• Korean Medical Education Review
• /
• v.18 no.2
• /
• pp.51-57
• /
• 2016

This literature review explores artificial intelligence (AI) technology trends and IBM Watson health and medical references. This study explains how healthcare will be changed by the evolution of AI technology, and also summarizes key technologies in AI, specifically the technology of IBM Watson. We look at this issue from the perspective of 'information overload,' in that medical literature doubles every three years, with approximately 700,000 new scientific articles being published every year, in addition to the explosion of patient data. Estimates are also forecasting a shortage of oncologists, with the demand expected to grow by 42%. Due to this projected shortage, physicians won't likely be able to explore the best treatment options for patients in clinical trials. This issue can be addressed by the AI Watson motivation to solve healthcare industry issues. In addition, the Watson Oncology solution is reviewed from the end user interface point of view. This study also investigates global company platform business to explain how AI and machine learning technology are expanding in the market with use cases. It emphasizes ecosystem partner business models that can support startup and venture businesses including healthcare models. Finally, we identify a need for healthcare company partnerships to be reviewed from the aspect of solution transformation. AI and Watson will change a lot in the healthcare business. This study addresses what we need to prepare for AI, Cognitive Era those are understanding of AI innovation, Cloud Platform business, the importance of data sets, and needs for further enhancement in our knowledge base.

• Korean Journal of Clinical Pharmacy
• /
• v.33 no.3
• /
• pp.168-177
• /
• 2023

Background & Objectives: Fixed-dose combinations (FDCs) offer advantages in adherence and cost-effectiveness compared to free combinations (FCs), but they can also complicate the prescribing process, potentially leading to therapeutic duplication (TD). This study aimed to identify the prescribing patterns of FDCs for dyslipidemia and investigate their associated risk of TD. Methods: This was a retrospective cohort study involving drugs that included statins, using Health Insurance Review & Assessment Service-National Patient Sample (HIRA-NPS) data from 2018. The unit of analysis was a prescription claim. The primary outcome was TD. The risk ratio of TD was calculated and adjusted for patient, prescriber, and the number of cardiovascular drugs prescribed using a multivariable Poisson model. Results: Our study included 252,797 FDC prescriptions and 515,666 FC prescriptions. Of the FDC group, 46.52% were male patients and 56.21% were aged 41 to 65. Ezetimibe was included in 71.61% of the FDC group, but only 0.25% of the FC group. TD occurred in 0.18% of the FDC group, and the adjusted risk ratio of TD in FDC prescriptions compared to FC was 6. 44 (95% CI 5. 30-7. 82). Conclusions: Prescribing FDCs for dyslipidemia was associated with a higher risk of TD compared to free combinations. Despite the relatively low absolute prevalence of TD, the findings underline the necessity for strategies to mitigate this risk when prescribing FDCs for dyslipidemia. Our study suggests the potential utility of Clinical Decision Support Systems and standardizing nomenclature in reducing medication errors, providing valuable insights for clinical practice and future research.

• KIISE Transactions on Computing Practices
• /
• v.21 no.7
• /
• pp.464-469
• /
• 2015

Long-term electrocardiogram data can be acquired by linking a Holter monitor to a mobile phone. However, most systems are designed to detect arrhythmia through heartbeat classification, and not just for supporting clinical decisions. In this paper, we propose an Abstracting algorithm, and introduce an analogous pateint search system using this algorithm. An analogous patient searcher summarizes each patient's typical pattern using the results of heartbeat, which can greatly simplify clinical activity. It helps to find patients with similar arrhythmia patterns, which can help in contributing to diagnostic clues. We have simulated these processes on data from the MIT-BIH arrhythmia database. As a result, the Abstracting algorithm provided a typical pattern to assist in reaching rapid clinical decisions for 64% of the patients. On an average, typical patterns and results generated by the abstracting algorithm summarized the results of heartbeat classification by 98.01%.

• 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.

