Article
Multidisciplinary Sciences
Hossein Estiri, Zachary H. Strasser, Shawn N. Murphy
Summary: The development of the MLHO machine learning framework has allowed for the prediction of hospitalization, ICU admission, mechanical ventilation, and death risks in COVID-19 patients using past medical records data, demonstrating the importance of demographic and clinical variables in predicting adverse outcomes, as well as the integration of past clinical records for a reliable prediction model.
SCIENTIFIC REPORTS
(2021)
Article
Orthopedics
Monika Halicka, Martin Wilby, Rui Duarte, Christopher Brown
Summary: This study aimed to develop and externally validate prediction models of spinal surgery outcomes based on a retrospective review of a prospective clinical database, uniquely comparing multivariate regression and random forest (machine learning) approaches, and identifying the most important predictors.
BMC MUSCULOSKELETAL DISORDERS
(2023)
Article
Medicine, General & Internal
Aashish Gupta, Sergey M. Kachur, Jose D. Tafur, Harsh K. Patel, Divina O. Timme, Farnoosh Shariati, Kristen D. Rogers, Daniel P. Morin, Carl J. Lavie
Summary: This study evaluated the clinical characteristics of COVID-19 patients admitted to hospitals in the Southern United States and developed a mortality risk prediction model. The 11-factor risk model showed good performance in predicting mortality risk, with an area under the curve of 0.783. Validation in a subsequent cohort of hospitalized patients confirmed the reliability and accuracy of the model in predicting mortality risk.
MAYO CLINIC PROCEEDINGS
(2021)
Article
Endocrinology & Metabolism
Morgan E. Grams, Nigel J. Brunskill, Shoshana H. Ballew, Yingying Sang, Josef Coresh, Kunihiro Matsushita, Aditya Surapaneni, Samira Bell, Juan J. Carrero, Gabriel Chodick, Marie Evans, Hiddo J. L. Heerspink, Lesley A. Inker, Kunitoshi Iseki, Philip A. Kalra, H. Lester Kirchner, Brian J. Lee, Adeera Levin, Rupert W. Major, James Medcalf, Girish N. Nadkarni, David M. J. Naimark, Ana C. Ricardo, Simon Sawhney, Manish M. Sood, Natalie Staplin, Nikita Stempniewicz, Benedicte Stengel, Keiichi Sumida, Jamie P. Traynor, Jan van den Brand, Chi-Pang Wen, Mark Woodward, Jae Won Yang, Angela Yee-Moon Wang, Navdeep Tangri
Summary: This study aims to predict adverse kidney outcomes and improve medical management and clinical trial design. By developing and validating models using various factors, the risk of a significant decline in glomerular filtration rate or kidney failure can be successfully predicted. These models are applicable to individuals with or without diabetes, as well as those with high or low eGFR.
Article
Public, Environmental & Occupational Health
Rashid M. Ansari, Peter Baker
Summary: This study identified predictors of Covid-19 infection outcomes and developed prediction models, including factors such as total T cells and the number of infected cells in the blood. Results showed that factors like BMI, comorbidity, and specific cell types were significantly associated with infection severity, and the multivariate logistic regression model showed promise in predicting infection severity.
JOURNAL OF INFECTION AND PUBLIC HEALTH
(2021)
Article
Computer Science, Information Systems
Boran Hao, Yang Hu, Shahabeddin Sotudian, Zahra Zad, William G. Adams, Sabrina A. Assoumou, Heather Hsu, Rebecca G. Mishuris, Ioannis C. Paschalidis
Summary: This study developed predictive models for COVID-19 outcomes using a racially diverse patient population with high social needs. The models accurately predicted the severity of COVID-19, taking into account the dynamic evolution of vital signs. The study also highlighted the influence of race, social determinants of health, and hospital occupancy on the outcomes.
JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION
(2022)
Article
Sport Sciences
Lasse Ishoi, Kristian Thorborg, Thomas Kallemose, Joanne L. Kemp, Michael P. Reiman, Mathias Fabricius Nielsen, Per Holmich
Summary: This study aimed to develop and validate clinical prediction models to assist surgical decision-making in hip arthroscopy by using preoperative clinical information. The models showed acceptable accuracy in predicting the success or failure of the surgery, providing valuable information for orthopaedic surgeons and patients to determine the appropriateness of the procedure.
BRITISH JOURNAL OF SPORTS MEDICINE
(2023)
Article
Immunology
Bilgin Osmanodja, Johannes Stegbauer, Marta Kantauskaite, Lars Christian Rump, Andreas Heinzel, Roman Reindl-Schwaighofer, Rainer Oberbauer, Ilies Benotmane, Sophie Caillard, Christophe Masset, Clarisse Kerleau, Gilles Blancho, Klemens Budde, Fritz Grunow, Michael Mikhailov, Eva Schrezenmeier, Simon Ronicke
Summary: This study developed and validated prediction models for serological response to third and fourth doses of SARS-CoV-2 vaccine in kidney transplant recipients, showing good overall accuracy in guiding immunosuppressive therapy decisions.
