KJKulsawasd Jitkajornwanich

Kulsawasd Jitkajornwanich

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Kulsawasd Jitkajornwanich has a total of 46 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Early Diagnosis of Knee Osteoarthritis With a Natural Language Processing–Driven Approach Based on Clinician Notes: Development and Validation Study

    by Narathip Thanyakunsajja, Kulsawasd Jitkajornwanich, Shan Xu, Donghee Shin, Pattama Charoenporn

    Background: Knee osteoarthritis (OA) is a common form of knee arthritis that can cause significant disability and affect a patient’s quality of life. Although this disease is chronic and irreversible, the patient’s condition can be improved and the progression of the disease can be prevented if the disease is diagnosed early and the patient receives appropriate treatment immediately. Therefore, the prediction of knee OA is considered one of the essential steps to effectively diagnose and prevent further severe OA conditions. Knee OA is commonly diagnosed by medical experts or physicians, and the diagnosis of OA is mainly based on patients’ laboratory results and medical images, including x-ray and magnetic resonance images. However, diagnosis through such data is often time-consuming. Moreover, the diagnosis results can vary among physicians depending on their expertise. Previous studies mostly focused on using approaches, such as those involving artificial intelligence, to automatically detect knee OA through such data. However, these studies did not incorporate clinicians’ or doctors’ notes (text data) into the analysis, although these data involving reported symptoms and behaviors are already available and easier to collect and access than laboratory data and image data. Objective: We propose a novel natural language processing–driven approach based on clinicians’ or doctors’ notes of patient-reported symptoms (text data only) for diagnosing knee OA. Methods: The textual information from clinicians’ or doctors’ notes was first preprocessed using text analysis algorithms with respect to natural language processing. We then incorporated deep learning models, including convolutional neural networks, bidirectional long short-term memory (BiLSTM), and gated recurrent units. Lastly, a disease-specific standard questionnaire called WOMAC (Western Ontario and McMaster Universities Arthritis Index) was taken into account to improve the overall performance of the models. Results: Our experiment included 5849 records (OA: 3455; non-OA: 2394). Before applying our WOMAC-based processing approach, the best-performing model was BiLSTM (area under the curve, 0.85; accuracy, 0.87; precision, 0.85; sensitivity, 0.95; specificity, 0.76; F1-score, 0.90), and there was an improvement in the results with BiLSTM after applying our approach (area under the curve, 0.91; accuracy, 0.91; precision, 0.91; sensitivity, 0.94; specificity, 0.87; F1-score, 0.93). Conclusions: Our proposed method for predicting the occurrence of knee OA showed better performance than other conventional methods that use image data and statistical laboratory data. The findings indicate the feasibility of using text data (symptom descriptions reported by patients and recorded by doctors) to predict knee OA. Medical notes of symptom reports can be considered a valuable data source for predicting whether a particular knee is likely to experience OA progression.


  • How Algorithms Promote Self-Radicalization: Audit of TikTok’s Algorithm Using a Reverse Engineering Method

    by Donghee Shin, Kulsawasd Jitkajornwanich

    Algorithmic radicalization is the idea that algorithms used by social media platforms push people down digital “rabbit holes” by framing personal online activity. Algorithms control what people see and when they see it and learn from their past activities. As such, people gradually and subconsciously adopt the ideas presented to them by the rabbit hole down which they have been pushed. In this study, TikTok’s role in fostering radicalized ideology is examined to offer a critical analysis of the state of radicalism and extremism on platforms. This study conducted an algorithm audit of the role of radicalizing information in social media by examining how TikTok’s algorithms are being used to radicalize, polarize, and spread extremism and societal instability. The results revealed that the pathways through which users access far-right content are manifold and that a large portion of the content can be ascribed to platform recommendations through radicalization pipelines. Algorithms are not simple tools that offer personalized services but rather contributors to radicalism, societal violence, and polarization. Such personalization processes have been instrumental in how artificial intelligence (AI) has been deployed, designed, and used to the detrimental outcomes that it has generated. Thus, the generation and adoption of extreme content on TikTok are, by and large, not only a reflection of user inputs and interactions with the platform but also the platform’s ability to slot users into specific categories and reinforce their ideas.


