Competing interests: digital health and indigenous data sovereignty.

Digital health is increasingly promoting open health data. Although this open approach promises a number of benefits, it also leads to tensions with Indigenous data sovereignty movements led by Indigenous peoples around the world who are asserting control over the use of health data as a part of self-determination. Digital health has a role in improving access to services and delivering improved health outcomes for Indigenous communities. However, we argue that in order to be effective and ethical, it is essential that the field engages more with Indigenous peoples´ rights and interests. We discuss challenges and possible improvements for data acquisition, management, analysis, and integration as they pertain to the health of Indigenous communities around the world.

Diversity and inclusion: A hidden additional benefit of Open Data.

The recent imperative by the National Institutes of Health to share scientific data publicly underscores a significant shift in academic research. Effective as of January 2023, it emphasizes that transparency in data collection and dedicated efforts towards data sharing are prerequisites for translational research, from the lab to the bedside. Given the role of data access in mitigating potential bias in clinical models, we hypothesize that researchers who leverage open-access datasets rather than privately-owned ones are more diverse. In this brief report, we proposed to test this hypothesis in the transdisciplinary and expanding field of artificial intelligence (AI) for critical care. Specifically, we compared the diversity among authors of publications leveraging open datasets, such as the commonly used MIMIC and eICU databases, with that among authors of publications relying exclusively on private datasets, unavailable to other research investigators (e.g., electronic health records from ICU patients accessible only to Mayo Clinic analysts). To measure the extent of author diversity, we characterized gender balance as well as the presence of researchers from low- and middle-income countries (LMIC) and minority-serving institutions (MSI) located in the United States (US). Our comparative analysis revealed a greater contribution of authors from LMICs and MSIs among researchers leveraging open critical care datasets (treatment group) than among those relying exclusively on private data resources (control group). The participation of women was similar between the two groups, albeit slightly larger in the former. Notably, although over 70% of all articles included at least one author inferred to be a woman, less than 25% had a woman as a first or last author. Importantly, we found that the proportion of authors from LMICs was substantially higher in the treatment than in the control group (10.1% vs. 6.2%, p<0.001), including as first and last authors. Moreover, we found that the proportion of US-based authors affiliated with a MSI was 1.5 times higher among articles in the treatment than in the control group, suggesting that open data resources attract a larger pool of participants from minority groups (8.6% vs. 5.6%, p<0.001). Thus, our study highlights the valuable contribution of the Open Data strategy to underrepresented groups, while also quantifying persisting gender gaps in academic and clinical research at the intersection of computer science and healthcare. In doing so, we hope our work points to the importance of extending open data practices in deliberate and systematic ways.

BRSET: A Brazilian Multilabel Ophthalmological Dataset of Retina Fundus Photos.

INTRODUCTION: The Brazilian Multilabel Ophthalmological Dataset (BRSET) addresses the scarcity of publicly available ophthalmological datasets in Latin America. BRSET comprises 16,266 color fundus retinal photos from 8,524 Brazilian patients, aiming to enhance data representativeness, serving as a research and teaching tool. It contains sociodemographic information, enabling investigations into differential model performance across demographic groups. METHODS: Data from three São Paulo outpatient centers yielded demographic and medical information from electronic records, including nationality, age, sex, clinical history, insulin use, and duration of diabetes diagnosis. A retinal specialist labeled images for anatomical features (optic disc, blood vessels, macula), quality control (focus, illumination, image field, artifacts), and pathologies (e.g., diabetic retinopathy). Diabetic retinopathy was graded using International Clinic Diabetic Retinopathy and Scottish Diabetic Retinopathy Grading. Validation used a ConvNext model trained during 50 epochs using a weighted cross entropy loss to avoid overfitting, with 70% training (20% validation), and 30% testing subsets. Performance metrics included area under the receiver operating curve (AUC) and Macro F1-score. Saliency maps were calculated for interpretability. RESULTS: BRSET comprises 65.1% Canon CR2 and 34.9% Nikon NF5050 images. 61.8% of the patients are female, and the average age is 57.6 (± 18.26) years. Diabetic retinopathy affected 15.8% of patients, across a spectrum of disease severity. Anatomically, 20.2% showed abnormal optic discs, 4.9% abnormal blood vessels, and 28.8% abnormal macula. A ConvNext V2 model was trained and evaluated BRSET in four prediction tasks: "binary diabetic retinopathy diagnosis (Normal vs Diabetic Retinopathy)" (AUC: 97, F1: 89); "3 class diabetic retinopathy diagnosis (Normal, Proliferative, Non-Proliferative)" (AUC: 97, F1: 82); "diabetes diagnosis" (AUC: 91, F1: 83); "sex classification" (AUC: 87, F1: 70). DISCUSSION: BRSET is the first multilabel ophthalmological dataset in Brazil and Latin America. It provides an opportunity for investigating model biases by evaluating performance across demographic groups. The model performance of three prediction tasks demonstrates the value of the dataset for external validation and for teaching medical computer vision to learners in Latin America using locally relevant data sources.

