Chien-Chang Chen

Dr. Chien-Chang Chen

National Kaohsiung University of Science and Technology, Kaohsiung 807618, 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
25 January 2024 in Journal of Medical Internet Research
Verified
Journal Article
Open access
YLYou-Qian Lee
You-Qian Lee
CCChing-Tai Chen
Ching-Tai Chen
CCChien-Chang Chen
Chien-Chang Chen
CLChung-Hong Lee
Chung-Hong Lee
PCPeitsz Chen
Peitsz Chen
Hong-Jie DaiHong-Jie Dai
Hong-Jie Dai
Background: The widespread use of electronic health records in the clinical and biomedical fields makes the removal of protected health information (PHI) essential to maintain privacy. However, a significant portion of information is recorded in unstructured textual forms, posing a challenge for deidentification. In multilingual countries, medical records could be written in a mixture of more than one language, referred to as code mixing. Most current clinical natural language processing techniques are designed for monolingual text, and there is a need to address the deidentification of code-mixed text. Objective: The aim of this study was to investigate the effectiveness and underlying mechanism of fine-tuned pretrained language models (PLMs) in identifying PHI in the code-mixed context. Additionally, we aimed to evaluate the potential of prompting large language models (LLMs) for recognizing PHI in a zero-shot manner. Methods: We compiled the first clinical code-mixed deidentification data set consisting of text written in Chinese and English. We explored the effectiveness of fine-tuned PLMs for recognizing PHI in code-mixed content, with a focus on whether PLMs exploit naming regularity and mention coverage to achieve superior performance, by probing the developed models’ outputs to examine their decision-making process. Furthermore, we investigated the potential of prompt-based in-context learning of LLMs for recognizing PHI in code-mixed text. Results: The developed methods were evaluated on a code-mixed deidentification corpus of 1700 discharge summaries. We observed that different PHI types had preferences in their occurrences within the different types of language-mixed sentences, and PLMs could effectively recognize PHI by exploiting the learned name regularity. However, the models may exhibit suboptimal results when regularity is weak or mentions contain unknown words that the representations cannot generate well. We also found that the availability of code-mixed training instances is essential for the model’s performance. Furthermore, the LLM-based deidentification method was a feasible and appealing approach that can be controlled and enhanced through natural language prompts. Conclusions: The study contributes to understanding the underlying mechanism of PLMs in addressing the deidentification process in the code-mixed context and highlights the significance of incorporating code-mixed training instances into the model training phase. To support the advancement of research, we created a manipulated subset of the resynthesized data set available for research purposes. Based on the compiled data set, we found that the LLM-based deidentification method is a feasible approach, but carefully crafted prompts are essential to avoid unwanted output. However, the use of such methods in the hospital setting requires careful consideration of data security and privacy concerns. Further research could explore the augmentation of PLMs and LLMs with external knowledge to improve their strength in recognizing rare PHI.

20 September 2024 in Journal of Medical Internet Research
Verified
Journal Article
Open access
Hong-Jie DaiHong-Jie Dai
Hong-Jie Dai
CWChen-Kai Wang
Chen-Kai Wang
CCChien-Chang Chen
Chien-Chang Chen
CLChong-Sin Liou
Chong-Sin Liou
ALAn-Tai Lu
An-Tai Lu
VTVincent S. Tseng
Vincent S. Tseng
Background: International Classification of Diseases codes are widely used to describe diagnosis information, but manual coding relies heavily on human interpretation, which can be expensive, time consuming, and prone to errors. With the transition from the International Classification of Diseases, Ninth Revision, to the International Classification of Diseases, Tenth Revision (ICD-10), the coding process has become more complex, highlighting the need for automated approaches to enhance coding efficiency and accuracy. Inaccurate coding can result in substantial financial losses for hospitals, and a precise assessment of outcomes generated by a natural language processing (NLP)–driven autocoding system thus assumes a critical role in safeguarding the accuracy of the Taiwan diagnosis related groups (Tw-DRGs). Objective: This study aims to evaluate the feasibility of applying an International Classification of Diseases, Tenth Revision, Clinical Modification (ICD-10-CM), autocoding system that can automatically determine diagnoses and codes based on free-text discharge summaries to facilitate the assessment of Tw-DRGs, specifically principal diagnosis and major diagnostic categories (MDCs). Methods: By using the patient discharge summaries from Kaohsiung Medical University Chung-Ho Memorial Hospital (KMUCHH) from April 2019 to December 2020 as a reference data set we developed artificial intelligence (AI)–assisted ICD-10-CM coding systems based on deep learning models. We constructed a web-based user interface for the AI-assisted coding system and deployed the system to the workflow of the certified coding specialists (CCSs) of KMUCHH. The data used for the assessment of Tw-DRGs were manually curated by a CCS with the principal diagnosis and MDC was determined from discharge summaries collected at KMUCHH from February 2023 to April 2023. Results: Both the reference data set and real hospital data were used to assess performance in determining ICD-10-CM coding, principal diagnosis, and MDC for Tw-DRGs. Among all methods, the GPT-2 (OpenAI)-based model achieved the highest F1-score, 0.667 (F1-score 0.851 for the top 50 codes), on the KMUCHH test set and a slightly lower F1-score, 0.621, in real hospital data. Cohen κ evaluation for the agreement of MDC between the models and the CCS revealed that the overall average κ value for GPT-2 (κ=0.714) was approximately 12.2 percentage points higher than that of the hierarchy attention network (κ=0.592). GPT-2 demonstrated superior agreement with the CCS across 6 categories of MDC, with an average κ value of approximately 0.869 (SD 0.033), underscoring the effectiveness of the developed AI-assisted coding system in supporting the work of CCSs. Conclusions: An NLP-driven AI-assisted coding system can assist CCSs in ICD-10-CM coding by offering coding references via a user interface, demonstrating the potential to reduce the manual workload and expedite Tw-DRG assessment. Consistency in performance affirmed the effectiveness of the system in supporting CCSs in ICD-10-CM coding and the judgment of Tw-DRGs.

