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 United States (USA) between 2006-2023, depending on data availability of each dataset. Patients with 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 four-fold higher (57.1%) than those not receiving RRT (16.8%). The mortality of patients treated with RRT varied across the health jurisdictions from 37-65%. CONCLUSION: The outcomes of patients who receive RRT in ICUs throughout the world vary widely. Our research suggests differences in access to and provision of this therapy are contributing factors.

AI in Pathology: What could possibly go wrong?

The field of medicine is undergoing rapid digital transformation. Pathologists are now striving to digitize their data, workflows, and interpretations, assisted by the enabling development of whole-slide imaging. Going digital means that the analog process of human diagnosis can be augmented or even replaced by rapidly evolving AI approaches, which are just now entering into clinical practice. But with such progress comes challenges that reflect a variety of stressors, including the impact of unrepresentative training data with accompanying implicit bias, data privacy concerns, and fragility of algorithm performance. Beyond such core digital aspects, considerations arise related to difficulties presented by changing disease presentations, diagnostic approaches, and therapeutic options. While some tools such as data federation can help with broadening data diversity while preserving expertise and local control, they may not be the full answer to some of these issues. The impact of AI in pathology on the field's human practitioners is still very much unknown: installation of unconscious bias and deference to AI guidance need to be understood and addressed. If AI is widely adopted, it may remove many inefficiencies in daily practice and compensate for staff shortages. It may also cause practitioner deskilling, dethrilling, and burnout. We discuss the technological, clinical, legal, and sociological factors that will influence the adoption of AI in pathology, and its eventual impact for good or ill.

The Global Open Source Severity of Illness Score (GOSSIS).

OBJECTIVES: To develop and demonstrate the feasibility of a Global Open Source Severity of Illness Score (GOSSIS)-1 for critical care patients, which generalizes across healthcare systems and countries. DESIGN: A merger of several critical care multicenter cohorts derived from registry and electronic health record data. Data were split into training (70%) and test (30%) sets, using each set exclusively for development and evaluation, respectively. Missing data were imputed when not available. SETTING/PATIENTS: Two large multicenter datasets from Australia and New Zealand (Australian and New Zealand Intensive Care Society Adult Patient Database [ANZICS-APD]) and the United States (eICU Collaborative Research Database [eICU-CRD]) representing 249,229 and 131,051 patients, respectively. ANZICS-APD and eICU-CRD contributed data from 162 and 204 hospitals, respectively. The cohort included all ICU admissions discharged in 2014-2015, excluding patients less than 16 years old, admissions less than 6 hours, and those with a previous ICU stay. INTERVENTIONS: Not applicable. MEASUREMENTS AND MAIN RESULTS: GOSSIS-1 uses data collected during the ICU stay's first 24 hours, including extrema values for vital signs and laboratory results, admission diagnosis, the Glasgow Coma Scale, chronic comorbidities, and admission/demographic variables. The datasets showed significant variation in admission-related variables, case-mix, and average physiologic state. Despite this heterogeneity, test set discrimination of GOSSIS-1 was high (area under the receiver operator characteristic curve [AUROC], 0.918; 95% CI, 0.915-0.921) and calibration was excellent (standardized mortality ratio [SMR], 0.986; 95% CI, 0.966-1.005; Brier score, 0.050). Performance was held within ANZICS-APD (AUROC, 0.925; SMR, 0.982; Brier score, 0.047) and eICU-CRD (AUROC, 0.904; SMR, 0.992; Brier score, 0.055). Compared with GOSSIS-1, Acute Physiology and Chronic Health Evaluation (APACHE)-IIIj (ANZICS-APD) and APACHE-IVa (eICU-CRD), had worse discrimination with AUROCs of 0.904 and 0.869, and poorer calibration with SMRs of 0.594 and 0.770, and Brier scores of 0.059 and 0.063, respectively. CONCLUSIONS: GOSSIS-1 is a modern, free, open-source inhospital mortality prediction algorithm for critical care patients, achieving excellent discrimination and calibration across three countries.

Systematic Review and Comparison of Publicly Available ICU Data Sets-A Decision Guide for Clinicians and Data Scientists.

