Objective To evaluate the performance of the artificial intelligence (AI)-enabled snail identification system for recognition of Oncomelania hupensis robertsoni and Tricula in schistosomiasis-endemic areas of Yunnan Province. Methods Fifty O. hupensis robertsoni and 50 Tricula samples were collected from Yongbei Township, Yongsheng County, Lijiang City, a schistosomiasis-endemic area in Yunnan Province in May 2024. A total of 100 snail sample images were captured with smartphones, including front-view images of 25 O. hupensis robertsoni and 25 Tricula samples (upward shell opening) and back-view images of 25 O. hupensis robertsoni and 25 Tricula samples (downward shell opening). Snail samples were identified as O. hupensis robertsoni or Tricula by schistosomiasis control experts with a deputy senior professional title and above according to image quality and morphological characteristics. A standard dataset for snail image classification was created, and served as a gold standard for recognition of snail samples. A total of 100 snail sample images were recognized with the AI-enabled intelligent snail identification system based on a WeChat mini program in smartphones. Schistosomiasis control professionals were randomly sampled from stations of schistosomisis prevention and control and centers for disease control and prevention in 18 schistosomiasis-endemic counties (districts, cities) of Yunnan Province, for artificial identification of 100 snail sample images. All professionals are assigned to two groups according the median years of snail survey experiences, and the effect of years of snail survey experiences on O. hupensis robertsoni sample image recognition was evaluated. A receiver operating characteristic (ROC) curve was plotted, and the sensitivity, specificity, accuracy, Youden’s index and the area under the curve (AUC) of the AI-enabled intelligent snail identification system and artificial identification were calculated for recognition of snail sample images. The snail sample image recognition results of AI-enabled intelligent snail identification system and artificial identification were compared with the gold standard, and the internal consistency of artificial identification results was evaluated with the Cronbach’s coefficient alpha. Results A total of 54 schistosomiasis control professionals were sampled for artificial identification of snail sample image recognition, with a response rate of 100% (54/54), and the accuracy, sensitivity, specificity, Youden’s index, and AUC of artificial identification were 90%, 86%, 94%, 0.80 and 0.90 for recognition of snail sample images, respectively. The overall Cronbach’s coefficient alpha of artificial identification was 0.768 for recognition of snail sample images, and the Cronbach’s coefficient alpha was 0.916 for recognition of O. hupensis robertsoni snail sample images and 0.925 for recognition of Tricula snail sample images. The overall accuracy of artificial identification was 90% for recognition of snail sample images, and there was no significant difference in the accuracy of artificial identification for recognition of O. hupensis robertsoni (86%) and Tricula snail sample images (94%) (χ² = 1.778, P > 0.05). There was no significant difference in the accuracy of artificial identification for recognition of snail sample images with upward (88%) and downward shell openings (92%) (χ² = 0.444, P > 0.05), and there was a significant difference in the accuracy of artificial identification for recognition of snail sample images between schistosomiasis control professionals with snail survey experiences of 6 years and less (75%) and more than 6 years (90%) (χ² = 7.792, P < 0.05). The accuracy, sensitivity, specificity and AUC of the AI-enabled intelligent snail identification system were 88%, 100%, 76% and 0.88 for recognition of O. hupensis robertsoni snail sample images, and there was no significant difference in the accuracy of recognition of O. hupensis robertsoni snail sample images between the AI-enabled intelligent snail identification system and artificial identification (χ² = 0.204, P > 0.05). In addition, there was no significant difference in the accuracy of artificial identification for recognition of snail sample images with upward (90%) and downward shell openings (86%) (χ² = 0.379, P > 0.05), and there was a significant difference in the accuracy of artificial identification for recognition of snail sample images between schistosomiasis control professionals with snail survey experiences of 6 years and less and more than 6 years (χ² = 5.604, P_adjusted < 0.025). Conclusions The accuracy of recognition of snail sample images is comparable between the AI-enabled intelligent snail identification system and artificial identification by schistosomiasis control professionals, and the AI-enabled intelligent snail identification system is feasible for recognition of O. hupensis robertsoni and Tricula in Yunnan Province.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Background: With growing elderly populations, management of patients with acute stroke is increasingly important. In South Korea, the Acute Stroke Quality Assessment Program (ASQAP) has contributed to improving the quality of stroke care and practice behavior in healthcare institutions. While the mortality of hemorrhagic stroke remains high, there are only a few assessment indices associated with hemorrhagic stroke. Considering the need to develop assessment indices to improve the actual quality of care in the field of acute stroke treatment, this study aims to investigate the current status of human resources and practices related to the treatment of patients with acute stroke through a nationwide survey. Methods: For the healthcare institutions included in the Ninth ASQAP of the Health Insurance Review and Assessment Service (HIRA), data from January 2022 to December 2022 were collected through a survey on the current status and practice of healthcare providers related to the treatment of patients with acute stroke. The questionnaire consisted of 19 items, including six items on healthcare providers involved in stroke care and 10 items on the care of patients with acute stroke. Results: In the treatment of patients with hemorrhagic stroke among patients with acute stroke, neurosurgeons were the most common providers. The contribution of neurosurgeons in the treatment of ischemic stroke has also been found to be equivalent to that of neurologists. However, a number of institutions were found to be devoid of healthcare providers who perform definitive treatments, such as intra-arterial thrombectomy for patients with ischemic stroke or cerebral aneurysm clipping for subarachnoid hemorrhage. The intensity of the workload of healthcare providers involved in the care of patients with acute stroke, especially those involved in definitive treatment, was also found to be quite high. Conclusion Currently, there are almost no assessment indices specific to hemorrhagic stroke in the ASQAP for acute stroke. Furthermore, it does not reflect the reality of the healthcare providers and practices that provide definitive treatment for acute stroke. The findings of this study suggest the need for the development of appropriate assessment indices that reflect the realities of acute stroke care.