A multimodal framework for extraction and fusion of satellite images and public health data.

In low- and middle-income countries, the substantial costs associated with traditional data collection pose an obstacle to facilitating decision-making in the field of public health. Satellite imagery offers a potential solution, but the image extraction and analysis can be costly and requires specialized expertise. We introduce SatelliteBench, a scalable framework for satellite image extraction and vector embeddings generation. We also propose a novel multimodal fusion pipeline that utilizes a series of satellite imagery and metadata. The framework was evaluated generating a dataset with a collection of 12,636 images and embeddings accompanied by comprehensive metadata, from 81 municipalities in Colombia between 2016 and 2018. The dataset was then evaluated in 3 tasks: including dengue case prediction, poverty assessment, and access to education. The performance showcases the versatility and practicality of SatelliteBench, offering a reproducible, accessible and open tool to enhance decision-making in public health.

INSPIRE, a publicly available research dataset for perioperative medicine.

We present the INSPIRE dataset, a publicly available research dataset in perioperative medicine, which includes approximately 130,000 surgical operations at an academic institution in South Korea over a ten-year period between 2011 and 2020. This comprehensive dataset includes patient characteristics such as age, sex, American Society of Anesthesiologists physical status classification, diagnosis, surgical procedure code, department, and type of anaesthesia. The dataset also includes vital signs in the operating theatre, general wards, and intensive care units (ICUs), laboratory results from six months before admission to six months after discharge, and medication during hospitalisation. Complications include total hospital and ICU length of stay and in-hospital death. We hope this dataset will inspire collaborative research and development in perioperative medicine and serve as a reproducible external validation dataset to improve surgical outcomes.

Towards long-tailed, multi-label disease classification from chest X-ray: Overview of the CXR-LT challenge.

Many real-world image recognition problems, such as diagnostic medical imaging exams, are "long-tailed" - there are a few common findings followed by many more relatively rare conditions. In chest radiography, diagnosis is both a long-tailed and multi-label problem, as patients often present with multiple findings simultaneously. While researchers have begun to study the problem of long-tailed learning in medical image recognition, few have studied the interaction of label imbalance and label co-occurrence posed by long-tailed, multi-label disease classification. To engage with the research community on this emerging topic, we conducted an open challenge, CXR-LT, on long-tailed, multi-label thorax disease classification from chest X-rays (CXRs). We publicly release a large-scale benchmark dataset of over 350,000 CXRs, each labeled with at least one of 26 clinical findings following a long-tailed distribution. We synthesize common themes of top-performing solutions, providing practical recommendations for long-tailed, multi-label medical image classification. Finally, we use these insights to propose a path forward involving vision-language foundation models for few- and zero-shot disease classification.

Epidemiology of Renal Replacement Therapy for Critically Ill Patients across Seven Health Jurisdictions.

INTRODUCTION: Acute kidney injury (AKI) requiring treatment with renal replacement therapy (RRT) is a common complication after admission to an intensive care unit (ICU) and is associated with significant morbidity and mortality. However, the prevalence of RRT use and the associated outcomes in critically patients across the globe are not well described. Therefore, we describe the epidemiology and outcomes of patients receiving RRT for AKI in ICUs across several large health system jurisdictions. METHODS: Retrospective cohort analysis using nationally representative and comparable databases from seven health jurisdictions in Australia, Brazil, Canada, Denmark, New Zealand, Scotland, and the USA between 2006 and 2023, depending on data availability of each dataset. Patients with a history of end-stage kidney disease receiving chronic RRT and patients with a history of renal transplant were excluded. RESULTS: A total of 4,104,480 patients in the ICU cohort and 3,520,516 patients in the mechanical ventilation cohort were included. Overall, 156,403 (3.8%) patients in the ICU cohort and 240,824 (6.8%) patients in the mechanical ventilation cohort were treated with RRT for AKI. In the ICU cohort, the proportion of patients treated with RRT was lowest in Australia and Brazil (3.3%) and highest in Scotland (9.2%). The in-hospital mortality for critically ill patients treated with RRT was almost fourfold higher (57.1%) than those not receiving RRT (16.8%). The mortality of patients treated with RRT varied across the health jurisdictions from 37 to 65%. CONCLUSION: The outcomes of patients who receive RRT in ICUs throughout the world vary widely. Our research suggests that differences in access to and provision of this therapy are contributing factors.

