Dysarthria may present during the natural course of many degenerative neurological conditions. Hypokinetic and ataxic dysarthria are common in movement disorders and represent the underlying neuropathology. We developed an artificial intelligence (AI) model to distinguish ataxic dysarthria and hypokinetic dysarthria from normal speech and differentiate ataxic and hypokinetic speech in parkinsonian diseases and cerebellar ataxia. We screened 804 perceptual speech analyses performed in the Samsung Medical Center Neurology Department between January 2017 and December 2020. The data of patients diagnosed with parkinsonian disorders or cerebellar ataxia were included. Two speech tasks (numbering from 1 to 50 and reading nine sentences) were analyzed. We adopted convolutional neural networks and developed a patch-wise wave splitting and integrating AI system for audio classification (PWSI-AI-AC) to differentiate between ataxic and hypokinetic speech. Of the 395 speech recordings for the reading task, 76, 112, and 207 were from normal, ataxic dysarthria, and hypokinetic dysarthria subjects, respectively. Of the 409 recordings of the numbering task, 82, 111, and 216 were from normal, ataxic dysarthria, and hypokinetic dysarthria subjects, respectively. The reading and numbering task recordings were classified with 5-fold cross-validation using PWSI-AI-AC as follows: hypokinetic dysarthria vs. others (area under the curve: 0.92 ± 0.01 and 0.92 ± 0.02), ataxia vs. others (0.93 ± 0.04 and 0.89 ± 0.02), hypokinetic dysarthria vs. ataxia (0.96 ± 0.02 and 0.95 ± 0.01), hypokinetic dysarthria vs. none (0.86 ± 0.03 and 0.87 ± 0.05), and ataxia vs. none (0.87 ± 0.07 and 0.87 ± 0.09), respectively. PWSI-AI-AC showed reliable performance in differentiating ataxic and hypokinetic dysarthria and effectively augmented data to classify the types even with limited training samples. The proposed fully automatic AI system outperforms neurology residents. Our model can provide effective guidelines for screening related diseases and differential diagnosis of neurodegenerative diseases.
Objectives Mortality following percutaneous coronary intervention (PCI) is a key quality measurement in clinical practice. This study investigated the 10-year trends of mortality following PCI in an unselected nationwide cohort. Design Retrospective cohort study. Setting A nationwide study in South Korea. Participants PCI claim data from 2006 to 2015 of the National Health Insurance Service and the Statistics of Korea. Measures 1-year cardiovascular or non-cardiovascular death. Results In total, 437,436 patients were included. The annual number of PCI increased from 32,098 to 51,990 over the decade studied (p<0.001). Patients were divided into quartile subgroups according to clinical score for predicting 1-year all-cause death. The proportion of patients in the high-risk quartiles increased, whereas those in the low-risk quartiles decreased (p<0.001). The 1-year cumulative incidence rate of all-cause death did not change in the population with risk scores in the 1st (0.9% to 0.8%) and 2nd (1.3% to 1.3%) quartiles, whereas it increased in the population with risk scores in the 3rd (3.4% to 5.1%) and 4th (15.5% to 19.4%) quartiles (p<0.001). Compared to year 2006, the mean survival time in year 2015 was shorter by 0, 3.3, and 12.4 days in patients with risk scores in the 1st or 2nd, 3rd, 4th quartiles, respectively. These findings were also consistent for cardiovascular or non-cardiovascular deaths. Conclusion The number, proportion, and the overall risk of patients with a high risk for mortality after PCI increased over the decade in Korea. Funding Acknowledgement Type of funding sources: None.
Background Sex-specific survival following percutaneous coronary intervention (PCI) varies among studies. This might be clarified using relative survival, which adjusts observed survival in relation to that seen in sex- and age-matched general population. We investigated sex-specific relative survival after PCI. Methods A total of 48,783 patients were enrolled in the year 2011 Korean nationwide PCI cohort. Primary outcome was all-cause death. Observed and relative survival at 5 years conditional on surviving 0 days, 30 days, 1 year, and 2 years were assessed. Sex-specific differences in cardiovascular risk factors were adjusted via age-group stratified propensity score matching. Results In the unadjusted analyses, 15,710 female patients had a higher frequency of cardiovascular risk factors compared with 33,073 male patients. Both observed survival (hazard ratio [HR]=1.28, 95% confidence interval [CI]=1.22–1.34) and relative survival (HR=1.21, 95% CI: 1.16–1.27) were worse in female compared with male (p<0.001, all). In analyses of propensity score-matched 14,454 pairs, female showed a higher observed survival (HR=0.78, 95% CI: 0.74–0.82) but a lower relative survival (HR=1.19, 95% CI: 1.13–1.26) compared with male (p<0.001, all). Neither observed nor relative survival differed between female of age≤50s and age-matched male, but they were lower in female of age≥60s than age-matched male. These findings were consistent in further analyses conditional on surviving 30 days, 1 year, and 2 years. Conclusions The 5-year relative survival of female aged≥60 years adjusted by clinical risk factors was lower than that of age-matched male, which mandates the need for the excessive risk reduction in older female undergoing PCI. Funding Acknowledgement Type of funding sources: None.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.