China
Africa
Explore chapters and articles related to this topic
Machine Learning for Disease Classification: A Perspective
Published in Kayvan Najarian, Delaram Kahrobaei, Enrique Domínguez, Reza Soroushmehr, Artificial Intelligence in Healthcare and Medicine, 2022
Jonathan Parkinson, Jonalyn H. DeCastro, Brett Goldsmith, Kiana Aran
Ultimately, these issues combine to ensure that assembling and pre-processing healthcare datasets are necessary for predictive modeling which may incur substantial effort and expense. Even once such datasets have been assembled, they may appear to be large and yet contain data for a wide array of conditions, so that only a handful of datapoints relevant to a particular disorder or outcome of interest appear in the dataset. Adibuzzaman et al., for example, report their experience with the Medical Information Mart for Intensive Care (MIMIC III) from Beth Israel Deaconess Hospital. This superficially large dataset contains data for some 50,000 patient encounters; yet if a researcher interested in drug-drug interactions were to query it for patients on antidepressants also taking an antihistamine, for example, they would retrieve a mere 44 datapoints (Adibuzzaman et al., 2017). Finally, most healthcare datasets contain missing values such that key information available for some patients is unavailable for others (Allen et al., 2014).
Severe Electrolyte Disturbances
Published in Stephen M. Cohn, Alan Lisbon, Stephen Heard, 50 Landmark Papers, 2021
Melanie P. Hoenig, Jeffrey H. William
The authors performed a retrospective logistic regression analysis of patients who were admitted (n = 122) with severe hypernatremia (>155 mmol/L) or who acquired (n = 327) severe hyponatremia during hospitalization and the effect of rate of correction on various outcomes. Data for the years 2001–2012 were obtained from the Medical Information Mart for Intensive Care-III (MIMIC-III) which is a publicly available database from a single hospital. They found that regardless of the rate of correction (>0.5 mmol/L/h or <0.5 mmol/L/h), there was no difference in 30-day mortality. In addition, morbidities such as worsening mental status, seizures, or cerebral edema could not be attributed to rapid correction of hypernatremia.
Measurement Bias, Multiple Indicator Multiple Cause Modeling and Multiple Group Modeling
Published in Douglas D. Gunzler, Adam T. Perzynski, Adam C. Carle, Structural Equation Modeling for Health and Medicine, 2021
Douglas D. Gunzler, Adam T. Perzynski, Adam C. Carle
A limitation to using the MIMIC model as discussed thus far is that it tests for uniform DIF but not non-uniform DIF [7]. Uniform DIF is constant across a construct. Non-uniform DIF varies across the construct by levels of different groups. For example, age-based DIF may vary across a health construct for men and women. This limitation can be addressed through the MG-MIMIC model discussed later in this chapter. Different moderated models can also be used to investigate non-uniform DIF within the MIMIC framework (see for example Woods and Grimm [4] and Montoya and Jeon [5]).
The association between lactate dehydrogenase to serum albumin ratio and the 28-day mortality in patients with sepsis-associated acute kidney injury in intensive care: a retrospective cohort study
Published in Renal Failure, 2023
Minghao Liang, Xiuhong Ren, Di Huang, Zhishen Ruan, Xianhai Chen, Zhanjun Qiu
This retrospective observational study followed the guidelines set forth in Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) [13]. MIMIC-IV (Medical Information Mart for Intensive Care–IV) is a large free public database that contains comprehensive clinical information about patients at Beth Israel Deaconess Hospital, a tertiary academic medical center in Boston, Massachusetts, United States. MIMIC-IV is the result of a collaboration between Beth Israel Deaconess Medical Center and the Massachusetts Institute of Technology. The first author of this study, Minghao Liang, was enrolled in a learning program offered by the National Institutes of Health (NIH) and was granted access to the MIMIC-IV database after passing the ‘Protecting Human Research Participants’ examination (ID: 11506836). All data in this database were deidentified to remove patient information, and all of the methods used in this study were performed according to relevant guidelines and regulations. All experimental protocols were approved by the institutional review boards of Beth Israel Deaconess Medical Center (Boston, Massachusetts, United States) and the Massachusetts Institute of Technology (Cambridge, Massachusetts, United States) (Record ID: 51261101).
Development and validation of a prediction model for the early occurrence of acute kidney injury in patients with acute pancreatitis
Published in Renal Failure, 2023
Simin Wu, Qin Zhou, Yang Cai, Xiangjie Duan
AKI is a common complication of AP patients. AKI was independently associated with a higher mortality rate in AP patients [13]. Therefore, early prediction of the risk of developing AKI in acute pancreatitis may help lower the mortality rate of the disease. The MIMIC database contains a large amount of data on the clinical diagnosis and treatment of critically ill patients, thus providing data for scientific research [14]. In our study, the risk factors of early AKI in AP patients were comprehensively screened using the all-subsets regression method and multivariate logistic regression. The results indicated that age, ethnicity, Total bilirubin (TBIL), activating partial thrombin time (APTT), mechanical ventilation, vasopressor and sepsis were independent risk factors for early AKI in AP patients, which was consistent with previous studies. The constructed nomogram had a good predicting ability, was based on a large sample size obtained from the MIMIC database, and had a good clinical utility.
Explainable machine learning model for predicting furosemide responsiveness in patients with oliguric acute kidney injury
Published in Renal Failure, 2023
Meng Jiang, Chun-qiu Pan, Jian Li, Li-gang Xu, Chang-li Li
We conducted this retrospective study based on two large US-based critical care databases named Medical Information Mart for Intensive Care-IV (MIMIC-IV) [21] and eICU Collaborative Research Database (eICU-CRD) [22]. The MIMIC-IV contains comprehensive and high-quality data of 524,520 admissions (including 257,366 patients) admitted to intensive care units (ICUs) at the Beth Israel Deaconess Medical Center during 2008–2019. The eICU-CRD covered 200,859 ICU admissions (including 139,367 patients) between 2014 and 2015 at 208 US hospitals. Since the study was an analysis of publicly available database with preexisting institutional review board (IRB) approval, IRB approval was exempted by our institution. The study was reported according to the recommendations of the Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD) statement [23].