The introduction of Large Language Models (LLMs) has advanced data representation and analysis, bringing significant progress in their use for medical questions and answering. Despite these advancements, integrating tabular data, especially numerical data pivotal in clinical contexts, into LLM paradigms has not been thoroughly explored. In this study, we examine the effectiveness of vector representations from last hidden states of LLMs for medical diagnostics and prognostics using electronic health record (EHR) data. We compare the performance of these embeddings with that of raw numerical EHR data when used as feature inputs to traditional machine learning (ML) algorithms that excel at tabular data learning, such as eXtreme Gradient Boosting. We focus on instruction-tuned LLMs in a zero-shot setting to represent abnormal physiological data and evaluating their utilities as feature extractors to enhance ML classifiers for predicting diagnoses, length of stay, and mortality. Furthermore, we examine prompt engineering techniques on zero-shot and few-shot LLM embeddings to measure their impact comprehensively. Although findings suggest the raw data features still prevails in medical ML tasks, zero-shot LLM embeddings demonstrate competitive results, suggesting a promising avenue for future research in medical applications.

The estimation and monitoring of SpO2 are crucial for assessing lung function and treating chronic pulmonary diseases. The COVID-19 pandemic has highlighted the importance of early detection of changes in SpO2, particularly in asymptomatic patients with clinical deterioration. However, conventional SpO2 measurement methods rely on contact-based sensing, presenting the risk of cross-contamination and complications in patients with impaired limb perfusion. Additionally, pulse oximeters may not be available in marginalized communities and undeveloped countries. To address these limitations and provide a more comfortable and unobtrusive way to monitor SpO2, recent studies have investigated SpO2 measurement using videos. However, measuring SpO2 using cameras in a contactless way, particularly from smartphones, is challenging due to weaker physiological signals and lower optical selectivity of smartphone camera sensors. The system includes three main steps: 1) extraction of the region of interest (ROI), which includes the palm and back of the hand, from the smartphone-captured videos; 2) spatial averaging of the ROI to produce R, G, and B time series; and 3) feeding the time series into an optophysiology-inspired CNN for SpO2 estimation. Our proposed method can provide a more efficient and accurate way to monitor SpO2 using videos captured from consumer-grade smartphones, which can be especially useful in telehealth and health screening settings.

From the NEJM Catalyst event AI and Machine Learning for Health Care Delivery, sponsored by Advisory Board, March 24, 2022. In the special artificial intelligence theme issue of NEJM Catalyst Innovations in Care Delivery, "Using AI to Empower Collaborative Team Workflows: Two Implementations for Advance Care Planning and Care Escalation" compares AI implementations for improving the rate of advanced care planning and earlier prediction of clinical deterioration. Speaking at the NEJM Catalyst "AI and Machine Learning for Health Care Delivery" event, first author Ron C. Li, MD, describes the care escalation intervention and key takeaways from the case study. "Our work starts with a foundational premise: that we need to change how we think about AI in health care," says Li. Instead of starting with a machine learning model and then deciding how to deploy it, Li says that health care should start with a problem and think about AI not as the solution, but as a capability that enables a broader set of solutions. AI will not replace humans in health care, but empower them.

PURPOSE OF REVIEW: To provide an overview of the systems being used to identify and predict clinical deterioration in hospitalised patients, with focus on the current and future role of artificial intelligence (AI). RECENT FINDINGS: There are five leading AI driven systems in this field: the Advanced Alert Monitor (AAM), the electronic Cardiac Arrest Risk Triage (eCART) score, Hospital wide Alert Via Electronic Noticeboard, the Mayo Clinic Early Warning Score, and the Rothman Index (RI). Each uses Electronic Patient Record (EPR) data and machine learning to predict adverse events. Less mature but relevant evolutions are occurring in the fields of Natural Language Processing, Time and Motion Studies, AI Sepsis and COVID-19 algorithms. SUMMARY: Research-based AI-driven systems to predict clinical deterioration are increasingly being developed, but few are being implemented into clinical workflows.

Early recognition of clinical deterioration is one of the main steps for reducing inpatient morbidity and mortality. The challenging task of clinical deterioration identification in hospitals lies in the intense daily routines of healthcare practitioners, in the unconnected patient data stored in the Electronic Health Records (EHRs) and in the usage of low accuracy scores. Since hospital wards are given less attention compared to the Intensive Care Unit, ICU, we hypothesized that when a platform is connected to a stream of EHR, there would be a drastic improvement in dangerous situations awareness and could thus assist the healthcare team. With the application of machine learning, the system is capable to consider all patient's history and through the use of high-performing predictive models, an intelligent early warning system is enabled. In this work we used 121,089 medical encounters from six different hospitals and 7,540,389 data points, and we compared popular ward protocols with six different scalable machine learning methods (three are classic machine learning models, logistic and probabilistic-based models, and three gradient boosted models). The results showed an advantage in AUC (Area Under the Receiver Operating Characteristic Curve) of 25 percentage points in the best Machine Learning model result compared to the current state-of-the-art protocols. This is shown by the generalization of the algorithm with leave-one-group-out (AUC of 0.949) and the robustness through cross-validation (AUC of 0.961). We also perform experiments to compare several window sizes to justify the use of five patient timestamps. A sample dataset, experiments, and code are available for replicability purposes.

Modeling continuous-time physiological processes that manifest a patient's evolving clinical states is a key step in approaching many problems in healthcare. In this paper, we develop the Hidden Absorbing Semi-Markov Model (HASMM): a versatile probabilistic model that is capable of capturing the modern electronic health record (EHR) data. Unlike existing models, the HASMM accommodates irregularly sampled, temporally correlated, and informatively censored physiological data, and can describe non-stationary clinical state transitions. Learning the HASMM parameters from the EHR data is achieved via a novel forward-filtering backward-sampling Monte-Carlo EM algorithm that exploits the knowledge of the endpoint clinical outcomes (informative censoring) in the EHR data, and implements the E-step by sequentially sampling the patients' clinical states in the reversetime direction while conditioning on the future states. Real-time inferences are drawn via a forward-filtering algorithm that operates on a virtually constructed discrete-time embedded Markov chain that mirrors the patient's continuous-time state trajectory. We demonstrate the prognostic utility of the HASMM in a critical care prognosis setting using a real-world dataset for patients admitted to the Ronald Reagan UCLA Medical Center. In particular, we show that using HASMMs, a patient's clinical deterioration can be predicted 8-9 hours prior to intensive care unit admission, with a 22% AUC gain compared to the Rothman index, which is the state-of-the-art critical care risk scoring technology.

Critically ill patients in regular wards are vulnerable to unanticipated clinical dete- rioration which requires timely transfer to the intensive care unit (ICU). To allow for risk scoring and patient monitoring in such a setting, we develop a novel Semi- Markov Switching Linear Gaussian Model (SSLGM) for the inpatients' physiol- ogy. The model captures the patients' latent clinical states and their corresponding observable lab tests and vital signs. We present an efficient unsupervised learn- ing algorithm that capitalizes on the informatively censored data in the electronic health records (EHR) to learn the parameters of the SSLGM; the learned model is then used to assess the new inpatients' risk for clinical deterioration in an online fashion, allowing for timely ICU admission. Experiments conducted on a het- erogeneous cohort of 6,094 patients admitted to a large academic medical center show that the proposed model significantly outperforms the currently deployed risk scores such as Rothman index, MEWS, SOFA and APACHE.