• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• v.30 no.4
• /
• pp.145-152
• /
• 2019

Objectives: The detection of autism spectrum disorder (ASD) is based on behavioral observations. To build a more objective datadriven method for screening and diagnosing ASD, many studies have attempted to incorporate artificial intelligence (AI) technologies. Therefore, the purpose of this literature review is to summarize the studies that used AI in the assessment process and examine whether other behavioral data could potentially be used to distinguish ASD characteristics. Methods: Based on our search and exclusion criteria, we reviewed 13 studies. Results: To improve the accuracy of outcomes, AI algorithms have been used to identify items in assessment instruments that are most predictive of ASD. Creating a smaller subset and therefore reducing the lengthy evaluation process, studies have tested the efficiency of identifying individuals with ASD from those without. Other studies have examined the feasibility of using other behavioral observational features as potential supportive data. Conclusion: While previous studies have shown high accuracy, sensitivity, and specificity in classifying ASD and non-ASD individuals, there remain many challenges regarding feasibility in the real-world that need to be resolved before AI methods can be fully integrated into the healthcare system as clinical decision support systems.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.355-357
• /
• 2019

Now that we are entering an aging society, the user interface for new devices and IoT technology is very inconvenient for senior generation. To improve this, we propose an AI technology-based intelligent senior assistant voice recognition system. This system implements Cloud platform based API to accumulate data for machine learning processing, provides content for diagnosis and prevention of dementia, and provide chat-bot content for senior generation. We hope that senior generations will increase the accessibility and convenience of IoT devices and new technology devices with our system.

• Annual Conference of KIPS
• /
• 2024.10a
• /
• pp.756-759
• /
• 2024

In this study, we propose a self-supervised learning framework for fundus image processing, utilizing both contrastive and generative learning techniques for pre-training. Our contrastive learning approach integrates both image and text modalities through cross-attention mechanisms, allowing the model to learn more informative and semantically rich representations. After pre-training, the model is fine-tuned for downstream tasks, including zero-shot, few-shot, and full fine-tuning. Experimental results show that our method significantly outperforms existing approaches, achieving 15% higher performance in zero-shot, 4.5% in few-shot, and 10.1% in fine-tuning scenarios. The proposed method demonstrates its potential in the medical imaging field, where access to large annotated datasets is often limited. By efficiently leveraging both image and textual information, our approach contributes to improving the accuracy and generalizability of models in fundus image analysis, highlighting its broader applicability in medical diagnostics and healthcare.

• Journal of Biomedical Engineering Research
• /
• v.44 no.6
• /
• pp.428-442
• /
• 2023

In this study, we have a goal to develop usability evaluation guidelines for heuristic-based artificial intelligence-based Software as a Medical Device (SaMD) in the medical field. We conducted a gap analysis between medical hardware (H/W) and non-medical software (S/W) based on ten heuristic principles. Through severity assessments, we identified 69 evaluation domains and 112 evaluation criteria aligned with the ten heuristic principles. Subsequently, we categorized each evaluation domain into five types, including user safety, data integrity, regulatory compliance, patient therapeutic effectiveness, and user convenience. We proposed usability evaluation guidelines that apply the newly derived heuristic-based Software as a Medical Device (SaMD) evaluation factors to the risk management process. In the discussion, we also have proposed the potential applications of the research findings and directions for future research. We have emphasized the importance of the judicious application of AI technology in the medical field and the evaluation of usability evaluation and offered valuable guidelines for various stakeholders, including medical device manufacturers, healthcare professionals, and regulatory authorities.

• The Journal of the Korea Contents Association
• /
• v.20 no.3
• /
• pp.515-526
• /
• 2020

Digital healthcare is a combined area of medical field and IT and various information on digital healthcare is provided in social media. This study aims to find the research trend of digital healthcare by collecting and analyzing data related to digital healthcare through the social media. The data were collected from Naver and Daum's news and blogs from January 2008 to June 2019. Major keywords with high frequency were extracted and visualized with wordcloud and network analysis was used to analyze the relationship between major keywords. Research combining medical field and IT from 2008 to 2001, various convergence research based on medical field and IT from 2012 to 2015, convergence research that applied the 4th industrial revolution technologies such as big data, blockchain and AI were actively conducted from 2016 to June 2019.

