Machine Learning-Based Early Warning Systems for Acute Care Utilization During Systemic Therapy for Cancer.

BACKGROUND: Emergency department visits and hospitalizations frequently occur during systemic therapy for cancer. We developed and evaluated a longitudinal warning system for acute care use. METHODS: Using a retrospective population-based cohort of patients who started intravenous systemic therapy for nonhematologic cancers between July 1, 2014, and June 30, 2020, we randomly separated patients into cohorts for model training, hyperparameter tuning and model selection, and system testing. Predictive features included static features, such as demographics, cancer type, and treatment regimens, and dynamic features, such as patient-reported symptoms and laboratory values. The longitudinal warning system predicted the probability of acute care utilization within 30 days after each treatment session. Machine learning systems were developed in the training and tuning cohorts and evaluated in the testing cohort. Sensitivity analyses considered feature importance, other acute care endpoints, and performance within subgroups. RESULTS: The cohort included 105,129 patients who received 1,216,385 treatment sessions. Acute care followed 182,444 (15.0%) treatments within 30 days. The ensemble model achieved an area under the receiver operating characteristic curve of 0.742 (95% CI, 0.739-0.745) and was well calibrated in the test cohort. Important predictive features included prior acute care use, treatment regimen, and laboratory tests. If the system was set to alarm approximately once every 15 treatments, 25.5% of acute care events would be preceded by an alarm, and 47.4% of patients would experience acute care after an alarm. The system underestimated risk for some treatment regimens and potentially underserved populations such as females and non-English speakers. CONCLUSIONS: Machine learning warning systems can detect patients at risk for acute care utilization, which can aid in preventive intervention and facilitate tailored treatment. Future research should address potential biases and prospectively evaluate impact after system deployment.

Artificial intelligence in gastroenterology and hepatology: how to advance clinical practice while ensuring health equity.

Artificial intelligence (AI) and machine learning (ML) systems are increasingly used in medicine to improve clinical decision-making and healthcare delivery. In gastroenterology and hepatology, studies have explored a myriad of opportunities for AI/ML applications which are already making the transition to bedside. Despite these advances, there is a risk that biases and health inequities can be introduced or exacerbated by these technologies. If unrecognised, these technologies could generate or worsen systematic racial, ethnic and sex disparities when deployed on a large scale. There are several mechanisms through which AI/ML could contribute to health inequities in gastroenterology and hepatology, including diagnosis of oesophageal cancer, management of inflammatory bowel disease (IBD), liver transplantation, colorectal cancer screening and many others. This review adapts a framework for ethical AI/ML development and application to gastroenterology and hepatology such that clinical practice is advanced while minimising bias and optimising health equity.

Outcomes in patients with and without disability admitted to hospital with COVID-19: a retrospective cohort study.

BACKGROUND: Disability-related considerations have largely been absent from the COVID-19 response, despite evidence that people with disabilities are at elevated risk for acquiring COVID-19. We evaluated clinical outcomes in patients who were admitted to hospital with COVID-19 with a disability compared with patients without a disability. METHODS: We conducted a retrospective cohort study that included adults with COVID-19 who were admitted to hospital and discharged between Jan. 1, 2020, and Nov. 30, 2020, at 7 hospitals in Ontario, Canada. We compared in-hospital death, admission to the intensive care unit (ICU), hospital length of stay and unplanned 30-day readmission among patients with and without a physical disability, hearing or vision impairment, traumatic brain injury, or intellectual or developmental disability, overall and stratified by age (≤ 64 and ≥ 65 yr) using multivariable regression, controlling for sex, residence in a long-term care facility and comorbidity. RESULTS: Among 1279 admissions to hospital for COVID-19, 22.3% had a disability. We found that patients with a disability were more likely to die than those without a disability (28.1% v. 17.6%), had longer hospital stays (median 13.9 v. 7.8 d) and more readmissions (17.6% v. 7.9%), but had lower ICU admission rates (22.5% v. 28.3%). After adjustment, there were no statistically significant differences between those with and without disabilities for in-hospital death or admission to ICU. After adjustment, patients with a disability had longer hospital stays (rate ratio 1.36, 95% confidence interval [CI] 1.19-1.56) and greater risk of readmission (relative risk 1.77, 95% CI 1.14-2.75). In age-stratified analyses, we observed longer hospital stays among patients with a disability than in those without, in both younger and older subgroups; readmission risk was driven by younger patients with a disability. INTERPRETATION: Patients with a disability who were admitted to hospital with COVID-19 had longer stays and elevated readmission risk than those without disabilities. Disability-related needs should be addressed to support these patients in hospital and after discharge.

