• Korean Journal of Radiology
• /
• 제22권3호
• /
• pp.442-453
• /
• 2021

Artificial intelligence (AI) will likely affect various fields of medicine. This article aims to explain the fundamental principles of clinical validation, device approval, and insurance coverage decisions of AI algorithms for medical diagnosis and prediction. Discrimination accuracy of AI algorithms is often evaluated with the Dice similarity coefficient, sensitivity, specificity, and traditional or free-response receiver operating characteristic curves. Calibration accuracy should also be assessed, especially for algorithms that provide probabilities to users. As current AI algorithms have limited generalizability to real-world practice, clinical validation of AI should put it to proper external testing and assisting roles. External testing could adopt diagnostic case-control or diagnostic cohort designs. A diagnostic case-control study evaluates the technical validity/accuracy of AI while the latter tests the clinical validity/accuracy of AI in samples representing target patients in real-world clinical scenarios. Ultimate clinical validation of AI requires evaluations of its impact on patient outcomes, referred to as clinical utility, and for which randomized clinical trials are ideal. Device approval of AI is typically granted with proof of technical validity/accuracy and thus does not intend to directly indicate if AI is beneficial for patient care or if it improves patient outcomes. Neither can it categorically address the issue of limited generalizability of AI. After achieving device approval, it is up to medical professionals to determine if the approved AI algorithms are beneficial for real-world patient care. Insurance coverage decisions generally require a demonstration of clinical utility that the use of AI has improved patient outcomes.

• Steel and Composite Structures
• /
• 제51권1호
• /
• pp.25-41
• /
• 2024

The measurement of pile bearing capacity is crucial for the design of pile foundations, where in-situ tests could be costly and time needed. The primary objective of this research was to investigate the potential use of fuzzy-based techniques to anticipate the maximum weight that concrete driven piles might bear. Despite the existence of several suggested designs, there is a scarcity of specialized studies on the exploration of adaptive neuro-fuzzy inference systems (ANFIS) for the estimation of pile bearing capacity. This paper presents the introduction and validation of a novel technique that integrates the fire hawk optimizer (FHO) and equilibrium optimizer (EO) with the ANFIS, referred to as ANFIS_FHO and ANFIS_EO, respectively. A comprehensive compilation of 472 static load test results for driven piles was located within the database. The recommended framework was built, validated, and tested using the training set (70%), validation set (15%), and testing set (15%) of the dataset, accordingly. Moreover, the sensitivity analysis is performed in order to determine the impact of each input on the output. The results show that ANFIS_FHO and ANFIS_EO both have amazing potential for precisely calculating pile bearing capacity. The R² values obtained for ANFIS_FHO were 0.9817, 0.9753, and 0.9823 for the training, validating, and testing phases. The findings of the examination of uncertainty showed that the ANFIS_FHO system had less uncertainty than the ANFIS_EO model. The research found that the ANFIS_FHO model provides a more satisfactory estimation of the bearing capacity of concrete driven piles when considering various performance evaluations and comparing it with existing literature.

• Korean Journal of Radiology
• /
• 제20권8호
• /
• pp.1266-1274
• /
• 2019

Objective: To determine whether radiologic extranodal extension (ENE) appearing on pretreatment CT and MRI could predict the prognosis in patients with human papillomavirus (HPV)-related oropharyngeal squamous cell carcinoma (OPSCC). Materials and Methods: The study population was obtained from a historical cohort diagnosed with HPV-related OPSCC. A total of 134 OPSCC patients who had a metastatic lymph node on pretreatment CT or MRI were included, and radiologic ENE was evaluated by two experienced head and neck radiologists. Kaplan-Meier and multivariate Cox regression analyses were performed to evaluate the impact of radiologic ENE on progression-free survival (PFS). The diagnostic performance of CT and MRI for the diagnosis of ENE was also evaluated in patients who underwent neck dissection. Results: Seventy patients (52.2%) showed radiologic ENE-positive findings. Although patients showing radiologic ENE had a worse 3-year PFS (83.7% vs. 95.3%, p = 0.023), the association between radiologic ENE and PFS was not statistically significant on multivariate analysis (p = 0.141; hazard ratio, 2.68; 95% confidence interval, 0.72-9.97). CT or MRI had a sensitivity of 62%, specificity of 77.8%, and accuracy of 71.9% for predicting pathologic ENE. Conclusion: Radiologic ENE on CT or MRI did not predict poor PFS in patients with HPV-related OPSCC, although there was a trend towards worse PFS. Further studies are warranted to determine whether radiologic ENE is a useful imaging biomarker to risk-stratify patients with HPV-related OPSCC.