  • Open Access

    Early Diagnosis of Knee Osteoarthritis With a Natural Language Processing–Driven Approach Based on Clinician Notes: Development and Validation Study (Preprint)

    by Narathip Thanyakunsajja, Kulsawasd Jitkajornwanich, Shan Xu, Donghee Shin, Pattama Charoenporn

    BACKGROUND Knee osteoarthritis (OA) is a common form of knee arthritis that can cause significant disability and affect a patient’s quality of life. Although this disease is chronic and irreversible, the patient’s condition can be improved and the progression of the disease can be prevented if the disease is diagnosed early and the patient receives appropriate treatment immediately. Therefore, the prediction of knee OA is considered one of the essential steps to effectively diagnose and prevent further severe OA conditions. Knee OA is commonly diagnosed by medical experts or physicians, and the diagnosis of OA is mainly based on patients’ laboratory results and medical images, including x-ray and magnetic resonance images. However, diagnosis through such data is often time-consuming. Moreover, the diagnosis results can vary among physicians depending on their expertise. Previous studies mostly focused on using approaches, such as those involving artificial intelligence, to automatically detect knee OA through such data. However, these studies did not incorporate clinicians’ or doctors’ notes (text data) into the analysis, although these data involving reported symptoms and behaviors are already available and easier to collect and access than laboratory data and image data. OBJECTIVE We propose a novel natural language processing–driven approach based on clinicians’ or doctors’ notes of patient-reported symptoms (text data only) for diagnosing knee OA. METHODS The textual information from clinicians’ or doctors’ notes was first preprocessed using text analysis algorithms with respect to natural language processing. We then incorporated deep learning models, including convolutional neural networks, bidirectional long short-term memory (BiLSTM), and gated recurrent units. Lastly, a disease-specific standard questionnaire called WOMAC (Western Ontario and McMaster Universities Arthritis Index) was taken into account to improve the overall performance of the models. RESULTS Our experiment included 5849 records (OA: 3455; non-OA: 2394). Before applying our WOMAC-based processing approach, the best-performing model was BiLSTM (area under the curve, 0.85; accuracy, 0.87; precision, 0.85; sensitivity, 0.95; specificity, 0.76; F1-score, 0.90), and there was an improvement in the results with BiLSTM after applying our approach (area under the curve, 0.91; accuracy, 0.91; precision, 0.91; sensitivity, 0.94; specificity, 0.87; F1-score, 0.93). CONCLUSIONS Our proposed method for predicting the occurrence of knee OA showed better performance than other conventional methods that use image data and statistical laboratory data. The findings indicate the feasibility of using text data (symptom descriptions reported by patients and recorded by doctors) to predict knee OA. Medical notes of symptom reports can be considered a valuable data source for predicting whether a particular knee is likely to experience OA progression.

  • Unleashing Hidden Business Insights: Harnessing Unstructured Big Data through Text Analysis, NLP, and Visualizations for Budgetary Decisions in Governmental Organizations

    by Chanwit Kongthong, Kulsawasd Jitkajornwanich, Sarun Intakosum

    Processing Thai language texts can be a challenge due to the complexities of the language, particularly texts from social media and online platforms. This paper introduces an analysis and visualization framework specifically designed to tackle the intricacies associated with processing the Thai language data within the context of online textual content, by utilizing natural language processing (NLP) and visualization techniques. The objectives of this study were to develop an effective Thai text data analysis and visualization framework that allows us to effectively and automatically get a better understanding of the content embedded in Thai textual data. The methodology initiated with a review of existing analysis frameworks and visualization techniques with a specific focus on Thai. The data collection phase encompassed a diverse corpus of Thai text data gathered from online sources. The selected data underwent preprocessing to address language-specific challenges. The proposed Thai analysis and visualization framework consists of multiple stages. Each stage is tailored to accommodate the intricacies of the Thai language, facilitating improved information extraction and text comprehension. The proposed visualization techniques utilize interactive graphs, such as bar charts, line charts, pie charts and donut charts, to offer intuitive and insightful representations of the processed data. Results from our case study show the effectiveness of our Thai analysis framework and visualization techniques in capturing crucial information from online contents written in Thai from governmental organizations.


  • RETRACTED: Debiasing misinformation: how do people diagnose health recommendations from AI?