Characteristics and outcomes of hospital admissions for COVID-19 and influenza in the Toronto area.

BACKGROUND: Patient characteristics, clinical care, resource use and outcomes associated with admission to hospital for coronavirus disease 2019 (COVID-19) in Canada are not well described. METHODS: We described all adults with COVID-19 or influenza discharged from inpatient medical services and medical-surgical intensive care units (ICUs) between Nov. 1, 2019, and June 30, 2020, at 7 hospitals in Toronto and Mississauga, Ontario. We compared patient outcomes using multivariable regression models, controlling for patient sociodemographic factors and comorbidity level. We validated the accuracy of 7 externally developed risk scores to predict mortality among patients with COVID-19. RESULTS: There were 1027 hospital admissions with COVID-19 (median age 65 yr, 59.1% male) and 783 with influenza (median age 68 yr, 50.8% male). Patients younger than 50 years accounted for 21.2% of all admissions for COVID-19 and 24.0% of ICU admissions. Compared with influenza, patients with COVID-19 had significantly greater in-hospital mortality (unadjusted 19.9% v. 6.1%, adjusted relative risk [RR] 3.46, 95% confidence interval [CI] 2.56-4.68), ICU use (unadjusted 26.4% v. 18.0%, adjusted RR 1.50, 95% CI 1.25-1.80) and hospital length of stay (unadjusted median 8.7 d v. 4.8 d, adjusted rate ratio 1.45, 95% CI 1.25-1.69). Thirty-day readmission was not significantly different (unadjusted 9.3% v. 9.6%, adjusted RR 0.98, 95% CI 0.70-1.39). Three points-based risk scores for predicting in-hospital mortality showed good discrimination (area under the receiver operating characteristic curve [AUC] ranging from 0.72 to 0.81) and calibration. INTERPRETATION: During the first wave of the pandemic, admission to hospital for COVID-19 was associated with significantly greater mortality, ICU use and hospital length of stay than influenza. Simple risk scores can predict in-hospital mortality in patients with COVID-19 with good accuracy.

What Every Reader Should Know About Studies Using Electronic Health Record Data but May Be Afraid to Ask.

Coincident with the tsunami of COVID-19-related publications, there has been a surge of studies using real-world data, including those obtained from the electronic health record (EHR). Unfortunately, several of these high-profile publications were retracted because of concerns regarding the soundness and quality of the studies and the EHR data they purported to analyze. These retractions highlight that although a small community of EHR informatics experts can readily identify strengths and flaws in EHR-derived studies, many medical editorial teams and otherwise sophisticated medical readers lack the framework to fully critically appraise these studies. In addition, conventional statistical analyses cannot overcome the need for an understanding of the opportunities and limitations of EHR-derived studies. We distill here from the broader informatics literature six key considerations that are crucial for appraising studies utilizing EHR data: data completeness, data collection and handling (eg, transformation), data type (ie, codified, textual), robustness of methods against EHR variability (within and across institutions, countries, and time), transparency of data and analytic code, and the multidisciplinary approach. These considerations will inform researchers, clinicians, and other stakeholders as to the recommended best practices in reviewing manuscripts, grants, and other outputs from EHR-data derived studies, and thereby promote and foster rigor, quality, and reliability of this rapidly growing field.

Caractéristiques et issues des hospitalisations pour les cas de COVID-19 et d'influenza dans la région de Toronto.