16 December 2023 in The International Journal of Advanced Manufacturing Technology
Verified
Journal Article
Closed access
PDF file
CCChien-Chang Chen
Chien-Chang Chen
HDHongjie Dai
Hongjie Dai
CLChunghong Lee
Chunghong Lee
THTunghsien Hsieh
Tunghsien Hsieh
WHWeicheng Hung
Weicheng Hung
WJWenyuh Jywe
Wenyuh Jywe

3 July 2024 in IEEE Sensors Journal
Verified
Journal Article
Closed access
CCChien-Chang Chen
Chien-Chang Chen
CTCheng‐Chi Tai
Cheng‐Chi Tai
CLChan-Liang Liu
Chan-Liang Liu
A microwave nondestructive evaluation (NDE) microstrip sensor operating in C-band (from 7 GHz to 8 GHz) to measure different thickness of the copper clad laminate (CCL). The study disclosed herein was developed and designed to perform noncontact precision measurement based on the reflection of electromagnetic waves. The different electromagnetic field losses of materials under test (MUT) with varying surface copper thicknesses, the changes in electromagnetic field losses can be observed through the S11 reflection coefficient to calculate the surface copper thickness of the MUT. The microwave microstrip sensor module was designed and manufactured to receive reflected electromagnetic waves. The sensor is sensitive and can identify copper layer variations effectively. Using non-contact measurement, the sensor achieves a sensitivity and resolution of 0.1 μm at a standoff distance of 5.5 mm between the sensor and the MUT. The experimental results demonstrate that when measuring the copper foil thickness of CCL, the measurement error rate percentage is within 1% deviation compared to the four-point probe method. The study is integrated an algorithm for converting the real time online measurement results of reflected electromagnetic wave signals into the thickness of a thin copper layer, achieving the same level of measurement precision as the contact-based four-point probe measurement.

18 December 2023 in IEEE Transactions on AgriFood Electronics
Verified
Journal Article
Closed access
ICI-Te Chen
I-Te Chen
CCChien-Chang Chen
Chien-Chang Chen
Hong-Jie DaiHong-Jie Dai
Hong-Jie Dai
BRBabam Rianto
Babam Rianto
SHSi-Kai Huang
Si-Kai Huang
CLChung-Hong Lee
Chung-Hong Lee
Specialty coffee beans have a unique aroma and flavor. The aromas of coffee in the world are affected by several issues, including growing area, climate, postharvest processing (such as dry and wet methods), roasting treatment, etc. These issues significantly contribute to the development of coffee-bean aromas. Since humans have a limited ability to recognize the aroma of coffee, we need a reliable system to resolve the method of characterizing the world's coffee aroma. Therefore, in this article, we proposed an incremental learning method for digitizing the complexity of coffee aromas using an electronic nose (E-nose) system. We also developed a method to create coffee-aroma fingerprints to represent their aromatic features among different coffees. In our experiments, the incremental learning model achieved high accuracy, proving the authenticity of recognizing various world specialty coffee aromas. The approach leverages an E-nose system and coffee-aroma datasets to preserve specialty coffee aromas around the world. In addition, the ultimate goal of this method is to build a scalable database of various coffee aromas while improving the accuracy of system recognition.

21 July 2025 in IEEE Sensors Journal
Verified
Journal Article
Closed access
CCChien-Chang Chen
Chien-Chang Chen
YCYen-Kai Chu
Yen-Kai Chu
Underwater wireless charging of autonomous underwater vehicles (AUVs) is often challenged by disturbances such as ocean currents, which can lead to reduced received current and decreased charging efficiency due to coil misalignment. This paper presents a novel underwater wireless charging system that features an electromagnetic coil module with displacement compensation to enhance misalignment tolerance in dynamic and turbulent underwater environments. The proposed twin square compensation magnetic module consists of front and back compensation coils, effectively enabling compensation for forward and backward displacements within a ±60 mm range. A Hall sensor is used to indirectly measure the current by detecting the magnetic field generated, allowing real-time current estimation. Experimental results demonstrate that the compensated magnetic module receives 5.37 times more current compared to the uncompensated module. The twin square compensation magnetic module significantly mitigates current loss caused by receiver coil misalignment, with the front coil compensating for displacements from 15 mm to 60 mm, and the back coil covering -60 mm to -15 mm. Under ideal alignment conditions, the system achieves a maximum wireless charging efficiency of 91.5%. Compared to conventional uncompensated systems, the proposed design substantially improves overall charging performance. This compensation approach effectively enhances magnetic-to-electrical energy conversion during underwater wireless charging in the presence of AUV misalignment.