• Journal of Intelligence and Information Systems
• /
• v.11 no.1
• /
• pp.17-33
• /
• 2005

This paper presents the proposed a classifier of liver cirrhotic step using MR(magnetic resonance) imaging and hierarchical neural network. The data sets for classification of each stage, which were normal, 1type, 2type and 3type, were analysis in the number of data was 231. We extracted liver region and nodule region from T1-weight MR liver image. Then objective interpretation classifier of liver cirrhotic steps. Liver cirrhosis classifier implemented using hierarchical neural network which gray-level analysis and texture feature descriptors to distinguish normal liver and 3 types of liver cirrhosis. Then proposed Neural network classifier learned through error back-propagation algorithm. A classifying result shows that recognition rate of normal is $100\%$, 1type is $82.8\%$, 2type is $87.1\%$, 3type is $84.2\%$. The recognition ratio very high, when compared between the result of obtained quantified data to that of doctors decision data and neural network classifier value. If enough data is offered and other parameter is considered this paper according to we expected that neural network as well as human experts and could be useful as clinical decision support tool for liver cirrhosis patients.

• Quality Improvement in Health Care
• /
• v.22 no.2
• /
• pp.43-73
• /
• 2016

Purpose: The aims of this study were to assess the presence of core patient safety practices in Korean hospitals and assess the differences in reporting and learning systems of patient safety, infrastructure, and safe practices by hospital characteristics. Methods: The authors developed a questionnaire including 39 items of patient safety staffing, health information system, reporting system, and event-specific prevention practices. The survey was conducted online or e-mail with 407 tertiary, general and specialty hospitals. Results: About 90% of hospitals answered the self-reporting system of patient safety related events is established. More than 90% of hospitals applied incidence monitoring or root cause analysis on healthcare-associated infection, in-facility pressure ulcers and falls, but only 60% did on surgery/procedure related events. More than 50% of the hospitals did not adopted present on admission (POA) indicators. One hundred (80.0%) hospitals had a department of patient safety and/or quality and only 52.8% of hospitals had a patient safety officer (PSO). While 82.4% of hospitals used electronic medical records (EMRs), only 53% of these hospitals adopted clinical decision support function. Infrastructure for patient safety except EMRs was well established in training, high-level and large hospitals. Most hospitals implemented prevention practices of adverse drug events, in-facility pressure ulcers and falls (94.4-100.0%). But prevention practices of surgery/procedure related events had relatively low adoption rate (59.2-92.8%). Majority of prevention practices for patient safety events were also implemented with a relatively modest increase in resources allocated. Conclusion: The hospital-based reporting and learning system, EMRs, and core evidence-based prevention practices were implemented well in high-level and large hospitals. But POA indicator and PSO were not adopted in more than half of surveyed hospitals and implementation of prevention practices for specific event had low. To support and monitor progress in hospital's patient safety effort, national-level safety practices set is needed.

• Imaging Science in Dentistry
• /
• v.53 no.3
• /
• pp.199-207
• /
• 2023

Purpose: The objective of this study was to evaluate the accuracy and effectiveness of an artificial intelligence (AI) program in identifying dental conditions using panoramic radiographs(PRs), as well as to assess the appropriateness of its treatment recommendations. Materials and Methods: PRs from 100 patients(representing 4497 teeth) with known clinical examination findings were randomly selected from a university database. Three dentomaxillofacial radiologists and the Diagnocat AI software evaluated these PRs. The evaluations were focused on various dental conditions and treatments, including canal filling, caries, cast post and core, dental calculus, fillings, furcation lesions, implants, lack of interproximal tooth contact, open margins, overhangs, periapical lesions, periodontal bone loss, short fillings, voids in root fillings, overfillings, pontics, root fragments, impacted teeth, artificial crowns, missing teeth, and healthy teeth. Results: The AI demonstrated almost perfect agreement (exceeding 0.81) in most of the assessments when compared to the ground truth. The sensitivity was very high (above 0.8) for the evaluation of healthy teeth, artificial crowns, dental calculus, missing teeth, fillings, lack of interproximal contact, periodontal bone loss, and implants. However, the sensitivity was low for the assessment of caries, periapical lesions, pontic voids in the root canal, and overhangs. Conclusion: Despite the limitations of this study, the synthesized data suggest that AI-based decision support systems can serve as a valuable tool in detecting dental conditions, when used with PR for clinical dental applications.