Background: With growing elderly populations, management of patients with acute stroke is increasingly important. In South Korea, the Acute Stroke Quality Assessment Program (ASQAP) has contributed to improving the quality of stroke care and practice behavior in healthcare institutions. While the mortality of hemorrhagic stroke remains high, there are only a few assessment indices associated with hemorrhagic stroke. Considering the need to develop assessment indices to improve the actual quality of care in the field of acute stroke treatment, this study aims to investigate the current status of human resources and practices related to the treatment of patients with acute stroke through a nationwide survey. Methods: For the healthcare institutions included in the Ninth ASQAP of the Health Insurance Review and Assessment Service (HIRA), data from January 2022 to December 2022 were collected through a survey on the current status and practice of healthcare providers related to the treatment of patients with acute stroke. The questionnaire consisted of 19 items, including six items on healthcare providers involved in stroke care and 10 items on the care of patients with acute stroke. Results: In the treatment of patients with hemorrhagic stroke among patients with acute stroke, neurosurgeons were the most common providers. The contribution of neurosurgeons in the treatment of ischemic stroke has also been found to be equivalent to that of neurologists. However, a number of institutions were found to be devoid of healthcare providers who perform definitive treatments, such as intra-arterial thrombectomy for patients with ischemic stroke or cerebral aneurysm clipping for subarachnoid hemorrhage. The intensity of the workload of healthcare providers involved in the care of patients with acute stroke, especially those involved in definitive treatment, was also found to be quite high. Conclusion Currently, there are almost no assessment indices specific to hemorrhagic stroke in the ASQAP for acute stroke. Furthermore, it does not reflect the reality of the healthcare providers and practices that provide definitive treatment for acute stroke. The findings of this study suggest the need for the development of appropriate assessment indices that reflect the realities of acute stroke care.

Background/Aims: Inaccurate prediction of lymph node metastasis (LNM) may lead to unnecessary surgery following endoscopic resection of T1 colorectal cancer (CRC). We aimed to validate the usefulness of artificial intelligence (AI) models for predicting LNM in patients with T1 CRC. Methods: We analyzed the clinical data, laboratory results, pathological reports, and endoscopic findings of patients who underwent radical surgery for T1 CRC. We developed AI models to predict LNM using four algorithms: regularized logistic regression classifier (RLRC), random forest classifier (RFC), CatBoost classifier (CBC), and the voting classifier (VC). Four histological factors and four endoscopic findings were included to develop AI models. Areas under the receiver operating characteristics curves (AUROCs) were measured to distinguish AI model performance in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines. Results: Among 1,386 patients with T1 CRC, 173 patients (12.5%) had LNM. The AUROC values of the RLRC, RFC, CBC, and VC models for LNM prediction were significantly higher (0.673, 0.640, 0.679, and 0.677, respectively) than the 0.525 suggested in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines (vs RLRC, p<0.001; vs RFC, p=0.001; vs CBC, p<0.001; vs VC, p<0.001). The AUROC value was similar between T1 colon versus T1 rectal cancers (0.718 vs 0.615, p=0.700). The AUROC value was also similar between the initial endoscopic resection and initial surgery groups (0.581 vs 0.746, p=0.845). Conclusions AI models trained on the basis of endoscopic findings and pathological features performed well in predicting LNM in patients with T1 CRC regardless of tumor location and initial treatment method.

