Machine learning (ML) approaches have been broadly applied to the prediction of length of stay and mortality in hospitalized patients. ML may also reduce societal health burdens, assist in health ...resources planning and improve health outcomes. However, the fairness of these ML models across ethnoracial or socioeconomic subgroups is rarely assessed or discussed. In this study, we aim (1) to quantify the algorithmic bias of ML models when predicting the probability of long-term hospitalization or in-hospital mortality for different heart failure (HF) subpopulations, and (2) to propose a novel method that can improve the fairness of our models without compromising predictive power.
We built 5 ML classifiers to predict the composite outcome of hospitalization length-of-stay and in-hospital mortality for 210 368 HF patients extracted from the Get With The Guidelines-Heart Failure registry data set. We integrated 15 social determinants of health variables, including the Social Deprivation Index and the Area Deprivation Index, into the feature space of ML models based on patients' geographies to mitigate the algorithmic bias.
The best-performing random forest model demonstrated modest predictive power but selectively underdiagnosed underserved subpopulations, for example, female, Black, and socioeconomically disadvantaged patients. The integration of social determinants of health variables can significantly improve fairness without compromising model performance.
We quantified algorithmic bias against underserved subpopulations in the prediction of the composite outcome for HF patients. We provide a potential direction to reduce disparities of ML-based predictive models by integrating social determinants of health variables. We urge fellow researchers to strongly consider ML fairness when developing predictive models for HF patients.
Machine learning is frequently being leveraged to tackle problems in the health sector including utilization for clinical decision-support. Its use has historically been focused on single modal data. ...Attempts to improve prediction and mimic the multimodal nature of clinical expert decision-making has been met in the biomedical field of machine learning by fusing disparate data. This review was conducted to summarize the current studies in this field and identify topics ripe for future research. We conducted this review in accordance with the PRISMA extension for Scoping Reviews to characterize multi-modal data fusion in health. Search strings were established and used in databases: PubMed, Google Scholar, and IEEEXplore from 2011 to 2021. A final set of 128 articles were included in the analysis. The most common health areas utilizing multi-modal methods were neurology and oncology. Early fusion was the most common data merging strategy. Notably, there was an improvement in predictive performance when using data fusion. Lacking from the papers were clear clinical deployment strategies, FDA-approval, and analysis of how using multimodal approaches from diverse sub-populations may improve biases and healthcare disparities. These findings provide a summary on multimodal data fusion as applied to health diagnosis/prognosis problems. Few papers compared the outputs of a multimodal approach with a unimodal prediction. However, those that did achieved an average increase of 6.4% in predictive accuracy. Multi-modal machine learning, while more robust in its estimations over unimodal methods, has drawbacks in its scalability and the time-consuming nature of information concatenation.
Sepsis is one of the most life-threatening circumstances for critically ill patients in the United States, while diagnosis of sepsis is challenging as a standardized criteria for sepsis ...identification is still under development. Disparities in social determinants of sepsis patients can interfere with the risk prediction performances using machine learning.
We analyzed a cohort of critical care patients from the Medical Information Mart for Intensive Care (MIMIC)-III database. Disparities in social determinants, including race, sex, marital status, insurance types and languages, among patients identified by six available sepsis criteria were revealed by forest plots with 95% confidence intervals. Sepsis patients were then identified by the Sepsis-3 criteria. Sixteen machine learning classifiers were trained to predict in-hospital mortality for sepsis patients on a training set constructed by random selection. The performance was measured by area under the receiver operating characteristic curve (AUC). The performance of the trained model was tested on the entire randomly conducted test set and each sub-population built based on each of the following social determinants: race, sex, marital status, insurance type, and language. The fluctuations in performances were further examined by permutation tests.
We analyzed a total of 11,791 critical care patients from the MIMIC-III database. Within the population identified by each sepsis identification method, significant differences were observed among sub-populations regarding race, marital status, insurance type, and language. On the 5783 sepsis patients identified by the Sepsis-3 criteria statistically significant performance decreases for mortality prediction were observed when applying the trained machine learning model on Asian and Hispanic patients, as well as the Spanish-speaking patients. With pairwise comparison, we detected performance discrepancies in mortality prediction between Asian and White patients, Asians and patients of other races, as well as English-speaking and Spanish-speaking patients.
