The increase in total knee replacement surgery in Taiwan: A 15-year retrospective study.

Total knee replacement (TKR) is considered as one of the most success among clinical interventions for patients with who suffering from knee osteoarthritis (OA). We sought to estimate the incidence of TKR using demographics, incidence rates, lengths of hospital stay, and costs from 1996 to 2010 by analyzing Taiwan's National Health Insurance Research Database. A total of 154,553 patients obtained primary TKR surgery between 1996 and 2010. The diagnosis code for knee OA and the procedure code for TKR were selected from the records. To compare the rate of TKR between covariables, we calculated the TKR risk ratios and 95% confidence interval (CI) of these variables (gender, age, age group, and primary diagnoses). A 2-tailed P-value of .05 was considered statistically significant. The statistical package SPSS version 20.0 (SPSS, Chicago, IL) was used to conduct all the statistical analyzes. We analyzed 154,553 TKRs performed by surgeons in Taiwan from 1996 to 2010. The overall crude incidence increased from 26.4 to 74.55 TKR per 100,000 inhabitants from 1996 to 2010. TKR incidence for the 70 to 79 years age group increased from 227 to 505 per 100,000 people from 1996 to 2010. The age-standardized rate ratios for TKR of women to men ranged from 2.5 to 3.0. The mean average length of stay in hospital was 15 days in 1996 and decreased to 8 days in 2010. During the study period, the adjusted mean cost per patient decreased from US$7485 to US$4827. Health expenditures for TKR were 5% of total National Health Insurance expenditure every year. Over the 15-year period, Taiwan's TKR incidence tripled, which is consistent with population ageing. Arthritis will be a major public health issue in the ageing population in the future.

No difference in the functional improvements between unilateral and bilateral total knee replacements.

BACKGROUND: Differences between staged bilateral total knee replacement (TKR) and simultaneous bilateral TKR have been investigated, but few studies have investigated differences in the functional improvements resulting from these methods. Therefore, this study investigates the different functional improvements between staged bilateral total knee TKR and simultaneous bilateral TKR. METHODS: Among 144 potential bilateral TKR patients who were included in this study, 93 (64.6%) patients selected unilateral TKR and 51 (35.4%) selected bilateral TKR. Functional improvements were assessed using the Western Ontario and McMaster University osteoarthritis index (WOMAC) and the Medical Outcomes Trust Short Form-36 (SF-36), and patients were interviewed pre-operatively and after 6 months. A generalized equation was used to test for differences in functional improvements. RESULTS: After TKR, pain, stiffness, function and total WOMAC scores were significantly reduced in both groups, with mean changes from - 26.6 to - 41.4 and from - 27.5 to - 42.2.The mean health change of SF-36 scores, physical component and mental component scores changed to 45.2 ± 18.2, 74.0 ± 15.4 and 77.0 ± 9.6, respectively, in Group 1 and 47.1 ± 17.1, 74.0 ± 15.2 and 75.5 ± 12.1, respectively, in Group 2. Unilateral and simultaneous bilateral TKR produce similar functional improvements, although current work status may be a novel impact factor. CONCLUSION: No differences in functional improvements were identified between patients who selected unilateral versus bilateral TKR, indicating no recommendation for one procedure over the other.

Artificial Intelligence Learning Semantics via External Resources for Classifying Diagnosis Codes in Discharge Notes.

BACKGROUND: Automated disease code classification using free-text medical information is important for public health surveillance. However, traditional natural language processing (NLP) pipelines are limited, so we propose a method combining word embedding with a convolutional neural network (CNN). OBJECTIVE: Our objective was to compare the performance of traditional pipelines (NLP plus supervised machine learning models) with that of word embedding combined with a CNN in conducting a classification task identifying International Classification of Diseases, Tenth Revision, Clinical Modification (ICD-10-CM) diagnosis codes in discharge notes. METHODS: We used 2 classification methods: (1) extracting from discharge notes some features (terms, n-gram phrases, and SNOMED CT categories) that we used to train a set of supervised machine learning models (support vector machine, random forests, and gradient boosting machine), and (2) building a feature matrix, by a pretrained word embedding model, that we used to train a CNN. We used these methods to identify the chapter-level ICD-10-CM diagnosis codes in a set of discharge notes. We conducted the evaluation using 103,390 discharge notes covering patients hospitalized from June 1, 2015 to January 31, 2017 in the Tri-Service General Hospital in Taipei, Taiwan. We used the receiver operating characteristic curve as an evaluation measure, and calculated the area under the curve (AUC) and F-measure as the global measure of effectiveness. RESULTS: In 5-fold cross-validation tests, our method had a higher testing accuracy (mean AUC 0.9696; mean F-measure 0.9086) than traditional NLP-based approaches (mean AUC range 0.8183-0.9571; mean F-measure range 0.5050-0.8739). A real-world simulation that split the training sample and the testing sample by date verified this result (mean AUC 0.9645; mean F-measure 0.9003 using the proposed method). Further analysis showed that the convolutional layers of the CNN effectively identified a large number of keywords and automatically extracted enough concepts to predict the diagnosis codes. CONCLUSIONS: Word embedding combined with a CNN showed outstanding performance compared with traditional methods, needing very little data preprocessing. This shows that future studies will not be limited by incomplete dictionaries. A large amount of unstructured information from free-text medical writing will be extracted by automated approaches in the future, and we believe that the health care field is about to enter the age of big data.

Angiotensin II receptor type 1 A1166C modifies the association between angiotensinogen M235T and chronic kidney disease.

Single nucleotide polymorphisms (SNPs) in renin-angiotensin system (RAS) genes are associated with RAS imbalance and chronic kidney disease (CKD). We performed a case-control study and meta-analysis to investigate the association between angiotensinogen (AGT) M235T polymorphism and CKD. A total of 634 patients with end-stage renal disease and 739 healthy controls were studied. We also searched PubMed and the Cochrane Library to identify prospective observational studies published before December 2015. We found that the TT and MT genotypes were associated with a higher risk of CKD than the MM genotype (odds ratio [OR]: 3.56; 95% confidence interval [CI]: 1.14-11.16 and OR: 2.93; 95% CI: 0.91-9.46, respectively). Thirty-eight study populations were included in the meta-analysis. The T allele was associated with a higher risk of CKD than the M allele in all populations (OR: 1.19; 95% CI: 1.08-1.32). The OR was 1.33 in Asians (95% CI: 1.06-1.67) and 1.10 in Caucasians (95% CI: 1.02-1.18). Evaluation of gene-gene and gene-environment interactions using epistasis analysis revealed an interaction between AGT M235T and angiotensin II receptor type 1 A1166C in CKD (OR: 0.767; 95% CI: 0.609-0.965). Genetic testing for CKD in high-risk individuals may be an effective strategy for CKD prevention.