OBJECTIVE: As data science and artificial intelligence continue to rapidly gain traction, the publication of freely available ICU datasets has become invaluable to propel data-driven clinical research. In this guide for clinicians and researchers, we aim to: 1) systematically search and identify all publicly available adult clinical ICU datasets, 2) compare their characteristics, data quality, and richness and critically appraise their strengths and weaknesses, and 3) provide researchers with suggestions, which datasets are appropriate for answering their clinical question. DATA SOURCES: A systematic search was performed in Pubmed, ArXiv, MedRxiv, and BioRxiv. STUDY SELECTION: We selected all studies that reported on publicly available adult patient-level intensive care datasets. DATA EXTRACTION: A total of four publicly available, adult, critical care, patient-level databases were included (Amsterdam University Medical Center data base [AmsterdamUMCdb], eICU Collaborative Research Database eICU CRD], High time-resolution intensive care unit dataset [HiRID], and Medical Information Mart for Intensive Care-IV). Databases were compared using a priori defined categories, including demographics, patient characteristics, and data richness. The study protocol and search strategy were prospectively registered. DATA SYNTHESIS: Four ICU databases fulfilled all criteria for inclusion and were queried using SQL (PostgreSQL version 12; PostgreSQL Global Development Group) and analyzed using R (R Foundation for Statistical Computing, Vienna, Austria). The number of unique patient admissions varied between 23,106 (AmsterdamUMCdb) and 200,859 (eICU-CRD). Frequency of laboratory values and vital signs was highest in HiRID, for example, 5.2 (±3.4) lactate values per day and 29.7 (±10.2) systolic blood pressure values per hour. Treatment intensity varied with vasopressor and ventilatory support in 69.0% and 83.0% of patients in AmsterdamUMCdb versus 12.0% and 21.0% in eICU-CRD, respectively. ICU mortality ranged from 5.5% in eICU-CRD to 9.9% in AmsterdamUMCdb. CONCLUSIONS: We identified four publicly available adult clinical ICU datasets. Sample size, severity of illness, treatment intensity, and frequency of reported parameters differ markedly between the databases. This should guide clinicians and researchers which databases to best answer their clinical questions.

Artificial intelligence for mechanical ventilation: systematic review of design, reporting standards, and bias.

BACKGROUND: Artificial intelligence (AI) has the potential to personalise mechanical ventilation strategies for patients with respiratory failure. However, current methodological deficiencies could limit clinical impact. We identified common limitations and propose potential solutions to facilitate translation of AI to mechanical ventilation of patients. METHODS: A systematic review was conducted in MEDLINE, Embase, and PubMed Central to February 2021. Studies investigating the application of AI to patients undergoing mechanical ventilation were included. Algorithm design and adherence to reporting standards were assessed with a rubric combining published guidelines, satisfying the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis [TRIPOD] statement. Risk of bias was assessed by using the Prediction model Risk Of Bias ASsessment Tool (PROBAST), and correspondence with authors to assess data and code availability. RESULTS: Our search identified 1,342 studies, of which 95 were included: 84 had single-centre, retrospective study design, with only one randomised controlled trial. Access to data sets and code was severely limited (unavailable in 85% and 87% of studies, respectively). On request, data and code were made available from 12 and 10 authors, respectively, from a list of 54 studies published in the last 5 yr. Ethnicity was frequently under-reported 18/95 (19%), as was model calibration 17/95 (18%). The risk of bias was high in 89% (85/95) of the studies, especially because of analysis bias. CONCLUSIONS: Development of algorithms should involve prospective and external validation, with greater code and data availability to improve confidence in and translation of this promising approach. TRIAL REGISTRATION NUMBER: PROSPERO - CRD42021225918.

Lower household income is associated with an increased risk of hospital readmission in patients with decompensated cirrhosis.

BACKGROUND AND AIM: The impact of household income, a surrogate of socioeconomic status, on hospital readmission rates for patients with decompensated cirrhosis has not been well characterized. METHODS: The Nationwide Readmission Database from 2012 to 2014 was used to study the association of lower median household income on 30-, 90-, and 180-day hospital readmission rates for patients with decompensated cirrhosis. RESULTS: From the 42 679 001 hospital admissions contained in the sample, there were 82 598 patients with decompensated cirrhosis who survived a hospital admission in the first 6 months of the year. During a uniform 6-month follow-up period, 25 914 (31.4%), 39 928 (48.3%), and 47 496 (57.5%) patients were readmitted at 30, 90, and 180 days, respectively. After controlling for demographic and clinical confounders, patients residing in the three lowest income quartiles were significantly more likely to be readmitted at 30 days than those in the fourth quartile (first quartile, odds ratio [OR] 1.32 [95% confidence interval, CI, 1.17-1.47, P < 0.01]; second quartile, OR 1.25 [95% CI 1.13-1.38, P < 0.01]; and third quartile, OR 1.08 [95% CI 0.97-1.20, P = 0.07]). The association between lower socioeconomic status and the higher risk of readmissions persisted at 90 days (first quartile, OR 1.21 [95% CI 1.14-1.30, P < 0.01]) and 180 days (first quartile, OR 1.32 [95% CI 1.20-1.44, P < 0.01]). CONCLUSION: Patients with decompensated cirrhosis residing in the lowest income quartile had a 32% higher odds of hospital readmissions at 30, 90, and 180 days compared with those in the highest income quartile.

