses to the booster SARS-CoV-2 vaccine in people with rare autoimmune rheumatic diseases (RAIRD). Methods: Blood samples were collected after second, before third, after third and after fourth vaccine doses. Anti-spike and anti-nucleocapsid antibody levels were measured using an in-house ELISA. Logistic regression models were built to determine the predictors for non-response. Results were compared with age- and sex-matched healthy controls. Results: Forty-three people with RAIRD were included, with a median age of 56 years. Anti-spike seropositivity increased from 42.9% after second dose to 51.2% after third dose and 65.6% after fourth dose. Median anti-spike antibody levels increased from 33.6 (interquartile range 7.8-724.5) binding antibody units after second dose to 239.4 (interquartile range 35.8-1051.1) binding antibody units after the booster dose (third dose, or fourth dose if eligible). Of the participants who had sufficient antibody levels post-second dose, 22.2% had insufficient levels after the booster, and 34.9% of participants had lower antibodies after the booster than the lowest healthy control had after the second dose. Rituximab in the 6 months prior to booster (P = 0.02) and non-White ethnicity (P = 0.04) were associated with non-response. There was a dose-response relationship between the timing of rituximab and generation of sufficient antibodies (P = 0.03). Conclusion: Although the booster dose increased anti-spike IgG and seropositivity rates, some people with RAIRD, particularly those on rituximab, had insufficient antibody levels despite three or four doses.

Diurnal Pain Classification in Critically Ill Patients using Machine Learning on Accelerometry and Analgesic Data.

Quantifying pain in patients admitted to intensive care units (ICUs) is challenging due to the increased prevalence of communication barriers in this patient population. Previous research has posited a positive correlation between pain and physical activity in critically ill patients. In this study, we advance this hypothesis by building machine learning classifiers to examine the ability of accelerometer data collected from daily wearables to predict self-reported pain levels experienced by patients in the ICU. We trained multiple Machine Learning (ML) models, including Logistic Regression, CatBoost, and XG-Boost, on statistical features extracted from the accelerometer data combined with previous pain measurements and patient demographics. Following previous studies that showed a change in pain sensitivity in ICU patients at night, we performed the task of pain classification separately for daytime and nighttime pain reports. In the pain versus no-pain classification setting, logistic regression gave the best classifier in daytime (AUC: 0.72, F1-score: 0.72), and CatBoost gave the best classifier at nighttime (AUC: 0.82, F1-score: 0.82). Performance of logistic regression dropped to 0.61 AUC, 0.62 F1-score (mild vs. moderate pain, nighttime), and CatBoost's performance was similarly affected with 0.61 AUC, 0.60 F1-score (moderate vs. severe pain, daytime). The inclusion of analgesic information benefited the classification between moderate and severe pain. SHAP analysis was conducted to find the most significant features in each setting. It assigned the highest importance to accelerometer-related features on all evaluated settings but also showed the contribution of the other features such as age and medications in specific contexts. In conclusion, accelerometer data combined with patient demographics and previous pain measurements can be used to screen painful from painless episodes in the ICU and can be combined with analgesic information to provide moderate classification between painful episodes of different severities.

Ideal algorithms in healthcare: Explainable, dynamic, precise, autonomous, fair, and reproducible.

Established guidelines describe minimum requirements for reporting algorithms in healthcare; it is equally important to objectify the characteristics of ideal algorithms that confer maximum potential benefits to patients, clinicians, and investigators. We propose a framework for ideal algorithms, including 6 desiderata: explainable (convey the relative importance of features in determining outputs), dynamic (capture temporal changes in physiologic signals and clinical events), precise (use high-resolution, multimodal data and aptly complex architecture), autonomous (learn with minimal supervision and execute without human input), fair (evaluate and mitigate implicit bias and social inequity), and reproducible (validated externally and prospectively and shared with academic communities). We present an ideal algorithms checklist and apply it to highly cited algorithms. Strategies and tools such as the predictive, descriptive, relevant (PDR) framework, the Standard Protocol Items: Recommendations for Interventional Trials-Artificial Intelligence (SPIRIT-AI) extension, sparse regression methods, and minimizing concept drift can help healthcare algorithms achieve these objectives, toward ideal algorithms in healthcare.

Multi-dimensional patient acuity estimation with longitudinal EHR tokenization and flexible transformer networks.

Transformer model architectures have revolutionized the natural language processing (NLP) domain and continue to produce state-of-the-art results in text-based applications. Prior to the emergence of transformers, traditional NLP models such as recurrent and convolutional neural networks demonstrated promising utility for patient-level predictions and health forecasting from longitudinal datasets. However, to our knowledge only few studies have explored transformers for predicting clinical outcomes from electronic health record (EHR) data, and in our estimation, none have adequately derived a health-specific tokenization scheme to fully capture the heterogeneity of EHR systems. In this study, we propose a dynamic method for tokenizing both discrete and continuous patient data, and present a transformer-based classifier utilizing a joint embedding space for integrating disparate temporal patient measurements. We demonstrate the feasibility of our clinical AI framework through multi-task ICU patient acuity estimation, where we simultaneously predict six mortality and readmission outcomes. Our longitudinal EHR tokenization and transformer modeling approaches resulted in more accurate predictions compared with baseline machine learning models, which suggest opportunities for future multimodal data integrations and algorithmic support tools using clinical transformer networks.

Long-Term Postoperative Pain Prediction Using Higher-Order Singular Value Decomposition of Intraoperative Physiological Responses: Prospective Cohort Study.

BACKGROUND: Long-term postoperative pain (POP) and patient responses to pain relief medications are not yet fully understood. Although recent studies have developed an index for the nociception level of patients under general anesthesia based on multiple physiological parameters, it remains unclear whether these parameters correlate with long-term POP outcomes. OBJECTIVE: This study aims to extract unbiased and interpretable descriptions of how the dynamics of physiological parameters change over time and across patients in response to surgical procedures and intraoperative medications using a multivariate-temporal analysis. We demonstrated that there is an association (correlation) between the main features of intraoperative physiological responses and long-term POP, which has a predictive value, even without claiming causality. METHODS: We proposed a complex higher-order singular value decomposition method to accurately decompose patients' physiological responses into multivariate structures evolving over time. We used intraoperative vital signs of 175 patients from a mixed surgical cohort to extract three interconnected, low-dimensional, complex-valued descriptions of patients' physiological responses: multivariate factors, reflecting subphysiological parameters; temporal factors, reflecting common intrasurgery temporal dynamics; and patients' factors, describing interpatient changes in physiological responses. RESULTS: Adoption of the complex higher-order singular value decomposition method allowed us to clarify the dynamic correlation structure included in the intraoperative physiological responses. Instantaneous phases of the complex-valued physiological responses of 242 patients within the subspace of principal descriptors enabled us to discriminate between mild and not-mild (moderate-severe) levels of pain at postoperative days 30 and 90. Following rotation of physiological responses before projection to align with the common multivariate-temporal dynamic, the method achieved an area under curve for postoperative day 30 and 90 outcomes of 0.81 and 0.89 for thoracic surgery, 0.87 and 0.83 for orthopedic surgery, 0.87 and 0.88 for urological surgery, 0.86 and 1 for colorectal surgery, 1 and 1 for transplant surgery, and 0.83 and 0.92 for pancreatic surgery, respectively. CONCLUSIONS: By categorizing patients into different surgical groups, we identified significant surgery-related principal descriptors. Each of them potentially encodes different surgical stimulation. The dynamics of patients' physiological responses to these surgical events were linked to long-term POP development.