FRONTIERS IN IMMUNOLOGY
(2022)
Article
Health Care Sciences & Services
Jiandong Zhou, Sharen Lee, Xiansong Wang, Yi Li, William Ka Kei Wu, Tong Liu, Zhidong Cao, Daniel Dajun Zeng, Keith Sai Kit Leung, Abraham Ka Chung Wai, Ian Chi Kei Wong, Bernard Man Yung Cheung, Qingpeng Zhang, Gary Tse
Summary: This study developed a simple risk score based on clinical and laboratory variables for predicting the severity of COVID-19 disease. The risk score demonstrated excellent predictive value based on test results taken on the day of admission, even without including symptoms, blood pressure or oxygen status. External validation results also confirmed the accuracy of this scoring system.
NPJ DIGITAL MEDICINE
(2021)
Article
Computer Science, Information Systems
Victor Alfonso Rodriguez, Shreyas Bhave, Ruijun Chen, Chao Pang, George Hripcsak, Soumitra Sengupta, Noemie Elhadad, Robert Green, Jason Adelman, Katherine Schlosser Metitiri, Pierre Elias, Holden Groves, Sumit Mohan, Karthik Natarajan, Adler Perotte
Summary: The study developed predictive models for COVID-19 patients to predict outcomes such as MV, RRT, and readmission, which demonstrated high performance, calibration, and interpretability. These models show potential in accurately estimating outcome prognosis for COVID-19 patients in resource-constrained care settings. Additional external validation studies are needed to confirm the generalizability of the results.
JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION
(2021)
Article
Multidisciplinary Sciences
Sam Nguyen, Ryan Chan, Jose Cadena, Braden Soper, Paul Kiszka, Lucas Womack, Mark Work, Joan M. Duggan, Steven T. Haller, Jennifer A. Hanrahan, David J. Kennedy, Deepa Mukundan, Priyadip Ray
Summary: The study developed a ML-based tool using EHR data to predict adverse outcomes in COVID-19 patients, optimizing clinical utility under a given cost structure. Results showed that it is possible to achieve a significant reduction in cost with only a small reduction in predictive performance under various budget constraints.
SCIENTIFIC REPORTS
(2021)
Article
Mathematics
Pelayo Martinez-Fernandez, Zulima Fernandez-Muniz, Ana Cernea, Juan Luis Fernandez-Martinez, Andrzej Kloczkowski
Summary: This paper compares the efficiency of Verhulst's, Gompertz's, and SIR models in describing the behavior of COVID-19 in Spain. By solving the corresponding inverse problems and inferring the posterior distributions of model parameters, the future of the pandemic is predicted using observed data from the past. The study concludes that predictive models must be accompanied by an uncertainty analysis of the corresponding inverse problem for practical decision-making.
Article
Multidisciplinary Sciences
Naichuan Su, Marie-Chris H. C. M. Donders, Jean-Pierre T. F. Ho, Valeria Vespasiano, Jan de Lange, Bruno G. Loos
Summary: This study aimed to develop and externally validate prediction models for critical outcomes of COVID-19 in unvaccinated adult patients in hospital settings. The models utilized demographics, medical conditions, and dental status as predictors, and showed good performance in both derivation and validation cohorts. The number of teeth was found to be an important predictor of critical outcomes of COVID-19.
Article
Health Care Sciences & Services
Junjun Chen, Yuelong Ji, Tao Su, Ma Jin, Zhichao Yuan, Yuanzhou Peng, Shuang Zhou, Heling Bao, Shusheng Luo, Hui Wang, Jue Liu, Na Han, Hai-Jun Wang
Summary: Prediction models developed through machine learning statistics can help identify high-risk patients with de novo hypertensive disorder of pregnancy, enabling timely intervention and care.
Article
Gastroenterology & Hepatology
Ryan C. Ungaro, Erica J. Brenner, Richard B. Gearry, Gilaad G. Kaplan, Michele Kissous-Hunt, James D. Lewis, Siew C. Ng, Jean-Francois Rahier, Walter Reinisch, Flavio Steinwurz, Fox E. Underwood, Xian Zhang, Jean-Frederic Colombel, Michael D. Kappelman
Summary: Combination therapy and thiopurines may be associated with an increased risk of severe COVID-19, while no significant differences were observed when comparing classes of biologicals. These findings warrant confirmation in large population-based cohorts.
Article
Computer Science, Artificial Intelligence
John Sperger, Nikki L. B. Freeman, Xiaotong Jiang, David Bang, Daniel de Marchi, Michael R. Kosorok
STATISTICAL ANALYSIS AND DATA MINING
(2020)
Editorial Material
Statistics & Probability
Hunyong Cho, Joshua P. Zitovsky, Xinyi Li, Minxin Lu, Kushal Shah, John Sperger, Matthew C. B. Tsilimigras, Michael R. Kosorok
STATISTICAL SCIENCE
(2020)
Article
Surgery
Jason R. Crowner, William A. Marston, Nikki L. B. Freeman, John Sperger, Haley D. Austin, Michael Steffan, Mark A. Farber, Jayer Chung, Katharine L. McGinigle
Summary: This study aims to assess whether the therapeutic goals for patients with chronic limb threatening ischemia (CLTI) can be achieved through nonoperative management alone. The study found that nonrevascularized CLTI patients had a higher risk of death but a lower risk of limb loss within two years.
ANNALS OF VASCULAR SURGERY
(2022)