Chien-Chen Chou

Chien-Chen Chou

Auto-generated profile, based on publicly available information

Chien-Chen Chou

Department of Neurology, Neurological Institute Taipei Veterans General Hospital Taipei Taiwan

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 November 2023 in Mayo Clinic Proceedings: Digital Health
Verified
Journal Article
Open access
JHJen-Cheng Hou
Jen-Cheng Hou
CLChin-Jou Li
Chin-Jou Li
CCChien-Chen Chou
Chien-Chen Chou
YSYen-Cheng Shih
Yen-Cheng Shih
SFSi-Lei Fong
Si-Lei Fong
HYHsiang-Yu Yu
Hsiang-Yu Yu
To investigate the feasibility and accuracy of artificial intelligence (AI) methods of facial deidentification in hospital-recorded epileptic seizure videos, for improved patient privacy protection while preserving clinically important features of seizure semiology. Videos of epileptic seizures displaying seizure-related involuntary facial changes were selected from recordings at Taipei Veterans General Hospital Epilepsy Unit (between August 1, 2020 and February 28, 2023), and a single representative video frame was prepared per seizure. We tested 3 AI transformation models: (1) morphing the original facial image with a different male face; (2) substitution with a female face; and (3) cartoonization. Facial deidentification and preservation of clinically relevant facial detail were calculated based on: (1) scoring by 5 independent expert clinicians and (2) objective computation. According to the clinician scoring of 26 facial frames in 16 patients, the best compromise between deidentification and preservation of facial semiology was the cartoonization model. A male facial morphing model was superior to the cartoonization model for deidentification, but clinical detail was sacrificed. Objective similarity testing of video data reported deidentification scores in agreement with the clinicians’ scores; however, preservation of semiology gave mixed results likely due to inadequate existing comparative databases. Artificial intelligence-based face transformation of medical seizure videos is feasible and may be useful for patient privacy protection. In our study, the cartoonization approach provided the best compromise between deidentification and preservation of seizure semiology.

1 August 2026 in Epilepsia
Verified
Journal Article
Open access
PDF file
CCChien‐Chen Chou
Chien‐Chen Chou
YSYen‐Cheng Shih
Yen‐Cheng Shih
YCYi‐Hsiu Chen
Yi‐Hsiu Chen
PLPo‐Tso Lin
Po‐Tso Lin
CLChun‐Fu Lin
Chun‐Fu Lin
HYHsiang‐Yu Yu
Hsiang‐Yu Yu
Objective: This study was undertaken to evaluate the safety, feasibility, and efficacy of low‐intensity focused ultrasound (LIFU) as a noninvasive neuromodulation technique in patients with drug‐resistant epilepsy (DRE). Methods: In this pilot, single‐blind, randomized sham‐controlled crossover trial, 12 patients with DRE underwent both LIFU and sham stimulation in a randomized sequence, targeting the seizure onset zone (SOZ), each followed by a 4‐week observation period. Seizure frequency was analyzed as proportional change from baseline using linear mixed‐effects models. An open‐label extension phase evaluated longitudinal seizure outcomes following LIFU. Safety assessments included neurological examinations, magnetic resonance imaging (MRI), and neuropsychological and quality of life (QOL) measures. Results: During the crossover phase, LIFU did not significantly reduce seizure frequency compared with sham (estimate = .49, 95% confidence interval [CI] = −.04 to 1.01, p = .068). No period or sequence effects were observed. Conversely, during the open‐label extension phase, seizure frequency demonstrated a significant longitudinal reduction following LIFU (β = −14.0 percentage points per month, 95% CI = −22.2 to −5.8, p = .001). Post‐LIFU MRI showed no structural lesions. No significant changes were observed in anxiety, depression, or QOL scores. There were only transient mild‐to‐moderate adverse events reported, without serious complications. Significance: LIFU neuromodulation targeting the SOZ is safe and well tolerated. Although the primary crossover analysis did not demonstrate a statistically significant antiseizure effect, delayed seizure reduction during the extended follow‐up suggests potential sustained neuromodulatory effects. Larger parallel‐group trials with longer observation periods are warranted.