Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.cca.2015.06.014 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Autonomous International Classification of Diseases Coding Using Pretrained Language Models and Advanced Prompt Learning Techniques: Evaluation of an Automated Analysis System Using Medical Text.
JMIR Med Inform
January 2025
Medical Big Data Research Center, Chinese PLA General Hospital, Beijing, China.
Background: Machine learning models can reduce the burden on doctors by converting medical records into International Classification of Diseases (ICD) codes in real time, thereby enhancing the efficiency of diagnosis and treatment. However, it faces challenges such as small datasets, diverse writing styles, unstructured records, and the need for semimanual preprocessing. Existing approaches, such as naive Bayes, Word2Vec, and convolutional neural networks, have limitations in handling missing values and understanding the context of medical texts, leading to a high error rate.
View Article and Find Full Text PDFPatient Factors Influence Minimal Clinically Important Difference for the SNOT-22 in Medically Treated Chronic Rhinosinusitis.
Int Forum Allergy Rhinol
January 2025
Department of Otolaryngology-Head and Neck Surgery, University of Washington, Seattle, Washington, USA.
Background: The present study explores the effect of sociodemographics and comorbidities on the calculated minimal clinically important difference (MCID) for 22-item Sinonasal Outcome Test (SNOT-22) scores in patients with medically treated chronic rhinosinusitis (CRS). The importance of delineating a threshold to indicate clinically meaningful changes perceived by a patient is well acknowledged, yet the influence of patient-specific factors on MCID has not been fully elucidated.
Methods: Patients with CRS (n = 221) presenting to a tertiary care practice reported their change in disease burden with anchor questions following CRS-directed medical treatment.
Neighborhood-level deprivation mediates racial and ethnic disparities in HCC diagnosis in Texas.
Hepatol Commun
November 2024
Section of Epidemiology and Population Sciences, Department of Medicine, Baylor College of Medicine, Houston, Texas, USA.
Background: Texas has the highest HCC rates in the United States, and the greatest burden is among Hispanics. Racial and ethnic disparities in HCC incidence have multiple underpinning factors. We conducted a mediation analysis to examine the role of neighborhood disadvantage (Area Deprivation Index) as a potential mediator of the association between neighborhood race and ethnicity distribution and neighborhood HCC case counts in Texas.
View Article and Find Full Text PDFApplication of Laparoscopic Partial Splenectomy with Total Blood Flow Occlusion in Benign Splenic Lesions.
J Vis Exp
December 2024
Department of Hepatobiliary and Pancreatic-Spleen Surgery, Shunde Hospital of Southern Medical University, First People's Hospital of Shunde;
Laparoscopic partial splenectomy (LPS) is gradually becoming the preferred method for treating benign splenic lesions. However, due to the abundant blood supply and its soft, fragile tissue texture, especially when the lesion is located near the splenic hilum or is particularly large, performing partial splenectomy (PS) in clinical practice is extremely challenging. Therefore, we have been continuously exploring and optimizing hemorrhage control methods during PS, and we here propose a method to perform LPS with complete spleen blood flow occlusion.
View Article and Find Full Text PDFDiagnosis Osteoporosis Risk: Using Machine Learning Algorithms Among Fasa Adults Cohort Study (FACS).
Endocrinol Diabetes Metab
January 2025
Noncommunicable Diseases Research Center, Fasa University of Medical Sciences, Fasa, Iran.
Introduction: In Iran, the assessment of osteoporosis through tools like dual-energy X-ray absorptiometry poses significant challenges due to their high costs and limited availability, particularly in small cities and rural areas. Our objective was to employ a variety of machine learning (ML) techniques to evaluate the accuracy and precision of each method, with the aim of identifying the most accurate pattern for diagnosing the osteoporosis risks.
Methods: We analysed the data related to osteoporosis risk factors obtained from the Fasa Adults Cohort Study in eight ML methods, including logistic regression (LR), baseline LR, decision tree classifiers (DT), support vector classifiers (SVC), random forest classifiers (RF), linear discriminant analysis (LDA), K nearest neighbour classifiers (KNN) and extreme gradient boosting (XGB).
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!