Disparities in proportions of patients identified by various sepsis criteria were detected among the different social determinant groups. The performances of mortality prediction for sepsis patients can be compromised when applying a universally trained model for each subpopulation. To achieve accurate diagnosis, a versatile diagnostic system for sepsis is needed to overcome the social determinant disparities of patients.
In the U.S. inpatient payment system, the Diagnosis-Related Group (DRG) is pivotal, but its assignment process is inefficient. The study introduces DRG-LLaMA, an advanced large language model (LLM) ...fine-tuned on clinical notes to enhance DRGs assignment. Utilizing LLaMA as the foundational model and optimizing it through Low-Rank Adaptation (LoRA) on 236,192 MIMIC-IV discharge summaries, our DRG-LLaMA -7B model exhibited a noteworthy macro-averaged F1 score of 0.327, a top-1 prediction accuracy of 52.0%, and a macro-averaged Area Under the Curve (AUC) of 0.986, with a maximum input token length of 512. This model surpassed the performance of prior leading models in DRG prediction, showing a relative improvement of 40.3% and 35.7% in macro-averaged F1 score compared to ClinicalBERT and CAML, respectively. Applied to base DRG and complication or comorbidity (CC)/major complication or comorbidity (MCC) prediction, DRG-LLaMA achieved a top-1 prediction accuracy of 67.8% and 67.5%, respectively. Additionally, our findings indicate that DRG-LLaMA 's performance correlates with increased model parameters and input context lengths.
Abstract
Background
Appropriate use of available inpatient beds is an ongoing challenge for US hospitals. Historical capacity goals of 80% to 85% may no longer serve the intended purpose of ...maximizing the resources of space, staff, and equipment. Numerous variables affect the input, throughput, and output of a hospital. Some of these variables include patient demand, regulatory requirements, coordination of patient flow between various systems, coordination of processes such as bed management and patient transfers, and the diversity of departments (both inpatient and outpatient) in an organization.
Methods
Mayo Clinic Health System in the Southwest Minnesota region of the US, a community-based hospital system primarily serving patients in rural southwestern Minnesota and part of Iowa, consists of 2 postacute care and 3 critical access hospitals. Our inpatient bed usage rates had exceeded 85%, and patient transfers from the region to other hospitals in the state (including Mayo Clinic in Rochester, Minnesota) had increased. To address these quality gaps, we used a blend of Agile project management methodology, rapid Plan-Do-Study-Act cycles, and a proactive approach to patient placement in the medical-surgical units as a quality improvement initiative.
Results
During 2 trial periods of the initiative, the main hub hospital (Mayo Clinic Health System hospital in Mankato) and other hospitals in the region increased inpatient bed usage while reducing total out-of-region transfers.
Conclusion
Our novel approach to proactively managing bed capacity in the hospital allowed the region’s only tertiary medical center to increase capacity for more complex and acute cases by optimizing the use of historically underused partner hospital beds.
Deoxynivalenol (DON) belongs to the type B group of trichothecenes family, which is composed of sesquiterpenoid metabolites produced by Fusarium and other fungi in grain. DON may cause various ...toxicities, such as cytotoxicity, immunotoxicity, genotoxicity as well as teratogenicity and carcinogenicity. In the present study, we focus on a hypothesis that DON alters the expressions of Nrf2/HO-1 pathway by inducing embryotoxicity in C57BL/6 mouse (5.0, 2.5, 1.0, and 0 mg/kg/day) and BeWo cell lines (0 and 50 nM; 3 h, 12 h and 24 h). Our results indicate that DON treatment in mice during pregnancy leads to ROS accumulation in the placenta, which results in embryotoxicity. At the same time Nrf2/HO-1 pathway is up-regulated by ROS to protect placenta cells from oxidative damage. In DON-treated BeWo cells, the level of ROS has time-effect and dose-effect relationships with HO-1 expression. Moderate increase in HO-1 protects the cell from oxidative damage, while excessive increase in HO-1 aggravates the oxidative damage, which is called in some studies the "threshold effect". Therefore, oxidative stress may be the critical molecular mechanism for DON-induced embryotoxicity. Besides, Nrf2/HO-1 pathway accompanied by the "threshold effect" also plays an important role against DON-induced oxidative damage in this process.
