BACKGROUND The use of machine learning(ML)to predict colonoscopy procedure duration has not been examined.AIM To assess if ML and data available at the time a colonoscopy procedure is scheduled could be used to estima...BACKGROUND The use of machine learning(ML)to predict colonoscopy procedure duration has not been examined.AIM To assess if ML and data available at the time a colonoscopy procedure is scheduled could be used to estimate procedure duration more accurately than the current practice.METHODS Total 40168 colonoscopies from the Clinical Outcomes Research Initiative database were collected.ML models predicting procedure duration were developed using data available at time of scheduling.The top performing model was compared against historical practice.Models were evaluated based on accuracy(prediction–actual time)±5,10,and 15 min.RESULTS ML outperformed historical practice with 77.1%to 68.9%,87.3%to 79.6%,and 92.1%to 86.8%accuracy at 5,10 and 15 min thresholds.CONCLUSION The use of ML to estimate colonoscopy procedure duration may lead to more accurate scheduling.展开更多
Background:Despite a growing population of patients starting hemodialysis in China,little is known about markers of mineral bone disease(MBD)and their management.We present data on prevalence and correlates of hypocal...Background:Despite a growing population of patients starting hemodialysis in China,little is known about markers of mineral bone disease(MBD)and their management.We present data on prevalence and correlates of hypocalcemia,hyperphosphatemia,and secondary hyperparathyroidism from the China Dialysis Outcomes and Practice Patterns Study(DOPPS),with evaluation of whether these laboratory markers triggered changes in management.Methods:We compared the frequency of measurement and prevalence of poor control of MBD markers in China DOPPS with other DOPPS regions.We also used generalized estimating equations to assess correlates of MBD markers,and separate models to assess predictors of vitamin D and phosphate binder prescriptions in the China DOPPS.Results:Severe hyperphosphatemia(>7 mg/dL)and secondary hyperparathyroidism(>600 pg/mL)were common(27%and 21%prevalence,respectively);both were measured infrequently(14.9%and 3.2%of patients received monthly measurements in China).Frequency of dialysis sessions was positively associated with hyperphosphatemia;presence of residual kidney function was negatively associated with both hyperphosphatemia and secondary hyperparathyroidism.Laboratory measures indicating poor control of MBD were not associated with subsequent prescription of active vitamin D or phosphate binder.Conclusions:There are substantial opportunities for improvement and standardization of MBD management in China.Development of country-specific guidelines may yield realistic targets and standardization of medication use accounting for availability and cost.展开更多
文摘BACKGROUND The use of machine learning(ML)to predict colonoscopy procedure duration has not been examined.AIM To assess if ML and data available at the time a colonoscopy procedure is scheduled could be used to estimate procedure duration more accurately than the current practice.METHODS Total 40168 colonoscopies from the Clinical Outcomes Research Initiative database were collected.ML models predicting procedure duration were developed using data available at time of scheduling.The top performing model was compared against historical practice.Models were evaluated based on accuracy(prediction–actual time)±5,10,and 15 min.RESULTS ML outperformed historical practice with 77.1%to 68.9%,87.3%to 79.6%,and 92.1%to 86.8%accuracy at 5,10 and 15 min thresholds.CONCLUSION The use of ML to estimate colonoscopy procedure duration may lead to more accurate scheduling.
基金This work was supported by grants from the Global support for the ongoing DOPPS Programs without restriction on publications by a variety of funders(For details see https://www.dopps.org/AboutUs/Support.aspx)Dr.Shuchi Anand is supported by U.S.National Institute of Diabetes,and Digestive and Kidney Diseases(No.NIDDK K-235K23DK101826-03)Dr.Jun Wang is supported by the National Natural Science Foundation of China(No.81470972).
文摘Background:Despite a growing population of patients starting hemodialysis in China,little is known about markers of mineral bone disease(MBD)and their management.We present data on prevalence and correlates of hypocalcemia,hyperphosphatemia,and secondary hyperparathyroidism from the China Dialysis Outcomes and Practice Patterns Study(DOPPS),with evaluation of whether these laboratory markers triggered changes in management.Methods:We compared the frequency of measurement and prevalence of poor control of MBD markers in China DOPPS with other DOPPS regions.We also used generalized estimating equations to assess correlates of MBD markers,and separate models to assess predictors of vitamin D and phosphate binder prescriptions in the China DOPPS.Results:Severe hyperphosphatemia(>7 mg/dL)and secondary hyperparathyroidism(>600 pg/mL)were common(27%and 21%prevalence,respectively);both were measured infrequently(14.9%and 3.2%of patients received monthly measurements in China).Frequency of dialysis sessions was positively associated with hyperphosphatemia;presence of residual kidney function was negatively associated with both hyperphosphatemia and secondary hyperparathyroidism.Laboratory measures indicating poor control of MBD were not associated with subsequent prescription of active vitamin D or phosphate binder.Conclusions:There are substantial opportunities for improvement and standardization of MBD management in China.Development of country-specific guidelines may yield realistic targets and standardization of medication use accounting for availability and cost.