BACKGROUND/OBJECTIVES: This study aimed to use plasma metabolites to identify clusters of breast cancer survivors and to compare their dietary characteristics and health-related factors across the clusters using unsupervised machine learning. SUBJECTS/METHODS: A total of 419 breast cancer survivors were included in this crosssectional study. We considered 30 plasma metabolites, quantified by high-throughput nuclear magnetic resonance metabolomics. Clusters were obtained based on metabolites using 4 different unsupervised clustering methods: k-means (KM), partitioning around medoids (PAM), self-organizing maps (SOM), and hierarchical agglomerative clustering (HAC). The t-test, χ2 test, and Fisher’s exact test were used to compare sociodemographic, lifestyle, clinical, and dietary characteristics across the clusters. P-values were adjusted through a false discovery rate (FDR). RESULTS: Two clusters were identified using the 4 methods. Participants in cluster 2 had lower concentrations of apolipoprotein A1 and large high-density lipoprotein (HDL) particles and smaller HDL particle sizes, but higher concentrations of chylomicrons and extremely large very-low-density-lipoprotein (VLDL) particles and glycoprotein acetyls, a higher ratio of monounsaturated fatty acids to total fatty acids, and larger VLDL particle sizes compared with cluster 1. Body mass index was significantly higher in cluster 2 compared with cluster 1 (FDR adjusted-PKM < 0.001; PPAM = 0.001; PSOM < 0.001; and PHAC = 0.043). CONCLUSION The breast cancer survivors clustered on the basis of plasma metabolites had distinct characteristics. Further prospective studies are needed to investigate the associations between metabolites, obesity, dietary factors, and breast cancer prognosis.

Background/Aims: Atrial fibrillation (AF) significantly contributes to global morbidity and mortality. Paroxysmal atrial fibrillation (PAF) is particularly common among patients with cryptogenic strokes or transient ischemic attacks and has a silent nature. This study aims to develop reliable artificial intelligence (AI) algorithms to detect early signs of AF in patients with normal sinus rhythm (NSR) using a 12-lead electrocardiogram (ECG). Methods: Between 2013 and 2020, 552,372 ECG traces from 318,321 patients were collected and split into training (n = 331,422), validation (n = 110,475), and test sets (n = 110,475). Deep neural networks were then trained to predict AF onset within one month of NSR. Model performance was evaluated using the area under the receiver operating characteristic curve (AUROC). An explainable AI technique was employed to identify the inference evidence underlying the predictions of deep learning models. Results: The AUROC for early diagnosis of PAF was 0.905 ± 0.007. The findings reveal that the vicinity of the T wave, including the ST segment and S-peak, significantly influences the ability of the trained neural network to diagnose PAF. Additionally, comparing the summarized ECG in NSR with those in PAF revealed that nonspecific ST-T abnormalities and inverted T waves were associated with PAF. Conclusions Deep learning can predict AF onset from NSR while detecting key features that influence decisions. This suggests that identifying undetected AF may serve as a predictive tool for PAF screening, offering valuable insights into cardiac dysfunction and stroke risk.

BACKGROUND/OBJECTIVES: This study aimed to use plasma metabolites to identify clusters of breast cancer survivors and to compare their dietary characteristics and health-related factors across the clusters using unsupervised machine learning. SUBJECTS/METHODS: A total of 419 breast cancer survivors were included in this crosssectional study. We considered 30 plasma metabolites, quantified by high-throughput nuclear magnetic resonance metabolomics. Clusters were obtained based on metabolites using 4 different unsupervised clustering methods: k-means (KM), partitioning around medoids (PAM), self-organizing maps (SOM), and hierarchical agglomerative clustering (HAC). The t-test, χ2 test, and Fisher’s exact test were used to compare sociodemographic, lifestyle, clinical, and dietary characteristics across the clusters. P-values were adjusted through a false discovery rate (FDR). RESULTS: Two clusters were identified using the 4 methods. Participants in cluster 2 had lower concentrations of apolipoprotein A1 and large high-density lipoprotein (HDL) particles and smaller HDL particle sizes, but higher concentrations of chylomicrons and extremely large very-low-density-lipoprotein (VLDL) particles and glycoprotein acetyls, a higher ratio of monounsaturated fatty acids to total fatty acids, and larger VLDL particle sizes compared with cluster 1. Body mass index was significantly higher in cluster 2 compared with cluster 1 (FDR adjusted-PKM < 0.001; PPAM = 0.001; PSOM < 0.001; and PHAC = 0.043). CONCLUSION The breast cancer survivors clustered on the basis of plasma metabolites had distinct characteristics. Further prospective studies are needed to investigate the associations between metabolites, obesity, dietary factors, and breast cancer prognosis.