Lower 90-day Hospital Readmission Rates for Esophageal Variceal Bleeding After TIPS: A Nationwide Linked Analysis.

OBJECTIVE: Hospital readmission rates following a transjugular intrahepatic portosystemic shunt (TIPS) insertion after an episode of esophageal variceal bleeding (EVB) has not been well studied. We aimed to address this gap in knowledge on a population level. METHODS: The Nationwide Readmission Database (NRD) was used to study the readmission rates for patients with decompensated cirrhosis who had a TIPS insertion performed for EVB. The NRD is a national database that tracks patients longitudinally for hospital readmissions. A propensity score matching model was created to match patients who received TIPS with those who did not. RESULTS: A total of 42,679,001 hospital admissions from the 2012 to 2014 NRD sample were analyzed. There were 33,934 patients with EVB who met inclusion criteria for the study, of whom, 1527 (4.5%) received TIPS after EVB and were matched with 1527 patients with EVB who did not undergo TIPS. With a uniform follow-up of 3 months, patients with TIPS were less likely to be readmitted to hospital with a recurrent EVB [odds ratio (OR): 0.33, 95% confidence interval (CI): 0.24-0.47, P<0.01], although were more likely to be readmitted with hepatic encephalopathy (OR: 1.66; 95% CI: 1.31-2.11, P<0.01). At 3 months, there was no difference in all cause hospital readmission rate between the 2 groups (OR: 38.8%; 95% CI: 38.1-44.9 TIPS vs. OR: 41.5%; 95% CI: 34.1-43.3 non-TIPS: P=0.17). CONCLUSIONS: In this large nationally representative study, TIPS insertion after an episode of EVB was associated with a significantly lower risk of 3-month readmission for recurrent EVB compared with patients who did not receive TIPS. Although those receiving TIPS had a higher rate of hepatic encephalopathy the overall readmission remained unchanged.

Accelerating ophthalmic artificial intelligence research: the role of an open access data repository.

PURPOSE OF REVIEW: Artificial intelligence has already provided multiple clinically relevant applications in ophthalmology. Yet, the explosion of nonstandardized reporting of high-performing algorithms are rendered useless without robust and streamlined implementation guidelines. The development of protocols and checklists will accelerate the translation of research publications to impact on patient care. RECENT FINDINGS: Beyond technological scepticism, we lack uniformity in analysing algorithmic performance generalizability, and benchmarking impacts across clinical settings. No regulatory guardrails have been set to minimize bias or optimize interpretability; no consensus clinical acceptability thresholds or systematized postdeployment monitoring has been set. Moreover, stakeholders with misaligned incentives deepen the landscape complexity especially when it comes to the requisite data integration and harmonization to advance the field. Therefore, despite increasing algorithmic accuracy and commoditization, the infamous 'implementation gap' persists. Open clinical data repositories have been shown to rapidly accelerate research, minimize redundancies and disseminate the expertise and knowledge required to overcome existing barriers. Drawing upon the longstanding success of existing governance frameworks and robust data use and sharing agreements, the ophthalmic community has tremendous opportunity in ushering artificial intelligence into medicine. By collaboratively building a powerful resource of open, anonymized multimodal ophthalmic data, the next generation of clinicians can advance data-driven eye care in unprecedented ways. SUMMARY: This piece demonstrates that with readily accessible data, immense progress can be achieved clinically and methodologically to realize artificial intelligence's impact on clinical care. Exponentially progressive network effects can be seen by consolidating, curating and distributing data amongst both clinicians and data scientists.

Outcomes of in-hospital cardiopulmonary resuscitation for patients with end-stage liver disease.