The value of combination therapy for refractory ITP is not well defined. We present the case of a 29-year-old male with severe ITP refractory to initial standard therapy including steroids, IVIG, and ...subsequent splenectomy, who was treated with the combination therapy of rituximab, romiplostim, and mycophenolate and eventually developed thrombocytosis requiring plateletpheresis. Our case highlights the importance of the need to understand predictors of response to standard upfront treatment of acute ITP.
BackgroundAcute blood pressure (BP) reduction is standard of care after acute intracerebral haemorrhage (ICH). More acute BP reduction is associated with acute kidney injury (AKI). It is not known if ...the choice of antihypertensive medications affects the risk of AKI.MethodsWe analysed data from the ATACH-II clinical trial. AKI was defined by the Kidney Disease: Improving Global Outcomes criteria. We analysed antihypertensive medication from two sources. The first was a case report form that specified the use of labetalol, diltiazem, urapidil or other. We tested the hypothesis that the secondary medication was associated with AKI with χ2 test. Second, we tested the hypotheses the dosage of diltiazem was associated with AKI using Mann-Whitney U test.ResultsAKI occurred in 109 of 1000 patients (10.9%). A higher proportion of patients with AKI received diltiazem after nicardipine (12 (29%) vs 21 (12%), p=0.03). The 95%ile (90%–99% ile) of administered diltiazem was 18 (0–130) mg in patients with AKI vs 0 (0–30) mg in patients without AKI (p=0.002). There was no apparent confounding by indication for diltiazem use.ConclusionsThe use of diltiazem, and more diltiazem, was associated with AKI in patients with acute ICH.
The emergence of SARS-CoV-2 (ie, COVID-19) has given rise to a global pandemic affecting 215 countries and over 40 million people as of October 2020. Meanwhile, we are also experiencing an infodemic ...induced by the overabundance of information, some accurate and some inaccurate, spreading rapidly across social media platforms. Social media has arguably shifted the information acquisition and dissemination of a considerably large population of internet users toward higher interactivities.
This study aimed to investigate COVID-19-related health beliefs on one of the mainstream social media platforms, Twitter, as well as potential impacting factors associated with fluctuations in health beliefs on social media.
We used COVID-19-related posts from the mainstream social media platform Twitter to monitor health beliefs. A total of 92,687,660 tweets corresponding to 8,967,986 unique users from January 6 to June 21, 2020, were retrieved. To quantify health beliefs, we employed the health belief model (HBM) with four core constructs: perceived susceptibility, perceived severity, perceived benefits, and perceived barriers. We utilized natural language processing and machine learning techniques to automate the process of judging the conformity of each tweet with each of the four HBM constructs. A total of 5000 tweets were manually annotated for training the machine learning architectures.
The machine learning classifiers yielded areas under the receiver operating characteristic curves over 0.86 for the classification of all four HBM constructs. Our analyses revealed a basic reproduction number R
of 7.62 for trends in the number of Twitter users posting health belief-related content over the study period. The fluctuations in the number of health belief-related tweets could reflect dynamics in case and death statistics, systematic interventions, and public events. Specifically, we observed that scientific events, such as scientific publications, and nonscientific events, such as politicians' speeches, were comparable in their ability to influence health belief trends on social media through a Kruskal-Wallis test (P=.78 and P=.92 for perceived benefits and perceived barriers, respectively).
As an analogy of the classic epidemiology model where an infection is considered to be spreading in a population with an R
greater than 1, we found that the number of users tweeting about COVID-19 health beliefs was amplifying in an epidemic manner and could partially intensify the infodemic. It is "unhealthy" that both scientific and nonscientific events constitute no disparity in impacting the health belief trends on Twitter, since nonscientific events, such as politicians' speeches, might not be endorsed by substantial evidence and could sometimes be misleading.