2,833 publications from this institution
We develop an unsupervised probabilistic model for heterogeneous Electronic Health Record (EHR) data. Utilizing a mixture model formulation, our approach directly models sequences of arbitrary length, such as medications and laboratory results. This allows for subgrouping and incorporation of the dynamics underlying heterogeneous data types. The model consists of a layered set of latent variables that encode underlying structure in the data. These variables represent subject subgroups at the top layer, and unobserved states for sequences in the second layer. We train this model on episodic data from subjects receiving medical care in the Kaiser Permanente Northern California integrated healthcare delivery system. The resulting properties of the trained model generate novel insight from these complex and multifaceted data. In addition, we show how the model can be used to analyze sequences that contribute to assessment of mortality likelihood.
Abstract Despite demonstrated facility for arithmetic and other quantitative tasks, the performance of ChatGPT and other large language models for clinical risk calculation have yet to be assessed. Using synthetic patient data, this preliminary study aimed to assess the calibration, reproducibility, and potential for sociodemographic bias of ChatGPT-derived Pooled Cohort Equation (PCE) scores of atherosclerotic cardiovascular disease risk as compared to true scores. We found that ChatGPT-derived PCE scores, despite being moderately associated with the true PCE scores, displayed poor calibration with respect to true PCE scores, and exhibited instability between repeated rounds of prompting, suggesting lack of reproducibility. Moreover, ChatGPT-derived PCE scores also appeared inappropriately sensitive to contextual indicators of the sociodemographic status of the synthetic patients in this study. Further work is needed to confirm these results, and to assess performance on a wider variety of prompts as well as in other settings beyond cardiovascular disease prevention where accurate risk calculation is also vital to appropriate clinical decision-making. Abstract Figure Figure. Underestimation of true PCE risk estimates ( x -axis) by ChatGPT ( y -axis) on synthetic patient data.
The SOFA score is a simple, but effective method to describe organ dysfunction/failure in critically ill patients. Regular, repeated scoring enables patient condition and disease development to be monitored and better understood. The SOFA score may enable comparison between patients that would benefit clinical trials.
Acute renal failure (ARF) in the ICU patient usually occurs as part of a wider multiple organ dysfunction, and is associated with mortality rates of around 50%. Differences in definitions make comparing study populations difficult and moves are being made to improve uniformity, and to recognize that ARF is not a single event but a continuous process from mild renal dysfunction through to complete organ failure requiring renal replacement therapy. In this review we will discuss the epidemiology of ARF within the limitations imposed by comparing studies that use different definitions and focus on different patient populations.
info:eu-repo/semantics/published
info:eu-repo/semantics/published
info:eu-repo/semantics/published
Endotoxin is an important pathogenic trigger for sepsis. The polymyxin B-immobilized endotoxin removal hemoperfusion cartridge, Toraymyxin (hereafter PMX), has been shown to remove endotoxin in preclinical and open-label clinical studies. In a multicenter, open-label, pilot, randomized, controlled study conducted in the intensive care unit in six academic medical centers in Europe, 36 postsurgical patients with severe sepsis or septic shock secondary to intra-abdominal infection were randomized to PMX treatment of 2 h (n = 17) or standard therapy (n = 19). PMX was well tolerated and showed no significant side effects. There were no statistically significant differences in the change in endotoxin levels from baseline to 6 to 8 h after treatment or to 24 h after treatment between the two groups. There was also no significant difference in the change in interleukin (IL)-6 levels from baseline to 6 to 8 h after treatment or to 24 h after treatment between the two groups. Patients treated with PMX demonstrated significant increases in cardiac index (CI; P = 0.012 and 0.032 at days 1 and 2, respectively), left ventricular stroke work index (LVSWI, P = 0.015 at day 2), and oxygen delivery index (DO2I, P = 0.007 at day 2) compared with the controls. The need for continuous renal replacement therapy (CRRT) after study entry was reduced in the PMX group (P = 0.043). There was no significant difference between the groups in organ dysfunction as assessed by the Sequential Organ Failure Assessment (SOFA) scores from day 0 (baseline) to day 6. Treatment using the PMX cartridge is safe and may improve cardiac and renal dysfunction due to sepsis or septic shock. Further studies are needed to prove this effectiveness.