Hepatocellular carcinoma (HCC) is an aggressive primary liver malignancy often diagnosed at an advanced stage, resulting in a poor prognosis. Accurate risk stratification and early detection of HCC are critical unmet needs for improving outcomes. Several blood-based biomarkers and imaging tests are available for early detection, prediction, and monitoring of HCC. However, serum protein biomarkers such as alpha-fetoprotein have shown relatively low sensitivity, leading to inaccurate performance. Imaging studies also face limitations related to suboptimal accuracy, high cost, and limited implementation. Recently, liquid biopsy techniques have gained attention for addressing these unmet needs. Liquid biopsy is non-invasive and provides more objective readouts, requiring less reliance on healthcare professional’s skills compared to imaging. Circulating tumor cells, cell-free DNA, and extracellular vesicles are targeted in liquid biopsies as novel biomarkers for HCC. Despite their potential, there are debates regarding the role of these novel biomarkers in the HCC care continuum. This review article aims to discuss the technical challenges, recent technical advancements, advantages and disadvantages of these liquid biopsies, as well as their current clinical application and future directions of liquid biopsy in HCC.

Background/Aims: Inaccurate prediction of lymph node metastasis (LNM) may lead to unnecessary surgery following endoscopic resection of T1 colorectal cancer (CRC). We aimed to validate the usefulness of artificial intelligence (AI) models for predicting LNM in patients with T1 CRC. Methods: We analyzed the clinical data, laboratory results, pathological reports, and endoscopic findings of patients who underwent radical surgery for T1 CRC. We developed AI models to predict LNM using four algorithms: regularized logistic regression classifier (RLRC), random forest classifier (RFC), CatBoost classifier (CBC), and the voting classifier (VC). Four histological factors and four endoscopic findings were included to develop AI models. Areas under the receiver operating characteristics curves (AUROCs) were measured to distinguish AI model performance in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines. Results: Among 1,386 patients with T1 CRC, 173 patients (12.5%) had LNM. The AUROC values of the RLRC, RFC, CBC, and VC models for LNM prediction were significantly higher (0.673, 0.640, 0.679, and 0.677, respectively) than the 0.525 suggested in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines (vs RLRC, p<0.001; vs RFC, p=0.001; vs CBC, p<0.001; vs VC, p<0.001). The AUROC value was similar between T1 colon versus T1 rectal cancers (0.718 vs 0.615, p=0.700). The AUROC value was also similar between the initial endoscopic resection and initial surgery groups (0.581 vs 0.746, p=0.845). Conclusions AI models trained on the basis of endoscopic findings and pathological features performed well in predicting LNM in patients with T1 CRC regardless of tumor location and initial treatment method.

Background/Aims: Inaccurate prediction of lymph node metastasis (LNM) may lead to unnecessary surgery following endoscopic resection of T1 colorectal cancer (CRC). We aimed to validate the usefulness of artificial intelligence (AI) models for predicting LNM in patients with T1 CRC. Methods: We analyzed the clinical data, laboratory results, pathological reports, and endoscopic findings of patients who underwent radical surgery for T1 CRC. We developed AI models to predict LNM using four algorithms: regularized logistic regression classifier (RLRC), random forest classifier (RFC), CatBoost classifier (CBC), and the voting classifier (VC). Four histological factors and four endoscopic findings were included to develop AI models. Areas under the receiver operating characteristics curves (AUROCs) were measured to distinguish AI model performance in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines. Results: Among 1,386 patients with T1 CRC, 173 patients (12.5%) had LNM. The AUROC values of the RLRC, RFC, CBC, and VC models for LNM prediction were significantly higher (0.673, 0.640, 0.679, and 0.677, respectively) than the 0.525 suggested in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines (vs RLRC, p<0.001; vs RFC, p=0.001; vs CBC, p<0.001; vs VC, p<0.001). The AUROC value was similar between T1 colon versus T1 rectal cancers (0.718 vs 0.615, p=0.700). The AUROC value was also similar between the initial endoscopic resection and initial surgery groups (0.581 vs 0.746, p=0.845). Conclusions AI models trained on the basis of endoscopic findings and pathological features performed well in predicting LNM in patients with T1 CRC regardless of tumor location and initial treatment method.

Hepatocellular carcinoma (HCC) is an aggressive primary liver malignancy often diagnosed at an advanced stage, resulting in a poor prognosis. Accurate risk stratification and early detection of HCC are critical unmet needs for improving outcomes. Several blood-based biomarkers and imaging tests are available for early detection, prediction, and monitoring of HCC. However, serum protein biomarkers such as alpha-fetoprotein have shown relatively low sensitivity, leading to inaccurate performance. Imaging studies also face limitations related to suboptimal accuracy, high cost, and limited implementation. Recently, liquid biopsy techniques have gained attention for addressing these unmet needs. Liquid biopsy is non-invasive and provides more objective readouts, requiring less reliance on healthcare professional’s skills compared to imaging. Circulating tumor cells, cell-free DNA, and extracellular vesicles are targeted in liquid biopsies as novel biomarkers for HCC. Despite their potential, there are debates regarding the role of these novel biomarkers in the HCC care continuum. This review article aims to discuss the technical challenges, recent technical advancements, advantages and disadvantages of these liquid biopsies, as well as their current clinical application and future directions of liquid biopsy in HCC.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.