Comparison of Patient Report and Medical Records of Comorbidities

Yu, Fan; Moon, Dominic H.; Carpenter, William R.; Reeve, Bryce B.; Usinger, Deborah S.; Green, Rebecca L.; Spearman, K.; Sheets, Nathan; Pearlstein, Kevin A.; Lucero, Angela; Waddle, Mark R.; Godley, Paul A.; Chen, Ronald C.

doi:10.1001/jamaoncol.2016.6744

Cited by 44 publications

(27 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, recent research has shown high agreement between patient self-reported co-morbidities and documentation of these conditions in the medical record. 24 Further, a similar proportion of men had specific co-morbidities based on self-report and electronic medical record. For instance, 44% of men self-reported hypertension and 44% of men had hypertension according to the electronic health record.…”

Section: Discussionmentioning

confidence: 92%

Co-morbidities in a Retrospective Cohort of Prostate Cancer Patients

et al. 2020

View full text Add to dashboard Cite

Objective: To characterize rates of co-morbidity among prostate cancer patients treated with radical prostatectomy and to examine the association between co-morbidity status and race, clinical factors, and health behaviors for cancer control.Design/Study Participants: Retrospective cohort study among prostate cancer patients treated with radical prostatectomy.Setting: Academic medical center located in the southeastern region of the United States.Main Outcome Measure: Patients with at least one of five co-morbid conditions considered were categorized as having a co-morbidity, and those without any were categorized as not having a co-morbid condition. Co-morbid conditions considered were hypertension, diabetes, heart problems, stroke, and high cholesterol, which had been recorded in the electronic medical record as part of their past medical history.Results: Fifty-one percent of participants had a co-morbidity, with hypertension being the most common. The average number of co-morbidities among study participants was .87. In a multivariate logistic regression analysis, being diagnosed with prostate cancer within the past four years was associated with an increased likelihood of having a co-morbidity (OR=4.71, 95% CI=2.69, 8.25, P=.0001) compared with diagnosis five or more years ago. Age was also associated with an increased likelihood of having a co-morbidity (OR=1.30, 95% CI=1.005, 1.68, P=.05). In this study cohort, race, stage at diagnosis, and PSA level were not statistically associated with co-morbidity status.Conclusion: Better chronic disease management is needed among prostate cancer survivors through more effective survivorship care planning and interventions that promote health behaviors.Ethn Dis. 2020;30(Suppl 1):185-192; doi:10.18865/ed.30.S1.185

show abstract

Section: Discussionmentioning

confidence: 92%

Co-morbidities in a Retrospective Cohort of Prostate Cancer Patients

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Unlike inpatient or hospital discharge records (complete coverage since 1987 58 ) or hospital-based outpatient physician visits (from 2011) which can be retrieved from the Swedish National Patient Register, primary health care data is not tracked on a national level. However, good agreement has been shown between patient-reported comorbidity events and information abstracted from medical records 59 . As with all studies using survey-based data regarding events or experiences from the past, recall error due to time and memory failure is a limitation and can bias our estimates towards the null.…”

Section: Discussionmentioning

confidence: 98%

Associations between childhood body size and seventeen adverse outcomes: analysis of 65,057 European women

Eriksson

et al. 2017

Sci Rep

View full text Add to dashboard Cite

Large childhood body size has been consistently shown to be associated with decreased breast cancer risk. However, it is important to consider the effects of a large childhood body size on other adult diseases. It is not clear if the associations between childhood body size and adult diseases will persist if they later attain healthy weight. The associations between body size at age 7 and 17 adverse outcomes in adulthood were examined using Cox models in a Swedish study of 65,057 women. Large body size at age 7, when compared to small body size, was associated with decreased risk for breast cancer (HR [95% CI]: 0.81 [0.70–0.93]) and increased risks for anorexia (2.13 [1.63–2.77]) and bulimia (1.91 [1.35–2.70]). Neither adjusting for adult BMI nor restricting the dataset to lean adults (BMI < 25 kg/m2) attenuated the associations. While large body size at age 7 by itself was positively associated with increased risks of diabetes (1.34 [1.16–1.55]), PCOS (1.69 [1.13–2.51]) and hypertension (before age 60), the associations were no longer significant after controlling for adult BMI. No clear associations were found with the remaining adverse outcomes (cervical, uterine, melanoma, colon cancer, depression, ovarian cyst, stroke, hyperlipidemia, heart failure, myocardial infarction, and angina pectoris).

show abstract

“…Conflicting evidence regarding the validity of self-reported patient data exists [85, 86]. However, a rigorous recent study concluded that patient reporting provides similar and less costly information compared with medical records [87]. Moreover, comorbidities in hospital medical records are often based on self-report as well, since clinical validation is mostly not feasible.…”

Section: Discussionmentioning

confidence: 99%

Predicting patient-reported outcomes following hip and knee replacement surgery using supervised machine learning

Huber

Kurz

Leidl

2019

BMC Med Inform Decis Mak

100

View full text Add to dashboard Cite

BackgroundMachine-learning classifiers mostly offer good predictive performance and are increasingly used to support shared decision-making in clinical practice. Focusing on performance and practicability, this study evaluates prediction of patient-reported outcomes (PROs) by eight supervised classifiers including a linear model, following hip and knee replacement surgery.MethodsNHS PRO data (130,945 observations) from April 2015 to April 2017 were used to train and test eight classifiers to predict binary postoperative improvement based on minimal important differences. Area under the receiver operating characteristic, J-statistic and several other metrics were calculated. The dependent outcomes were generic and disease-specific improvement based on the EQ-5D-3L visual analogue scale (VAS) as well as the Oxford Hip and Knee Score (Q score).ResultsThe area under the receiver operating characteristic of the best training models was around 0.87 (VAS) and 0.78 (Q score) for hip replacement, while it was around 0.86 (VAS) and 0.70 (Q score) for knee replacement surgery. Extreme gradient boosting, random forests, multistep elastic net and linear model provided the highest overall J-statistics. Based on variable importance, the most important predictors for post-operative outcomes were preoperative VAS, Q score and single Q score dimensions. Sensitivity analysis for hip replacement VAS evaluated the influence of minimal important difference, patient selection criteria as well as additional data years. Together with a small benchmark of the NHS prediction model, robustness of our results was confirmed.ConclusionsSupervised machine-learning implementations, like extreme gradient boosting, can provide better performance than linear models and should be considered, when high predictive performance is needed. Preoperative VAS, Q score and specific dimensions like limping are the most important predictors for postoperative hip and knee PROMs.Electronic supplementary materialThe online version of this article (10.1186/s12911-018-0731-6) contains supplementary material, which is available to authorized users.

show abstract

Comparison of Patient Report and Medical Records of Comorbidities

Cited by 44 publications

References 31 publications

Co-morbidities in a Retrospective Cohort of Prostate Cancer Patients

Co-morbidities in a Retrospective Cohort of Prostate Cancer Patients

Associations between childhood body size and seventeen adverse outcomes: analysis of 65,057 European women

Predicting patient-reported outcomes following hip and knee replacement surgery using supervised machine learning

Contact Info

Product

Resources

About