• Journal of The Korean Society of Integrative Medicine
• /
• v.11 no.2
• /
• pp.1-13
• /
• 2023

Purpose : Along with the rapid development of digital technology, the application of digital healthcare in the medical field is also increasing. According to many experts, increasing the amount of exercise and physical activity is a helpful way to prevent and manage physical problems in modern society. However, a lack of exercise, which is of the lifestyle of modern people, leads to the development of various diseases. This study aimed to examine the effects of digital exercise intervention using artificial intelligence (AI) on the physical abilities of adults whether digital exercise intervention can be a reliable and effective therapeutic option for musculoskeletal disorders in real-world clinical settings. Methods : In this study, exercise was conducted using a digital application to investigate the effects of an AI-based digital exercise intervention on the physical abilities of adults. A total of 13 adults were evaluated, and their physical abilities before and after the exercise intervention were compared. Hand-grip strength, functional leg muscle strength, dynamic balance, and quadriceps muscle strength were assessed. Exercise was performed using a digital application and in a non-face-to-face manner. AI identified the exercise status of each participant and adjusted the exercise difficulty level accordingly. The exercised daily for 4 weeks. Results : A total of 12 participants were analyzed for the final results. Significant improvements were observed in hand-grip strength, functional leg muscle strength (evaluated using the stand-up test), dynamic balance, and straight-gait ability (p<.05), indicating an increase in the overall muscular strength and physical function of the participants. Conclusions : Digital exercise intervention using AI is effective in improving physical abilities related to musculoskeletal function. It can be useful in clinical practice as an effective treatment option for patients with musculoskeletal disorders or muscle weakness.

• Annual Conference of KIPS
• /
• 2024.10a
• /
• pp.461-462
• /
• 2024

In pediatric healthcare, early detection of cardiovascular diseases in newborns is crucial. Analyzing heart sounds using stethoscopes can be subjective and reliant on physician expertise, potentially leading to delayed diagnosis. There is a need for a simple method that can help even inexperienced doctors detect heart abnormalities without an electrocardiogram or ultrasound. Automated heart sound diagnosis systems can aid clinicians by providing accurate and early detection of abnormal heartbeats. To address this, we developed an intelligent deep-learning model incorporating CNN and LSTM to detect heart abnormalities based on artificial intelligence using heart sound data from stethoscope recordings. Our research achieved a high accuracy rate of 97.8%. Using audio data to introduce advanced models for cardiac abnormalities in children is essential for enhancing early detection and intervention in pediatric cardiovascular healthcare.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.19 no.1
• /
• pp.31-42
• /
• 2023

As computer performance is leveled upward, the use of IoT systems is gradually expanding. Although IoT systems are used in many fields, it is true that it is difficult to build a safe system due to performance limitations. To overcome these limitations, many researchers have proposed numerous protocols to improve security issues. Among them, Azrour et al. except. We proposed a new efficient and secure authentication protocol for remote healthcare systems in a cloud-based IoT environment, and claimed that the new protocol could solve the security vulnerabilities of the existing protocols and was more efficient. However, in this paper, through the security analysis of the remote healthcare system in the cloud-based IoT environment proposed by Azrour et al., the protocol of this system was found to be vulnerable to Masquerade attack, Lack of Perfect Forward Secrecy, Off-line password guessing attack, and Replay attack.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.4
• /
• pp.1080-1099
• /
• 2023

Digital healthcare combined with telemedicine services in the form of convergence with digital technology and AI is developing rapidly. Digital healthcare research is being conducted on many conditions including shock. However, the causes of shock are diverse, and the treatment is very complicated, requiring a high level of medical knowledge. In this paper, we propose a shock detection method based on the correlation between shock and data extracted from hemodynamic monitoring equipment. From the various parameters expressed by this equipment, four parameters closely related to patient shock were used as the input data for a machine learning model in order to detect the shock. Using the four parameters as input data, that is, feature values, a random forest-based ensemble machine learning model was constructed. The value of the mean arterial pressure was used as the correct answer value, the so called label value, to detect the patient's shock state. The performance was then compared with the decision tree and logistic regression model using a confusion matrix. The average accuracy of the random forest model was 92.80%, which shows superior performance compared to other models. We look forward to our work playing a role in helping medical staff by making recommendations for the diagnosis and treatment of complex and difficult cases of shock.

• Asia Pacific Journal of Corpus Research
• /
• v.1 no.1
• /
• pp.95-125
• /
• 2020

This paper aims to inform people how to support each other on social media. It alludes to an architecture for social media discourse and proposes a novel theory of support in social media discourse. It makes a methodological contribution. It combines predominately artificial intelligence with corpus linguistics analysis. It is on a large-scale dataset of anonymised diabetes-related user's posts from the Facebook platform. Log-likelihood and precision measures help with validation. A multi-method approach with Discourse Analysis helps in understanding any potential patterns. People living with Diabetes are found to employ sophisticated high-frequency patterns of device-enabled categories of purpose and content. It is with, for example, linguistic forms of Advice with stance-taking and targets such as Diabetes amongst other interactional ways. There can be uncertainty and variation of effect displayed when sharing information for support. The implications of the new theory aim at healthcare communicators, corpus linguists and with preliminary work for AI support-bots. These bots may be programmed to utilise the language patterns to support people who need them automatically.