• The Korean Journal of Physiology and Pharmacology
• /
• 제28권1호
• /
• pp.21-30
• /
• 2024

The challenging clinical outcomes associated with advanced cervical cancer underscore the need for a novel therapeutic approach. Monensin, a polyether antibiotic, has recently emerged as a promising candidate with anti-cancer properties. In line with these ongoing efforts, our study presents compelling evidence of monensin's potent efficacy in cervical cancer. Monensin exerts a pronounced inhibitory impact on proliferation and anchorage-independent growth. Additionally, monensin significantly inhibited cervical cancer growth in vivo without causing any discernible toxicity in mice. Mechanism studies show that monensin's anti-cervical cancer activity can be attributed to its capacity to inhibit the Wnt/β-catenin pathway, rather than inducing oxidative stress. Monensin effectively reduces both the levels and activity of β-catenin, and we identify Akt, rather than CK1, as the key player involved in monensin-mediated Wnt/β-catenin inhibition. Rescue studies using Wnt activator and β-catenin-overexpressing cells confirmed that β-catenin inhibition is the mechanism of monensin's action. As expected, cervical cancer cells exhibiting heightened Wnt/β-catenin activity display increased sensitivity to monensin treatment. In conclusion, our findings provide pre-clinical evidence that supports further exploration of monensin's potential for repurposing in cervical cancer therapy, particularly for patients exhibiting aberrant Wnt/β-catenin activation.

• 한국간담췌외과학회지
• /
• 제27권2호
• /
• pp.166-171
• /
• 2023

Backgrounds/Aims: Routine execution of intraoperative cholangiography (IOC) in laparoscopic cholecystectomy (LC) is considered a good practice to help early identification of biliary duct injuries (BDIs) or common bile duct (CBD) stones. This study aimed to determine the impact of IOC during LC. Methods: This is a retrospective, monocentric study, including patients with a LC performed from January 2020 to December 2021. Results: Of 303 patients, 215 (71.0%) were in the IOC group and 88 (29.0%) in the no-IOC group. IOC was incomplete or unclear in 10.7% of patients, with a failure rate of 14.7%. Operating time was 15 minutes longer in the IOC group (p = 0.01), and postoperative complications were higher (5.1% vs. 0.0%, p = 0.03). There were three BDIs (0.99%), all included in the IOC group; only one was diagnosed intraoperatively, and the other two were identified during the postoperative course. Regarding identifying CBD stones, IOC showed a sensitivity of 77%, a specificity of 98%, an accuracy of 97.2%, a positive predictive value of 63% and a negative predictive value of 99%. Conclusions: Systematic IOC has shown no specific benefits and prolonged operative duration. IOC should be performed on selected patients or in situations of uncertainty on the anatomy.

• Journal of Cardiovascular Imaging
• /
• 제31권4호
• /
• pp.159-168
• /
• 2023

BACKGROUND: The gold standard for diagnosis of cardiac tumours is histopathological examination. Cardiovascular magnetic resonance (CMR) is a valuable non-invasive, radiation-free tool for identifying and characterizing cardiac tumours. Our aim is to understand CMR diagnosis of cardiac tumours by distinguishing benign vs. malignant tumours compared to the gold standard. METHODS: A systematic search was performed in the PubMed, Web of Science, and Scopus databases up to December 2022, and the results were reviewed by 2 independent investigators. Studies reporting CMR diagnosis were included in a meta-analysis, and pooled measures were obtained. The risk of bias was assessed using the Quality Assessment Tools from the National Institutes of Health. RESULTS: A total of 2,321 results was obtained; 10 studies were eligible, including one identified by citation search. Eight studies were included in the meta-analysis, which presented a pooled sensitivity of 93% and specificity of 94%, a diagnostic odds ratio of 185, and an area under the curve of 0.98 for CMR diagnosis of benign vs. malignant tumours. Additionally, 4 studies evaluated whether CMR diagnosis of cardiac tumours matched specific histopathological subtypes, with 73.6% achieving the correct diagnosis. CONCLUSIONS: To the best of our knowledge, this is the first published systematic review on CMR diagnosis of cardiac tumours. Compared to histopathological results, the ability to discriminate benign from malignant tumours was good but not outstanding. However, significant heterogeneity may have had an impact on our findings.

