Multimorbidity and mortality among older patients with coronary heart disease in Shenzhen,China

BACKGROUND The current understanding of the magnitude and consequences of multimorbidity in Chinese older adults with coronary heart disease(CHD)is insufficient.We aimed to assess the association and population-attributable fractions(PAFs)between multimorbidity and mortality among hospitalized older patients who were diagnosed with CHD in Shenzhen,China.METHODS We conducted a retrospective cohort study of older Chinese patients(aged≥65 years)who were diagnosed with CHD.Cox proportional hazards models were used to estimate the associations between multimorbidity and all-cause and cardiovascular disease(CVD)mortality.We also calculated the PAFs.RESULTS The study comprised 76,455 older hospitalized patients who were diagnosed with CHD between January 1,2016,and August 31,2022.Among them,70,217(91.9%)had multimorbidity,defined as the presence of at least one of the predefined 14 chronic conditions.Those with cancer,hemorrhagic stroke and chronic liver disease had the worst overall death risk,with adjusted HRs(95%CIs)of 4.05(3.77,4.38),2.22(1.94,2.53),and 1.85(1.63,2.11),respectively.For CVD mortality,the highest risk was observed for hemorrhagic stroke,ischemic stroke,and chronic kidney disease;the corresponding adjusted HRs(95%CIs)were 3.24(2.77,3.79),1.91(1.79,2.04),and 1.81(1.64,1.99),respectively.All-cause mortality was mostly attributable to cancer,heart failure and ischemic stroke,with PAFs of 11.8,10.2,and 9.1,respectively.As for CVD mortality,the leading PAFs were heart failure,ischemic stroke and diabetes;the corresponding PAFs were 18.0,15.7,and 6.1,respectively.CONCLUSIONS Multimorbidity was common and had a significant impact on mortality among older patients with CHD in Shenzhen,China.Cancer,heart failure,ischemic stroke and diabetes are the primary contributors to PAFs.Therefore,prioritizing improved treatment and management of these comorbidities is essential for the survival prognosis of CHD patients from a holistic public health perspective.

Classification of Medical Image Notes for Image Labeling by Using MinBERT

The lack of labeled image data poses a serious challenge to the application of artificial intelligence(AI)in medical image diagnosis.Medical image notes contain valuable patient information that could be used to label images for machine learning tasks.However,most image note texts are unstructured with heterogeneity and short-paragraph characters,which fail traditional keyword-based techniques.We utilized a deep learning approach to recover missing labels for medical image notes automatically by using a combination of deep word embedding and deep neural network classifiers.Bidirectional encoder representations from transformers trained on medical image notes corpus(MinBERT)were proposed.We applied the proposed techniques to two typical classification tasks:Medical image type identification and clinical diagnosis identification.The two methods significantly outperformed baseline methods and presented high accuracies of 99.56%and 99.72%in image type identification and of 94.56%and 92.45%in clinical diagnosis identification.Visualization analysis further indicated that word embedding could efficiently capture semantic similarities and regularities across diverse expressions.Results indicated that our proposed framework could accurately recover the missing label information of medical images through the automatic extraction of electronic medical record information.Hence,it could serve as a powerful tool for exploring useful training data in various medical AI applications.