• Archives of Plastic Surgery
• /
• v.40 no.4
• /
• pp.335-340
• /
• 2013

Background In patients with medial orbital wall fracture, predicting the correlation between the degree of enophthalmos and the extent of fracture is essential for deciding on surgical treatment. We conducted this retrospective study to identify the correlation between the two parameters. Methods We quantitatively analyzed the correlation between the area of the bone defect and the degree of enophthalmos on computed tomography scans in 81 patients with medial orbital wall fracture who had been left untreated for more than six months. Results There was a significant linear positive correlation between the area of the medial orbital wall fracture and the degree of enophthalmos with a formula of E=0.705A+0.061 (E, the degree of enophthalmos; A, the area of bone defect) (Pearson's correlation coefficient, 0.812) (P<0.05). In addition, that there were no cases in which the degree of enophthalmos was greater than 2 mm when the area of the medial orbital wall fracture was smaller than $1.90cm^2$. Conclusions Our results indicate not only that 2 mm of enophthalmos corresponds to a bone defect area of approximately $2.75cm^2$ in patients with medial orbital wall fracture but also that the degree of enophthalmos could be quantitatively predicted based on the area of the bone defect even more than six months after trauma.

• Journal of the Korean Society of Radiology
• /
• v.82 no.5
• /
• pp.1196-1206
• /
• 2021

Purpose To construct a standard dataset of contrast-enhanced CT images of liver tumors to test the performance and safety of artificial intelligence (AI)-based algorithms for clinical decision support systems (CDSSs). Materials and Methods A consensus group of medical experts in gastrointestinal radiology from four national tertiary institutions discussed the conditions to be included in a standard dataset. Seventy-five cases of hepatocellular carcinoma, 75 cases of metastasis, and 30-50 cases of benign lesions were retrieved from each institution, and the final dataset consisted of 300 cases of hepatocellular carcinoma, 300 cases of metastasis, and 183 cases of benign lesions. Only pathologically confirmed cases of hepatocellular carcinomas and metastases were enrolled. The medical experts retrieved the medical records of the patients and manually labeled the CT images. The CT images were saved as Digital Imaging and Communications in Medicine (DICOM) files. Results The medical experts in gastrointestinal radiology constructed the standard dataset of contrast-enhanced CT images for 783 cases of liver tumors. The performance and safety of the AI algorithm can be evaluated by calculating the sensitivity and specificity for detecting and characterizing the lesions. Conclusion The constructed standard dataset can be utilized for evaluating the machine-learning-based AI algorithm for CDSS.

• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.10
• /
• pp.239-246
• /
• 2020

In the medical field where artificial intelligence technology is introduced, research related to clinical decision support system(CDSS) in relation to diagnosis and prediction is actively being conducted. In particular, medical imaging-based disease diagnosis area applied AI technologies at various products. However, medical imaging data consists of inconsistent data, and it is a reality that it takes considerable time to prepare and use it for research. This paper describes a one-stop AI learning platform for converting to medical image standard R_CDM(Radiology Common Data Model) and supporting AI algorithm development research based on the dataset. To this, the focus is on linking with the existing CDM(common data model) and model the system, including the schema of the medical imaging standard model and report information for multi-center research based on DICOM(Digital Imaging and Communications in Medicine) tag information. And also, we show the execution results based on generated datasets through the AI learning platform. As a proposed platform, it is expected to be used for various image-based artificial intelligence researches.