CONTEXTE: Les caractéristiques des patients, les soins cliniques, l'utilisation des ressources et les issues cliniques des personnes atteintes de la maladie à coronavirus 2019 (COVID-19) hospitalisées au Canada ne sont pas bien connus. MÉTHODES: Nous avons recueilli des données sur tous les adultes hospitalisés atteints de la COVID-19 ou de l'influenza ayant obtenu leur congé d'unités médicales ou d'unités de soins intensifs médicaux et chirurgicaux entre le 1er novembre 2019 et le 30 juin 2020 dans 7 centres hospitaliers de Toronto et de Mississauga (Ontario). Nous avons comparé les issues cliniques des patients à l'aide de modèles de régression multivariée, en tenant compte des facteurs sociodémographiques et de l'intensité des comorbidités. Nous avons validé le degré d'exactitude de 7 scores de risque mis au point à l'externe pour déterminer leur capacité à prédire le risque de décès chez les patients atteints de la COVID-19. RÉSULTATS: Parmi les hospitalisations retenues, 1027 patients étaient atteints de la COVID-19 (âge médian de 65 ans, 59,1 % d'hommes) et 783 étaient atteints de l'influenza (âge médian de 68 ans, 50,8 % d'hommes). Les patients âgés de moins de 50 ans comptaient pour 21,2 % de toutes les hospitalisations dues à la COVID-19 et 24,0 % des séjours aux soins intensifs. Comparativement aux patients atteints de l'influenza, les patients atteints de la COVID-19 présentaient un taux de mortalité perhospitalière (mortalité non ajustée 19,9 % c. 6,1 %; risque relatif [RR] ajusté 3,46 %, intervalle de confiance [IC] à 95 % 2,56­4,68) et un taux d'utilisation des ressources des unités de soins intensifs (taux non ajusté 26,4 % c. 18,0 %; RR ajusté 1,50, IC à 95 % 1,25­1,80) significativement plus élevés, ainsi qu'une durée d'hospitalisation (durée médiane non ajustée 8,7 jours c. 4,8 jours; rapport des taux d'incidence ajusté 1,45; IC à 95 % 1,25­1,69) significativement plus longue. Le taux de réhospitalisation dans les 30 jours n'était pas significativement différent (taux non ajusté 9,3 % c. 9,6 %; RR ajusté 0,98 %, IC à 95 % 0,70­1,39). Trois scores de risque utilisant un pointage pour prédire la mortalité perhospitalière ont montré une bonne discrimination (aire sous la courbe [ASC] de la fonction d'efficacité du récepteur [ROC] 0,72­0,81) et une bonne calibration. INTERPRÉTATION: Durant la première vague de la pandémie, l'hospitalisation des patients atteints de la COVID-19 était associée à des taux de mortalité et d'utilisation des ressources des unités de soins intensifs et à une durée d'hospitalisation significativement plus importants que les hospitalisations des patients atteints de l'influenza. De simples scores de risque peuvent prédire avec une bonne exactitude le risque de mortalité perhospitalière des patients atteints de la COVID-19.

Sodium modelling to reduce intradialytic hypotension during haemodialysis for acute kidney injury in the intensive care unit.

AIM: Intradialytic hypotension often complicates haemodialysis for patients with acute kidney injury (AKI) and may impact renal recovery. Sodium modelling is sometimes used as prophylaxis against intradialytic hypotension in the chronic haemodialysis population, but there is little evidence for its use among critically ill patients with AKI. METHODS: A retrospective cohort with AKI requiring intermittent haemodialysis in the intensive care unit from 2001 to 2008 was used to study the association of prophylactic sodium modelling and multiple outcomes. Outcomes included a composite of in-hospital death or dialysis dependence at hospital discharge, as well as intradialytic hypotension, ultrafiltration goal achievement and net ultrafiltration volume. Associations were estimated using logistic regression, mixed linear models and generalized estimating equations adjusting for demographic and clinical characteristics. RESULTS: One hundred and ninety-one individuals who underwent 892 sessions were identified; sodium modelling was prescribed in 27.1% of the sessions. In adjusted analyses, sodium modelling was not significantly associated with intradialytic hypotension (P = 0.67) or with the ultrafiltration goal achievement (P = 0.06). Sodium modelling during the first dialysis session was numerically associated with lower risk for the composite of in-hospital death or dialysis dependence: adjusted odds ratio (95% confidence interval) 0.39 (0.15-1.02; P = 0.06); however, this association did not reach statistical significance. CONCLUSION: We did not observe statistically significant associations between sodium modelling and improved outcomes among AKI patients receiving intermittent dialysis in the intensive care unit. However, suggestive findings warrant further study.

State of the art review: the data revolution in critical care.

This article is one of ten reviews selected from the Annual Update in Intensive Care and Emergency Medicine 2015 and co-published as a series in Critical Care. Other articles in the series can be found online at http://ccforum.com/series/annualupdate2015. Further information about the Annual Update in Intensive Care and Emergency Medicine is available from http://www.springer.com/series/8901.

The limits of fair medical imaging AI in real-world generalization.

As artificial intelligence (AI) rapidly approaches human-level performance in medical imaging, it is crucial that it does not exacerbate or propagate healthcare disparities. Previous research established AI's capacity to infer demographic data from chest X-rays, leading to a key concern: do models using demographic shortcuts have unfair predictions across subpopulations? In this study, we conducted a thorough investigation into the extent to which medical AI uses demographic encodings, focusing on potential fairness discrepancies within both in-distribution training sets and external test sets. Our analysis covers three key medical imaging disciplines-radiology, dermatology and ophthalmology-and incorporates data from six global chest X-ray datasets. We confirm that medical imaging AI leverages demographic shortcuts in disease classification. Although correcting shortcuts algorithmically effectively addresses fairness gaps to create 'locally optimal' models within the original data distribution, this optimality is not true in new test settings. Surprisingly, we found that models with less encoding of demographic attributes are often most 'globally optimal', exhibiting better fairness during model evaluation in new test environments. Our work establishes best practices for medical imaging models that maintain their performance and fairness in deployments beyond their initial training contexts, underscoring critical considerations for AI clinical deployments across populations and sites.

