Journal of the Chinese Medical Association : JCMA
-
The majority of patients diagnosed with early stage endometrial cancer have a favorable prognosis; however, approximately 10% to 15% experience a recurrence. Therefore, the aim of the present study was to evaluate whether postoperative carbohydrate antigen 125 (CA-125) levels could be used to predict recurrence and recurrence-free survival (RFS) in patients with surgical stage I endometrial cancer. ⋯ In patients with stage I endometrial cancer, a postoperative CA-125 level ≥13.75 U/mL was found to be significantly correlated with a higher recurrence rate, as well as a shorter RFS. Therefore, obtaining a follow-up CA-125 level within 6 to 12 months after staging surgery may be a promising noninvasive biomarker for predicting recurrence.
-
Tumor staging is crucial for melanoma, of which acral melanoma is the predominant subtype in Asians. 18 F-fluoro-2-deoxyglucose (FDG) positron emission tomography (PET) and 18 F-FDG-PET/computed tomography ( 18 F-FDG-PET/CT) serve as noninvasive imaging tools for tumor staging. However, the literature is scarce on the diagnostic value of PET for acral melanoma. ⋯ Although noninvasive, PET/CT has relatively low sensitivity in regional lymph node evaluations, and fair sensitivity in distal metastasis detection in Asian patients with acral melanoma. Thus, PET/CT may be more useful in patients with clinically palpable nodes or more advanced disease stages.
-
Comparative Study
Comparison between linear regression and four different machine learning methods in selecting risk factors for osteoporosis in a Chinese female aged cohort.
Population aging is emerging as an increasingly acute challenge for countries around the world. One particular manifestation of this phenomenon is the impact of osteoporosis on individuals and national health systems. Previous studies of risk factors for osteoporosis were conducted using traditional statistical methods, but more recent efforts have turned to machine learning approaches. Most such efforts, however, treat the target variable (bone mineral density [BMD] or fracture rate) as a categorical one, which provides no quantitative information. The present study uses five different machine learning methods to analyze the risk factors for T-score of BMD, seeking to (1) compare the prediction accuracy between different machine learning methods and traditional multiple linear regression (MLR) and (2) rank the importance of 25 different risk factors. ⋯ In a group of women older than 55 years, we demonstrated that machine learning methods provide superior performance in estimating T-Score, with age being the most important impact factor, followed by eGFR, BMI, UA, and education level.
-
Steady-state auditory evoked responses (SSAERs) are promising indicators of major auditory function. The improvement in accessibility in the clinical setting depends on the standardization and definition of the characteristics of SSAERs. There have been some insights into the changes in the interhemispheric dominance of SSAERs in some clinical entities. However, the hemispheric asymmetry of SSAERs in healthy controls remains inconclusive. ⋯ Right-sided dominance of the SSAEFs was verified in subjects with normal hearing. Acoustic sources clinically available in audiometric tests were used as stimuli. Such a simplification of parameters would be helpful for the standardization of precise production and the definition of the characteristics of SSAERs. Because MEG is still not easily accessible clinically, further studies using electroencephalography with larger sample sizes are necessary to address these issues.