Patients with acute kidney injury (AKI) are at high risk of developing chronic kidney disease (CKD), but identifying those at greatest risk remains challenging. We used electronic health record (EHR) data to dynamically track AKI patients' clinical evolution and characterize AKI-to-CKD progression. Post-AKI clinical states were identified by clustering patient vectors derived from longitudinal medical codes and creatinine measurements. Transition probabilities between states and progression to CKD were estimated using multi-state modeling. After identifying common post-AKI trajectories, CKD risk factors in AKI subpopulations were identified through survival analysis. Of 20,699 patients with AKI at admission, 3,491 (17%) developed CKD. We identified fifteen distinct post-AKI states, each with different probabilities of CKD development. Most patients (75%, n=15,607) remained in a single state or made only one transition during the study period. Both established (e.g., AKI severity, diabetes, hypertension, heart failure, liver disease) and novel CKD risk factors, with their impact varying across these clinical states. This study demonstrates a data-driven approach for identifying high-risk AKI patients, supporting the development of decision-support tools for early CKD detection and intervention.

Sepsis is a severe condition that causes the body to respond incorrectly to an infection. This reaction can subsequently cause organ failure, a major one being acute kidney injury (AKI). For septic patients, approximately 50% develop AKI, with a mortality rate above 40%. Creating models that can accurately predict AKI based on specific qualities of septic patients is crucial for early detection and intervention. Using medical data from septic patients during intensive care unit (ICU) admission from the Medical Information Mart for Intensive Care 3 (MIMIC-III) database, we extracted 3301 patients with sepsis, with 73% of patients developing AKI. The data was randomly divided into a training set (n = 1980, 40%), a test set (n = 661, 10%), and a validation set (n = 660, 50%). The proposed model was logistic regression, and it was compared against five baseline models: XGBoost, K Nearest Neighbors (KNN), Support Vector Machines (SVM), Random Forest (RF), and LightGBM. Area Under the Curve (AUC), Accuracy, F1-Score, and Recall were calculated for each model. After analysis, we were able to select 23 features to include in our model, the top features being urine output, maximum bilirubin, minimum bilirubin, weight, maximum blood urea nitrogen, and minimum estimated glomerular filtration rate. The logistic regression model performed the best, achieving an AUC score of 0.887 (95% CI: [0.861-0.915]), an accuracy of 0.817, an F1 score of 0.866, a recall score of 0.827, and a Brier score of 0.13. Compared to the best existing literature in this field, our model achieved an 8.57% improvement in AUC while using 13 fewer variables, showcasing its effectiveness in determining AKI in septic patients. While the features selected for predicting AKI in septic patients are similar to previous literature, the top features that influenced our model's performance differ.

With the enhancement in the field of generative artificial intelligence (AI), contextual question answering has become extremely relevant. Attributing model generations to the input source document is essential to ensure trustworthiness and reliability. We observe that when large language models (LLMs) are used for contextual question answering, the output answer often consists of text copied verbatim from the input prompt which is linked together with "glue text" generated by the LLM. Motivated by this, we propose that LLMs have an inherent awareness from where the text was copied, likely captured in the hidden states of the LLM. We introduce a novel method for attribution in contextual question answering, leveraging the hidden state representations of LLMs. Our approach bypasses the need for extensive model retraining and retrieval model overhead, offering granular attributions and preserving the quality of generated answers. Our experimental results demonstrate that our method performs on par or better than GPT-4 at identifying verbatim copied segments in LLM generations and in attributing these segments to their source. Importantly, our method shows robust performance across various LLM architectures, highlighting its broad applicability. Additionally, we present Verifiability-granular, an attribution dataset which has token level annotations for LLM generations in the contextual question answering setup.

Background: Acute kidney injury (AKI), the decline of kidney excretory function, occurs in up to 18% of hospitalized admissions. Progression of AKI may lead to irreversible kidney damage. Methods: This retrospective cohort study includes adult patients admitted to a non-intensive care unit at the University of Pittsburgh Medical Center (UPMC) (n = 46,815) and University of Florida Health (UFH) (n = 127,202). We developed and compared deep learning and conventional machine learning models to predict progression to Stage 2 or higher AKI within the next 48 hours. We trained local models for each site (UFH Model trained on UFH, UPMC Model trained on UPMC) and a separate model with a development cohort of patients from both sites (UFH-UPMC Model). We internally and externally validated the models on each site and performed subgroup analyses across sex and race. Results: Stage 2 or higher AKI occurred in 3% (n=3,257) and 8% (n=2,296) of UFH and UPMC patients, respectively. Area under the receiver operating curve values (AUROC) for the UFH test cohort ranged between 0.77 (UPMC Model) and 0.81 (UFH Model), while AUROC values ranged between 0.79 (UFH Model) and 0.83 (UPMC Model) for the UPMC test cohort. UFH-UPMC Model achieved an AUROC of 0.81 (95% confidence interval [CI] [0.80, 0.83]) for UFH and 0.82 (95% CI [0.81,0.84]) for UPMC test cohorts; an area under the precision recall curve values (AUPRC) of 0.6 (95% CI, [0.05, 0.06]) for UFH and 0.13 (95% CI, [0.11,0.15]) for UPMC test cohorts. Kinetic estimated glomerular filtration rate, nephrotoxic drug burden and blood urea nitrogen remained the top three features with the highest influence across the models and health centers. Conclusion: Locally developed models displayed marginally reduced discrimination when tested on another institution, while the top set of influencing features remained the same across the models and sites.