BACKGROUND AND AIMS: There have been improving survival trends after in-hospital cardiac arrest for the general population, but there is limited information on the outcomes of hospitalized patients with end-stage liver disease (ESLD) who undergo cardiopulmonary resuscitation (CPR). We aimed to examine survival to hospital discharge after receipt of in-hospital CPR in patients with ESLD using a nationally representative sample. METHODS: We used the Nationwide Inpatient Sample database from 2006 to 2014 to identify adult patients who underwent in-hospital CPR. Using multivariate modelling, we compared survival to hospital discharge for patients with ESLD to those without ESLD. We also compared outcomes of patients with ESLD to patients with metastatic cancer. RESULTS: A total of 177 533 patients underwent in-hospital CPR, of which 1474 (0.8%) had ESLD. Patients with ESLD had lower rates of survival to hospital discharge compared to patients without ESLD (10.7% vs 28.6%, P < 0.01). In multivariate modelling, ESLD was significantly associated with lower odds of survival to hospital discharge after in-hospital CPR (OR 0.35, 95% CI 0.28-0.44, P < 0.01). Among survivors of in-hospital CPR, ESLD patients had a significantly lower chance of discharge to home compared to patients without ESLD (3.2% vs 8.0%, P < 0.05). Patients with ESLD also had lower rates of survival to hospital discharge compared to those with metastatic cancer (10.7% vs 15.5%, P < 0.01). CONCLUSIONS: Outcomes are poor after in-hospital CPR in patients with ESLD and are worse than for patients with metastatic cancer. The current analysis can be used to inform goals of care discussions for patients with ESLD.

A Comparative Analysis of Sepsis Identification Methods in an Electronic Database.

OBJECTIVES: To evaluate the relative validity of criteria for the identification of sepsis in an ICU database. DESIGN: Retrospective cohort study of adult ICU admissions from 2008 to 2012. SETTING: Tertiary teaching hospital in Boston, MA. PATIENTS: Initial admission of all adult patients to noncardiac surgical ICUs. INTERVENTIONS: Comparison of five different algorithms for retrospectively identifying sepsis, including the Sepsis-3 criteria. MEASUREMENTS AND MAIN RESULTS: 11,791 of 23,620 ICU admissions (49.9%) met criteria for the study. Within this subgroup, 59.9% were suspected of infection on ICU admission, 75.2% of admissions had Sequential Organ Failure Assessment greater than or equal to 2, and 49.1% had both suspicion of infection and Sequential Organ Failure Assessment greater than or equal to 2 thereby meeting the Sepsis-3 criteria. The area under the receiver operator characteristic of Sequential Organ Failure Assessment (0.74) for hospital mortality was consistent with previous studies of the Sepsis-3 criteria. The Centers for Disease Control and Prevention, Angus, Martin, Centers for Medicare & Medicaid Services, and explicit coding methods for identifying sepsis revealed respective sepsis incidences of 31.9%, 28.6%, 14.7%, 11.0%, and 9.0%. In-hospital mortality increased with decreasing cohort size, ranging from 30.1% (explicit codes) to 14.5% (Sepsis-3 criteria). Agreement among the criteria was acceptable (Cronbach's alpha, 0.40-0.62). CONCLUSIONS: The new organ dysfunction-based Sepsis-3 criteria have been proposed as a clinical method for identifying sepsis. These criteria identified a larger, less severely ill cohort than that identified by previously used administrative definitions. The Sepsis-3 criteria have several advantages over prior methods, including less susceptibility to coding practices changes, provision of temporal context, and possession of high construct validity. However, the Sepsis-3 criteria also present new challenges, especially when calculated retrospectively. Future studies on sepsis should recognize the differences in outcome incidence among identification methods and contextualize their findings according to the different cohorts identified.

Palliative care access for hospitalized patients with end-stage liver disease across the United States.