DF-DM: A foundational process model for multimodal data fusion in the artificial intelligence era.

In the big data era, integrating diverse data modalities poses significant challenges, particularly in complex fields like healthcare. This paper introduces a new process model for multimodal Data Fusion for Data Mining, integrating embeddings and the Cross-Industry Standard Process for Data Mining with the existing Data Fusion Information Group model. Our model aims to decrease computational costs, complexity, and bias while improving efficiency and reliability. We also propose "disentangled dense fusion," a novel embedding fusion method designed to optimize mutual information and facilitate dense inter-modality feature interaction, thereby minimizing redundant information. We demonstrate the model's efficacy through three use cases: predicting diabetic retinopathy using retinal images and patient metadata, domestic violence prediction employing satellite imagery, internet, and census data, and identifying clinical and demographic features from radiography images and clinical notes. The model achieved a Macro F1 score of 0.92 in diabetic retinopathy prediction, an R-squared of 0.854 and sMAPE of 24.868 in domestic violence prediction, and a macro AUC of 0.92 and 0.99 for disease prediction and sex classification, respectively, in radiological analysis. These results underscore the Data Fusion for Data Mining model's potential to significantly impact multimodal data processing, promoting its adoption in diverse, resource-constrained settings.

Navigating the Complexities of Artificial Intelligence-Enabled Real-World Data Collection for Oncology Pharmacovigilance.

This new editorial discusses the promise and challenges of successful integration of natural language processing methods into electronic health records for timely, robust, and fair oncology pharmacovigilance.

BOLD: Blood-gas and Oximetry Linked Dataset.

Pulse oximeters measure peripheral arterial oxygen saturation (SpO2) noninvasively, while the gold standard (SaO2) involves arterial blood gas measurement. There are known racial and ethnic disparities in their performance. BOLD is a dataset that aims to underscore the importance of addressing biases in pulse oximetry accuracy, which disproportionately affect darker-skinned patients. The dataset was created by harmonizing three Electronic Health Record databases (MIMIC-III, MIMIC-IV, eICU-CRD) comprising Intensive Care Unit stays of US patients. Paired SpO2 and SaO2 measurements were time-aligned and combined with various other sociodemographic and parameters to provide a detailed representation of each patient. BOLD includes 49,099 paired measurements, within a 5-minute window and with oxygen saturation levels between 70-100%. Minority racial and ethnic groups account for ~25% of the data - a proportion seldom achieved in previous studies. The codebase is publicly available. Given the prevalent use of pulse oximeters in the hospital and at home, we hope that BOLD will be leveraged to develop debiasing algorithms that can result in more equitable healthcare solutions.

Use of artificial intelligence in critical care: opportunities and obstacles.

BACKGROUND: Perhaps nowhere else in the healthcare system than in the intensive care unit environment are the challenges to create useful models with direct time-critical clinical applications more relevant and the obstacles to achieving those goals more massive. Machine learning-based artificial intelligence (AI) techniques to define states and predict future events are commonplace activities of modern life. However, their penetration into acute care medicine has been slow, stuttering and uneven. Major obstacles to widespread effective application of AI approaches to the real-time care of the critically ill patient exist and need to be addressed. MAIN BODY: Clinical decision support systems (CDSSs) in acute and critical care environments support clinicians, not replace them at the bedside. As will be discussed in this review, the reasons are many and include the immaturity of AI-based systems to have situational awareness, the fundamental bias in many large databases that do not reflect the target population of patient being treated making fairness an important issue to address and technical barriers to the timely access to valid data and its display in a fashion useful for clinical workflow. The inherent "black-box" nature of many predictive algorithms and CDSS makes trustworthiness and acceptance by the medical community difficult. Logistically, collating and curating in real-time multidimensional data streams of various sources needed to inform the algorithms and ultimately display relevant clinical decisions support format that adapt to individual patient responses and signatures represent the efferent limb of these systems and is often ignored during initial validation efforts. Similarly, legal and commercial barriers to the access to many existing clinical databases limit studies to address fairness and generalizability of predictive models and management tools. CONCLUSIONS: AI-based CDSS are evolving and are here to stay. It is our obligation to be good shepherds of their use and further development.