Artificial intelligence.

Experts discuss the challenges and opportunities of using artificial intelligence (AI) to study the evolution of cancer cells and their microenvironment, improve diagnosis, predict treatment response, and ensure responsible implementation in the clinic.

Peer review of GPT-4 technical report and systems card.

The study provides a comprehensive review of OpenAI's Generative Pre-trained Transformer 4 (GPT-4) technical report, with an emphasis on applications in high-risk settings like healthcare. A diverse team, including experts in artificial intelligence (AI), natural language processing, public health, law, policy, social science, healthcare research, and bioethics, analyzed the report against established peer review guidelines. The GPT-4 report shows a significant commitment to transparent AI research, particularly in creating a systems card for risk assessment and mitigation. However, it reveals limitations such as restricted access to training data, inadequate confidence and uncertainty estimations, and concerns over privacy and intellectual property rights. Key strengths identified include the considerable time and economic investment in transparent AI research and the creation of a comprehensive systems card. On the other hand, the lack of clarity in training processes and data raises concerns about encoded biases and interests in GPT-4. The report also lacks confidence and uncertainty estimations, crucial in high-risk areas like healthcare, and fails to address potential privacy and intellectual property issues. Furthermore, this study emphasizes the need for diverse, global involvement in developing and evaluating large language models (LLMs) to ensure broad societal benefits and mitigate risks. The paper presents recommendations such as improving data transparency, developing accountability frameworks, establishing confidence standards for LLM outputs in high-risk settings, and enhancing industry research review processes. It concludes that while GPT-4's report is a step towards open discussions on LLMs, more extensive interdisciplinary reviews are essential for addressing bias, harm, and risk concerns, especially in high-risk domains. The review aims to expand the understanding of LLMs in general and highlights the need for new reflection forms on how LLMs are reviewed, the data required for effective evaluation, and addressing critical issues like bias and risk.

Optimizing warfarin dosing for patients with atrial fibrillation using machine learning.

While novel oral anticoagulants are increasingly used to reduce risk of stroke in patients with atrial fibrillation, vitamin K antagonists such as warfarin continue to be used extensively for stroke prevention across the world. While effective in reducing the risk of strokes, the complex pharmacodynamics of warfarin make it difficult to use clinically, with many patients experiencing under- and/or over- anticoagulation. In this study we employed a novel implementation of deep reinforcement learning to provide clinical decision support to optimize time in therapeutic International Normalized Ratio (INR) range. We used a novel semi-Markov decision process formulation of the Batch-Constrained deep Q-learning algorithm to develop a reinforcement learning model to dynamically recommend optimal warfarin dosing to achieve INR of 2.0-3.0 for patients with atrial fibrillation. The model was developed using data from 22,502 patients in the warfarin treated groups of the pivotal randomized clinical trials of edoxaban (ENGAGE AF-TIMI 48), apixaban (ARISTOTLE) and rivaroxaban (ROCKET AF). The model was externally validated on data from 5730 warfarin-treated patients in a fourth trial of dabigatran (RE-LY) using multilevel regression models to estimate the relationship between center-level algorithm consistent dosing, time in therapeutic INR range (TTR), and a composite clinical outcome of stroke, systemic embolism or major hemorrhage. External validation showed a positive association between center-level algorithm-consistent dosing and TTR (R2 = 0.56). Each 10% increase in algorithm-consistent dosing at the center level independently predicted a 6.78% improvement in TTR (95% CI 6.29, 7.28; p < 0.001) and a 11% decrease in the composite clinical outcome (HR 0.89; 95% CI 0.81, 1.00; p = 0.015). These results were comparable to those of a rules-based clinical algorithm used for benchmarking, for which each 10% increase in algorithm-consistent dosing independently predicted a 6.10% increase in TTR (95% CI 5.67, 6.54, p < 0.001) and a 10% decrease in the composite outcome (HR 0.90; 95% CI 0.83, 0.98, p = 0.018). Our findings suggest that a deep reinforcement learning algorithm can optimize time in therapeutic range for patients taking warfarin. A digital clinical decision support system to promote algorithm-consistent warfarin dosing could optimize time in therapeutic range and improve clinical outcomes in atrial fibrillation globally.