Patients with end-stage liver disease (ESLD) often have a high symptom burden. Historically, palliative care (PC) services have been underused in this population. We investigated the use of PC services in patients with ESLD hospitalized across the United States. We used the Nationwide Inpatient Sample to conduct a retrospective nationwide cohort analysis. All patients >18 years of age admitted with ESLD, defined as those with at least two liver decompensation events, were included in the analysis. A multivariate logistic regression model predicting referral to PC was created. We analyzed 55,208,382 hospitalizations from the 2006-2012 Nationwide Inpatient Sample, with 39,349 (0.07%) patients meeting study inclusion. PC consultation was performed in 1,789 (4.5%) ESLD patients. The rate of PC referral in ESLD increased from 0.97% in 2006 to 7.1% in 2012 (P < 0.01). In multivariate analysis, factors associated with lower referral to PC were Hispanic race (odds ratio [OR], 0.77; 95% confidence interval [CI], 0.66-0.89; P < 0.01) and insurance coverage (OR, 0.74; 95% CI, 0.65-0.84; P < 0.01). Factors associated with increased referral to PC were age (per 5-year increase, OR, 1.05; 95% CI, 1.03-1.08; P < 0.01), do-not-resuscitate status (OR, 16.24; 95% CI, 14.20-18.56; P < 0.01), treatment in a teaching hospital (OR, 1.25; 95% CI, 1.12-1.39; P < 0.01), presence of hepatocellular carcinoma (OR, 2.00; 95% CI, 1.71-2.33; P < 0.01), and presence of metastatic cancer (OR, 2.39; 95% CI, 1.80-3.18; P < 0.01). PC referral was most common in west coast hospitals (OR, 1.81; 95% CI, 1.53-2.14; P < 0.01) as well as large-sized hospitals (OR, 1.49; 95% CI, 1.22-1.82; P < 0.01). CONCLUSION: From 2006 to 2012 the use of PC in ESLD patients increased substantially; socioeconomic, geographical, and ethnic barriers to accessing PC were observed. (Hepatology 2017;66:1585-1591).

Fuzzy Modeling to Predict Severely Depressed Left Ventricular Ejection Fraction following Admission to the Intensive Care Unit Using Clinical Physiology.

Left ventricular ejection fraction (LVEF) constitutes an important physiological parameter for the assessment of cardiac function, particularly in the settings of coronary artery disease and heart failure. This study explores the use of routinely and easily acquired variables in the intensive care unit (ICU) to predict severely depressed LVEF following ICU admission. A retrospective study was conducted. We extracted clinical physiological variables derived from ICU monitoring and available within the MIMIC II database and developed a fuzzy model using sequential feature selection and compared it with the conventional logistic regression (LR) model. Maximum predictive performance was observed using easily acquired ICU variables within 6 hours after admission and satisfactory predictive performance was achieved using variables acquired as early as one hour after admission. The fuzzy model is able to predict LVEF ≤ 25% with an AUC of 0.71 ± 0.07, outperforming the LR model, with an AUC of 0.67 ± 0.07. To the best of the authors' knowledge, this is the first study predicting severely impaired LVEF using multivariate analysis of routinely collected data in the ICU. We recommend inclusion of these findings into triaged management plans that balance urgency with resources and clinical status, particularly for reducing the time of echocardiographic examination.

Optimal data systems: the future of clinical predictions and decision support.

PURPOSE OF REVIEW: The purpose of the review is to describe the evolving concept and role of data as it relates to clinical predictions and decision-making. RECENT FINDINGS: Critical care medicine is, as an especially data-rich specialty, becoming acutely cognizant not only of its historic deficits in data utilization but also of its enormous potential for capturing, mining, and leveraging such data into well-designed decision support modalities as well as the formulation of robust best practices. SUMMARY: Modern electronic medical records create an opportunity to design complete and functional data systems that can support clinical care to a degree never seen before. Such systems are often referred to as 'data-driven,' but a better term is 'optimal data systems' (ODS). Here we discuss basic features of an ODS and its benefits, including the potential to transform clinical prediction and decision support.

Identifying and improving the "ground truth" of race in disparities research through improved EMR data reporting. A systematic review.

BACKGROUND: Studies about racial disparities in healthcare are increasing in quantity; however, they are subject to vast differences in definition, classification, and utilization of race/ethnicity data. Improved standardization of this information can strengthen conclusions drawn from studies using such data. The objective of this study is to examine how data related to race/ethnicity are recorded in research through examining articles on race/ethnicity health disparities and examine problems and solutions in data reporting that may impact overall data quality. METHODS: In this systematic review, Business Source Complete, Embase.com, IEEE Xplore, PubMed, Scopus and Web of Science Core Collection were searched for relevant articles published from 2000 to 2020. Search terms related to the concepts of electronic medical records, race/ethnicity, and data entry related to race/ethnicity were used. Exclusion criteria included articles not in the English language and those describing pediatric populations. Data were extracted from published articles. This review was organized and reported in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 statement for systematic reviews. FINDINGS: In this systematic review, 109 full text articles were reviewed. Weaknesses and possible solutions have been discussed in current literature, with the predominant problem and solution as follows: the electronic medical record (EMR) is vulnerable to inaccuracies and incompleteness in the methods that research staff collect this data; however, improved standardization of the collection and use of race data in patient care may help alleviate these inaccuracies. INTERPRETATION: Conclusions drawn from large datasets concerning peoples of certain race/ethnic groups should be made cautiously, and a careful review of the methodology of each publication should be considered prior to implementation in patient care.