Variation in monitoring: Glucose measurement in the ICU as a case study to preempt spurious correlations.

OBJECTIVE: Health inequities can be influenced by demographic factors such as race and ethnicity, proficiency in English, and biological sex. Disparities may manifest as differential likelihood of testing which correlates directly with the likelihood of an intervention to address an abnormal finding. Our retrospective observational study evaluated the presence of variation in glucose measurements in the Intensive Care Unit (ICU). METHODS: Using the MIMIC-IV database (2008-2019), a single-center, academic referral hospital in Boston (USA), we identified adult patients meeting sepsis-3 criteria. Exclusion criteria were diabetic ketoacidosis, ICU length of stay under 1 day, and unknown race or ethnicity. We performed a logistic regression analysis to assess differential likelihoods of glucose measurements on day 1. A negative binomial regression was fitted to assess the frequency of subsequent glucose readings. Analyses were adjusted for relevant clinical confounders, and performed across three disparity proxy axes: race and ethnicity, sex, and English proficiency. RESULTS: We studied 24,927 patients, of which 19.5% represented racial and ethnic minority groups, 42.4% were female, and 9.8% had limited English proficiency. No significant differences were found for glucose measurement on day 1 in the ICU. This pattern was consistent irrespective of the axis of analysis, i.e. race and ethnicity, sex, or English proficiency. Conversely, subsequent measurement frequency revealed potential disparities. Specifically, males (incidence rate ratio (IRR) 1.06, 95% confidence interval (CI) 1.01 - 1.21), patients who identify themselves as Hispanic (IRR 1.11, 95% CI 1.01 - 1.21), or Black (IRR 1.06, 95% CI 1.01 - 1.12), and patients being English proficient (IRR 1.08, 95% CI 1.01 - 1.15) had higher chances of subsequent glucose readings. CONCLUSION: We found disparities in ICU glucose measurements among patients with sepsis, albeit the magnitude was small. Variation in disease monitoring is a source of data bias that may lead to spurious correlations when modeling health data.

A Reassessment of Sodium Correction Rates and Hospital Length of Stay Accounting for Admission Diagnosis.

Background Slow correction of severe hyponatremia has been historically recommended due to the risk of rare but catastrophic neurologic events with rapid correction. A recent study challenging this paradigm reported that rapid correction is associated with shorter hospital length of stay, but that study did not control for admission diagnosis. The objective of this study was to determine whether rapid correction is associated with shorter length of stay when controlling for admission diagnosis. Methods This retrospective cohort study is based on the fourth edition of the Medical Information Mart for Intensive Care, MIMIC-IV, a deidentified, publicly available clinical research database which includes admissions from 2008-2019. Patients were identified who presented to the hospital with initial sodium <120 mEq/L and were categorized according to total sodium correction achieved in the first day (<6 mEq/L; 6-10 mEq/L; >10 mEq/L). Linear regression was used to assess for an association between correction rate and hospital length of stay, and to determine if this association was significant when controlling for admission diagnosis classifications based on diagnosis related groups (DRGs). Results There were 419 patients with severe hyponatremia (<120 mEq/L) included in this study, of whom 374 survived to discharge. Median [IQR] hospital length of stay was 6 [4, 11] days. In a univariable linear regression, there was a trend towards a significant association between the highest rate of correction (>10 mEq/L) and shorter length of stay, as compared with a moderate rate of correction (coef. -2.764, 95% CI [-5.791, 0.263], p=0.073), but the association was not significant when controlling for admission diagnosis group (coef. -1.561, 95% CI [-4.398, 1.276], p=0.280). There was a significant association in the survivor subset (coef. -3.455, 95% CI [-6.668, -0.242], p=0.035), but it was also not significant when controlling for admission diagnosis group (coef. -2.200, 95% CI [-5.144, 0.743], p=0.142). Conclusions Rapid correction is not associated with shorter length of stay when controlling for admission diagnosis, suggesting that the disease state confounds this association. Findings from prior and future studies reporting this association should not drive clinical decision making if the confounding effect of hospital admission diagnosis and competing risk of death are not fully accounted for.