• Steel and Composite Structures
• /
• 제51권5호
• /
• pp.509-527
• /
• 2024

Bonding carbon fiber-reinforced polymer (CFRP) laminates have been extensively employed in the restoration of steel constructions. In addition to the mechanical properties of the CFRP, the bond strength (P_U) between the CFRP and steel is often important in the eventual strengthened performance. Nonetheless, the bond behavior of the CFRP-steel (CS) interface is exceedingly complicated, with multiple failure causes, giving the P_U challenging to forecast, and the CFRP-enhanced steel structure is unsteady. In just this case, appropriate methods were established by hybridized Random Forests (RF) and support vector regression (SVR) approaches on assembled CS single-shear experiment data to foresee the P_U of CS, in which a recently established optimization algorithm named Aquila optimizer (AO) was used to tune the RF and SVR hyperparameters. In summary, the practical novelty of the article lies in its development of a reliable and efficient method for predicting bond strength at the CS interface, which has significant implications for structural rehabilitation, design optimization, risk mitigation, cost savings, and decision support in engineering practice. Moreover, the Fourier Amplitude Sensitivity Test was performed to depict each parameter's impact on the target. The order of parameter importance was t_c> L_c > E_A > t_A > E_c > b_c > f_c > f_A from largest to smallest by 0.9345 > 0.8562 > 0.79354 > 0.7289 > 0.6531 > 0.5718 > 0.4307 > 0.3657. In three training, testing, and all data phases, the superiority of AO - RF with respect to AO - SVR and MARS was obvious. In the training stage, the values of R² and VAF were slightly similar with a tiny superiority of AO - RF compared to AO - SVR with R² equal to 0.9977 and VAF equal to 99.772, but large differences with results of MARS.

• Journal of Microbiology and Biotechnology
• /
• 제34권6호
• /
• pp.1222-1228
• /
• 2024

Protein-specific antibodies are essential for various aspects of protein research, including detection, purification, and characterization. When specific antibodies are unavailable, protein tagging is a useful alternative. Small epitope tags, typically less than 10 amino acids, are widely used in protein research due to the simple modification through PCR and reduced impact on the target protein's function compared to larger tags. The 2B8 epitope tag (RDPLPFFPP), reported by us in a previous study, has high specificity and sensitivity to the corresponding antibody. However, when attached to the C-terminus of the target protein in immunoprecipitation experiments, we observed a decrease in detection signal with reduced immunity and low protein recovery. This phenomenon was not unique to 2B8 and was also observed with the commercially available Myc tag. Our study revealed that C-terminal tagging of small epitope tags requires the addition of more than one extra amino acid to enhance (restore) antibody immunities. Moreover, among the amino acids we tested, serine was the best for the 2B8 tag. Our findings demonstrated that the interaction between a small epitope and a corresponding paratope of an antibody requires an extra amino acid at the C-terminus of the epitope. This result is important for researchers planning studies on target proteins using small epitope tags.

• Journal of Microbiology and Biotechnology
• /
• 제34권6호
• /
• pp.1229-1238
• /
• 2024

This study aimed to develop and assess a chitosan biomedical antibacterial gel ZincOxide-GrapheneOxide/Chitosan/β-Glycerophosphate (ZnO-GO/CS/β-GP) loaded with nano-zinc oxide (ZnO) and graphene oxide (GO), known for its potent antibacterial properties, biocompatibility, and sustained drug release. ZnO nanoparticles (ZnO-NPs) were modified and integrated with GO sheets to create 1% and 3% ZnO-GO/CS/β-GP thermo-sensitive hydrogels based on ZnO-GO to Chitosan (CS) mass ratio. Gelation time, pH, structural changes, and microscopic morphology were evaluated. The hydrogel's antibacterial efficacy against Porphyromonas gingivalis, biofilm biomass, and metabolic activity was examined alongside its impact (MC3T3-e1). The findings of this study revealed that both hydrogel formulations exhibited temperature sensitivity, maintaining a neutral pH. The ZnO-GO/CS/β-GP formulation effectively inhibited P. gingivalis bacterial activity and biofilm formation, with a 3% ZnO-GO/CS/β-GP antibacterial rate approaching 100%. MC3T3-e1 cells displayed good biocompatibility when cultured in the hydrogel extract.The ZnO-GO/CS/β-GP thermo-sensitive hydrogel demonstrates favorable physical and chemical properties, effectively preventing P. gingivalis biofilm formation. It exhibits promising biocompatibility, suggesting its potential as an adjuvant therapy for managing and preventing peri-implantitis, subject to further clinical investigations.

• 한국가스학회지
• /
• 제28권2호
• /
• pp.47-55
• /
• 2024

한국에는 2030년까지 100여 기의 액화수소 탱크가 도입될 것으로 전망된다. 액화수소는 -253 ℃ 상태로 진공단열구조 탱크에 저장되기 때문에 단열에 문제가 생기면 탱크가 파열되는 대재해의 가능성이 상존한다. 그래서 법령에서는 최후의 보루로 PRV를 설치하도록 규정하고 있다. 주의할 것은 액화수소의 경우 배관의 압력강하를 무시하고 용량을 잘못 계산하면 무용지물이 된다는 것이다. CGA S-1.3에서는 PRV 입·출구 압력강하율을 각각 3% 미만 및 10% 미만으로 하도록 하고 있다. 그러나 배관의 압력강하량과 유량 사이에 상호 의존성이 있어 이들 값을 단번에 계산하는 것이 불가능하다. 그래서 본 연구에서는 매트랩/시뮬링크를 이용하여 PRV시스템의 압력강하율을 계산하는 시뮬레이터를 개발하고, 설계 요소에 대한 압력강하율의 민감도를 평가하였다.