    by Donghee Shin, Kulsawasd Jitkajornwanich, Joon Soo Lim, Anastasia Spyridou

    Purpose: This study examined how people assess health information from AI and improve their diagnostic ability to identify health misinformation. The proposed model was designed to test a cognitive heuristic theory in misinformation discernment. Design/methodology/approach: We proposed the heuristic-systematic model to assess health misinformation processing in the algorithmic context. Using the Analysis of Moment Structure (AMOS) 26 software, we tested fairness/transparency/accountability (FAccT) as constructs that influence the heuristic evaluation and systematic discernment of misinformation by users. To test moderating and mediating effects, PROCESS Macro Model 4 was used. Findings: The effect of AI-generated misinformation on people’s perceptions of the veracity of health information may differ according to whether they process misinformation heuristically or systematically. Heuristic processing is significantly associated with the diagnosticity of misinformation. There is a greater chance that misinformation will be correctly diagnosed and checked, if misinformation aligns with users’ heuristics or is validated by the diagnosticity they perceive. Research limitations/implications: When exposed to misinformation through algorithmic recommendations, users’ perceived diagnosticity of misinformation can be predicted accurately from their understanding of normative values. This perceived diagnosticity would then positively influence the accuracy and credibility of the misinformation. Practical implications: Perceived diagnosticity exerts a key role in fostering misinformation literacy, implying that improving people’s perceptions of misinformation and AI features is an efficient way to change their misinformation behavior. Social implications: Although there is broad agreement on the need to control and combat health misinformation, the magnitude of this problem remains unknown. It is essential to understand both users’ cognitive processes when it comes to identifying health misinformation and the diffusion mechanism from which such misinformation is framed and subsequently spread. Originality/value: The mechanisms through which users process and spread misinformation have remained open-ended questions. This study provides theoretical insights and relevant recommendations that can make users and firms/institutions alike more resilient in protecting themselves from the detrimental impact of misinformation. Peer review: The peer review history for this article is available at: https://publons.com/publon/10.1108/OIR-04-2023-0167


  • Open Access

    Enhancing risk communication and environmental crisis management through satellite imagery and AI for air quality index estimation

    by Kulsawasd Jitkajornwanich, Nattadet Vijaranakul, Saichon Jaiyen, Panu Srestasathiern, Siam Lawawirojwong


  • LifeGuard: An Improvement of Actor-Critic Model with Collision Predictor in Autonomous UAV Navigation

    by Manit Chansuparp, Kulsawasd Jitkajornwanich

    The needs for autonomous unmanned aerial vehicle navigation (AUN) have been emerging for recent years due to the growth of the logistic industry and the need for social distancing during the pandemic. There have been different methods trying to overcome the AUN task, and most of them have focused on deep reinforcement learning (DRL). But the results were still far from satisfactory, and even if the result was good, the environment was usually too trivial and simple. We report in this paper one of the causes of low success rate for AUN in our previous work, which is the apprehensive behavior of agents. After numerous episodes of training, when the agent faces risky scenes, it often moves back and forth repeatedly until running out of the limited steps. Hence, in this paper, we propose a new role, LifeGuard, into the popular DRL model, Actor-Critic, to tackle the apprehensive behavior and expect a better success rate. In addition, we developed a pilot method of unsupervised classification for sequential data to further enhance our reward function from previous work, augmentative backward reward function. The experimental results demonstrated that the proposed method can eliminate the apprehensive behavior and gain higher success rates than the state-of-the-art method, FORK, with lesser effort.


  • Open Access

    A Novel Augmentative Backward Reward Function with Deep Reinforcement Learning for Autonomous UAV Navigation

    by Manit Chansuparp, Kulsawasd Jitkajornwanich

    The autonomous UAV (unmanned aerial vehicle) navigation has recently gained an increasing interest from both academic and industrial sectors due to its potential uses in various fields and especially, the need for social distancing during the pandemic. Many works have adopted a deep reinforcement learning (RL) method with experience replay called deep deterministic policy gradient (DDPG) to control the motion of UAV, and gain high accuracy results in static and simplified environments. However, they are still far from being ready for real world adoption in that the UAVs have to operate under complex and dynamic conditions. We also found that using only DDPG makes the learning process prone to oscillation and is inefficient for tasks having high dimensional action-state spaces. Furthermore, the goal reward mechanism in traditional reward functions brings a bias to the state, which resembles the one at the goal area and leads to erroneous action selection. To get closer to being ready for real world adoption, we proposed a novel method that enables UAVs to be capable of handling motion control in realistic environments. The first component of our proposed method is point cloud data (PCD) simplification with truncated icosahedron structure which converts enormous PCD into a few essential data points. In the second component of our method, we replace the traditional goal reward mechanism with a new mechanism called Augmentative Backward Reward (ABR) function to dispense the goal reward to transitions proportionately to its participation. By integrating simplified PCD and ABR, we achieved significantly better results when compared with using only the-state-of-the-art, TD3. In addition, we tested the proposed method with another navigation task, BipedalWalkerHardcore, a testbed for RL, and the result is still better and steadier than of TD3. These results indicate that the proposed method is robust.