Critical appraisal of machine learning prognostic models for acute pancreatitis: protocol for a systematic review.

Acute pancreatitis (AP) is an acute inflammatory disorder that is common, costly, and is increasing in incidence worldwide with over 300,000 hospitalizations occurring yearly in the United States alone. As its course and outcomes vary widely, a critical knowledge gap in the field has been a lack of accurate prognostic tools to forecast AP patients' outcomes. Despite several published studies in the last three decades, the predictive performance of published prognostic models has been found to be suboptimal. Recently, non-regression machine learning models (ML) have garnered intense interest in medicine for their potential for better predictive performance. Each year, an increasing number of AP models are being published. However, their methodologic quality relating to transparent reporting and risk of bias in study design has never been systematically appraised. Therefore, through collaboration between a group of clinicians and data scientists with appropriate content expertise, we will perform a systematic review of papers published between January 2021 and December 2023 containing artificial intelligence prognostic models in AP. To systematically assess these studies, the authors will leverage the CHARMS checklist, PROBAST tool for risk of bias assessment, and the most current version of the TRIPOD-AI. (Research Registry ( http://www.reviewregistry1727 .).

Inherent Bias in Electronic Health Records: A Scoping Review of Sources of Bias.

Objectives: 1.1Biases inherent in electronic health records (EHRs), and therefore in medical artificial intelligence (AI) models may significantly exacerbate health inequities and challenge the adoption of ethical and responsible AI in healthcare. Biases arise from multiple sources, some of which are not as documented in the literature. Biases are encoded in how the data has been collected and labeled, by implicit and unconscious biases of clinicians, or by the tools used for data processing. These biases and their encoding in healthcare records undermine the reliability of such data and bias clinical judgments and medical outcomes. Moreover, when healthcare records are used to build data-driven solutions, the biases are further exacerbated, resulting in systems that perpetuate biases and induce healthcare disparities. This literature scoping review aims to categorize the main sources of biases inherent in EHRs. Methods: 1.2We queried PubMed and Web of Science on January 19th, 2023, for peer-reviewed sources in English, published between 2016 and 2023, using the PRISMA approach to stepwise scoping of the literature. To select the papers that empirically analyze bias in EHR, from the initial yield of 430 papers, 27 duplicates were removed, and 403 studies were screened for eligibility. 196 articles were removed after the title and abstract screening, and 96 articles were excluded after the full-text review resulting in a final selection of 116 articles. Results: 1.3Systematic categorizations of diverse sources of bias are scarce in the literature, while the effects of separate studies are often convoluted and methodologically contestable. Our categorization of published empirical evidence identified the six main sources of bias: a) bias arising from past clinical trials; b) data-related biases arising from missing, incomplete information or poor labeling of data; human-related bias induced by c) implicit clinician bias, d) referral and admission bias; e) diagnosis or risk disparities bias and finally, (f) biases in machinery and algorithms. Conclusions: 1.4Machine learning and data-driven solutions can potentially transform healthcare delivery, but not without limitations. The core inputs in the systems (data and human factors) currently contain several sources of bias that are poorly documented and analyzed for remedies. The current evidence heavily focuses on data-related biases, while other sources are less often analyzed or anecdotal. However, these different sources of biases add to one another exponentially. Therefore, to understand the issues holistically we need to explore these diverse sources of bias. While racial biases in EHR have been often documented, other sources of biases have been less frequently investigated and documented (e.g. gender-related biases, sexual orientation discrimination, socially induced biases, and implicit, often unconscious, human-related cognitive biases). Moreover, some existing studies lack causal evidence, illustrating the different prevalences of disease across groups, which does not per se prove the causality. Our review shows that data-, human- and machine biases are prevalent in healthcare and they significantly impact healthcare outcomes and judgments and exacerbate disparities and differential treatment. Understanding how diverse biases affect AI systems and recommendations is critical. We suggest that researchers and medical personnel should develop safeguards and adopt data-driven solutions with a "bias-in-mind" approach. More empirical evidence is needed to tease out the effects of different sources of bias on health outcomes.