Advancing equitable and personalized cancer care: Novel applications and priorities of artificial intelligence for fairness and inclusivity in the patient care workflow.

Patient care workflows are highly multimodal and intertwined: the intersection of data outputs provided from different disciplines and in different formats remains one of the main challenges of modern oncology. Artificial Intelligence (AI) has the potential to revolutionize the current clinical practice of oncology owing to advancements in digitalization, database expansion, computational technologies, and algorithmic innovations that facilitate discernment of complex relationships in multimodal data. Within oncology, radiation therapy (RT) represents an increasingly complex working procedure, involving many labor-intensive and operator-dependent tasks. In this context, AI has gained momentum as a powerful tool to standardize treatment performance and reduce inter-observer variability in a time-efficient manner. This review explores the hurdles associated with the development, implementation, and maintenance of AI platforms and highlights current measures in place to address them. In examining AI's role in oncology workflows, we underscore that a thorough and critical consideration of these challenges is the only way to ensure equitable and unbiased care delivery, ultimately serving patients' survival and quality of life.

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.

An intentional approach to managing bias in general purpose embedding models.

Advances in machine learning for health care have brought concerns about bias from the research community; specifically, the introduction, perpetuation, or exacerbation of care disparities. Reinforcing these concerns is the finding that medical images often reveal signals about sensitive attributes in ways that are hard to pinpoint by both algorithms and people. This finding raises a question about how to best design general purpose pretrained embeddings (GPPEs, defined as embeddings meant to support a broad array of use cases) for building downstream models that are free from particular types of bias. The downstream model should be carefully evaluated for bias, and audited and improved as appropriate. However, in our view, well intentioned attempts to prevent the upstream components-GPPEs-from learning sensitive attributes can have unintended consequences on the downstream models. Despite producing a veneer of technical neutrality, the resultant end-to-end system might still be biased or poorly performing. We present reasons, by building on previously published data, to support the reasoning that GPPEs should ideally contain as much information as the original data contain, and highlight the perils of trying to remove sensitive attributes from a GPPE. We also emphasise that downstream prediction models trained for specific tasks and settings, whether developed using GPPEs or not, should be carefully designed and evaluated to avoid bias that makes models vulnerable to issues such as distributional shift. These evaluations should be done by a diverse team, including social scientists, on a diverse cohort representing the full breadth of the patient population for which the final model is intended.

Proton-pump inhibitor use is associated with low serum magnesium concentrations.

Although case reports link proton-pump inhibitor (PPI) use and hypomagnesemia, no large-scale studies have been conducted. Here we examined the serum magnesium concentration and the likelihood of hypomagnesemia (<1.6 mg/dl) with a history of PPI or histamine-2 receptor antagonist used to reduce gastric acid, or use of neither among 11,490 consecutive adult admissions to an intensive care unit of a tertiary medical center. Of these, 2632 patients reported PPI use prior to admission, while 657 patients were using a histamine-2 receptor antagonist. PPI use was associated with 0.012 mg/dl lower adjusted serum magnesium concentration compared to users of no acid-suppressive medications, but this effect was restricted to those patients taking diuretics. Among the 3286 patients concurrently on diuretics, PPI use was associated with a significant increase of hypomagnesemia (odds ratio 1.54) and 0.028 mg/dl lower serum magnesium concentration. Among those not using diuretics, PPI use was not associated with serum magnesium levels. Histamine-2 receptor antagonist use was not significantly associated with magnesium concentration without or with diuretic use. The use of PPI was not associated with serum phosphate concentration regardless of diuretic use. Thus, we verify case reports of the association between PPI use and hypomagnesemia in those concurrently taking diuretics. Hence, serum magnesium concentrations should be followed in susceptible individuals on chronic PPI therapy.