The current best practice approach for the retrospective diagnosis of adverse drug events (ADEs) in hospitalized patients relies on a full patient chart review and a formal causality assessment by multiple medical experts. This evaluation serves to qualitatively estimate the probability of causation (PC); the probability that a drug was a necessary cause of an adverse event. This practice is manual, resource intensive and prone to human biases, and may thus benefit from data-driven decision support. Here, we pioneer a causal modeling approach using observational data to estimate a lower bound of the PC (PC$_{low}$). This method includes two key causal inference components: (1) the target trial emulation framework and (2) estimation of individualized treatment effects using machine learning. We apply our method to the clinically relevant use-case of vancomycin-induced acute kidney injury in intensive care patients, and compare our causal model-based PC$_{low}$ estimates to qualitative estimates of the PC provided by a medical expert. Important limitations and potential improvements are discussed, and we conclude that future improved causal models could provide essential data-driven support for medication safety monitoring in hospitalized patients.

Deep learning (DL) can aid doctors in detecting worsening patient states early, affording them time to react and prevent bad outcomes. While DL-based early warning models usually work well in the hospitals they were trained for, they tend to be less reliable when applied at new hospitals. This makes it difficult to deploy them at scale. Using carefully harmonised intensive care data from four data sources across Europe and the US (totalling 334,812 stays), we systematically assessed the reliability of DL models for three common adverse events: death, acute kidney injury (AKI), and sepsis. We tested whether using more than one data source and/or explicitly optimising for generalisability during training improves model performance at new hospitals. We found that models achieved high AUROC for mortality (0.838-0.869), AKI (0.823-0.866), and sepsis (0.749-0.824) at the training hospital. As expected, performance dropped at new hospitals, sometimes by as much as -0.200. Using more than one data source for training mitigated the performance drop, with multi-source models performing roughly on par with the best single-source model. This suggests that as data from more hospitals become available for training, model robustness is likely to increase, lower-bounding robustness with the performance of the most applicable data source in the training data. Dedicated methods promoting generalisability did not noticeably improve performance in our experiments.

Acute kidney injury (AKI) is common in patients in intensive care units, and predicting which patients are at risk can help clinicians take appropriate preventive measures. Investigators recently developed an artificial intelligence–based model to help make such predictions. The research will be presented at ASN Kidney Week 2022 November 3–November 6. Among 16,785 adults admitted to the intensive care unit in 2015–2020 in Taichung Veterans General Hospital, 30% developed AKI. An artificial intelligence–based AKI prediction model based on these patients' data (21 features including urine trend and serum creatine) was validated in patients from 4 other medical centers (2,874, 10,758, 12,299, and 12,483 patients, respectively, with a wide range of AKI incidence of 24.9–67.2%).

Qiuchong Chen,1,* Yixue Zhang,1,* Mengjun Zhang,1 Ziying Li,1 Jindong Liu1,2 1Department of Anesthesiology, The Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, People's Republic of China; 2Jiangsu Province Key Laboratory of Anesthesiology, Xuzhou Medical University, Xuzhou, Jiangsu, People's Republic of China *These authors contributed equally to this work Correspondence: Jindong Liu, Department of Anesthesiology, The Affiliated Hospital of Xuzhou Medical University, 99 Huaihai Road West, Quanshan District, Xuzhou, Jiangsu, 221000, People's Republic of China, Email [email protected] Objective: There has been a worldwide increment in acute kidney injury (AKI) incidence among elderly orthopedic operative patients. The AKI prediction model provides patients' early detection a possibility at risk of AKI; most of the AKI prediction models derive, however, from the cardiothoracic operation. The purpose of this study is to predict the risk of AKI in elderly patients after orthopedic surgery based on machine learning algorithm models. Methods: We organized a retrospective study being comprised of 1000 patients with postoperative AKI undergoing orthopedic surgery from September 2016, to June, 2021. They were divided into training (80%;n 799) and test (20%;n 201) sets.We utilized nine machine learning (ML) algorithms and used intraoperative information and preoperative clinical features to acquire models to predict AKI. The performance of the model was evaluated according to the area under the receiver operating characteristic (AUC), sensitivity, specificity and accuracy. Select the optimal model and establish the nomogram to make the prediction model visualization. The concordance statistic (C-statistic) and calibration curve were used to discriminate and calibrate the nomogram respectively. Results: In predicting AKI, nine ML algorithms posted AUC of 0.656– 1.000 in the training cohort, with the randomforest standing out and AUC of 0.674– 0.821 in the test cohort, with the logistic regression model standing out.

This is an Early Access article. Please select the PDF button, above, to view it.

Purpose: To assess the performance of models for early prediction of acute kidney injury (AKI) in the Intensive Care Unit (ICU) setting. Patients and Methods: Data were collected from the Medical Information Mart for Intensive Care (MIMIC)-III database for all patients aged 18 years who had their serum creatinine (SCr) level measured for 72 h following ICU admission. Those with existing conditions of kidney disease upon ICU admission were excluded from our analyses. Seventeen predictor variables comprising patient demographics and physiological indicators were selected on the basis of the Kidney Disease Improving Global Outcomes (KDIGO) and medical literature. Six models from three types of methods were tested: Logistic Regression (LR), Support Vector Machines (SVM), Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Decision Machine (LightGBM), and Convolutional Neural Network (CNN).