Background/Aims: Atrial fibrillation (AF) significantly contributes to global morbidity and mortality. Paroxysmal atrial fibrillation (PAF) is particularly common among patients with cryptogenic strokes or transient ischemic attacks and has a silent nature. This study aims to develop reliable artificial intelligence (AI) algorithms to detect early signs of AF in patients with normal sinus rhythm (NSR) using a 12-lead electrocardiogram (ECG). Methods: Between 2013 and 2020, 552,372 ECG traces from 318,321 patients were collected and split into training (n = 331,422), validation (n = 110,475), and test sets (n = 110,475). Deep neural networks were then trained to predict AF onset within one month of NSR. Model performance was evaluated using the area under the receiver operating characteristic curve (AUROC). An explainable AI technique was employed to identify the inference evidence underlying the predictions of deep learning models. Results: The AUROC for early diagnosis of PAF was 0.905 ± 0.007. The findings reveal that the vicinity of the T wave, including the ST segment and S-peak, significantly influences the ability of the trained neural network to diagnose PAF. Additionally, comparing the summarized ECG in NSR with those in PAF revealed that nonspecific ST-T abnormalities and inverted T waves were associated with PAF. Conclusions Deep learning can predict AF onset from NSR while detecting key features that influence decisions. This suggests that identifying undetected AF may serve as a predictive tool for PAF screening, offering valuable insights into cardiac dysfunction and stroke risk.

BACKGROUND/OBJECTIVES: This study aimed to use plasma metabolites to identify clusters of breast cancer survivors and to compare their dietary characteristics and health-related factors across the clusters using unsupervised machine learning. SUBJECTS/METHODS: A total of 419 breast cancer survivors were included in this crosssectional study. We considered 30 plasma metabolites, quantified by high-throughput nuclear magnetic resonance metabolomics. Clusters were obtained based on metabolites using 4 different unsupervised clustering methods: k-means (KM), partitioning around medoids (PAM), self-organizing maps (SOM), and hierarchical agglomerative clustering (HAC). The t-test, χ2 test, and Fisher’s exact test were used to compare sociodemographic, lifestyle, clinical, and dietary characteristics across the clusters. P-values were adjusted through a false discovery rate (FDR). RESULTS: Two clusters were identified using the 4 methods. Participants in cluster 2 had lower concentrations of apolipoprotein A1 and large high-density lipoprotein (HDL) particles and smaller HDL particle sizes, but higher concentrations of chylomicrons and extremely large very-low-density-lipoprotein (VLDL) particles and glycoprotein acetyls, a higher ratio of monounsaturated fatty acids to total fatty acids, and larger VLDL particle sizes compared with cluster 1. Body mass index was significantly higher in cluster 2 compared with cluster 1 (FDR adjusted-PKM < 0.001; PPAM = 0.001; PSOM < 0.001; and PHAC = 0.043). CONCLUSION The breast cancer survivors clustered on the basis of plasma metabolites had distinct characteristics. Further prospective studies are needed to investigate the associations between metabolites, obesity, dietary factors, and breast cancer prognosis.

Background/Aims: Atrial fibrillation (AF) significantly contributes to global morbidity and mortality. Paroxysmal atrial fibrillation (PAF) is particularly common among patients with cryptogenic strokes or transient ischemic attacks and has a silent nature. This study aims to develop reliable artificial intelligence (AI) algorithms to detect early signs of AF in patients with normal sinus rhythm (NSR) using a 12-lead electrocardiogram (ECG). Methods: Between 2013 and 2020, 552,372 ECG traces from 318,321 patients were collected and split into training (n = 331,422), validation (n = 110,475), and test sets (n = 110,475). Deep neural networks were then trained to predict AF onset within one month of NSR. Model performance was evaluated using the area under the receiver operating characteristic curve (AUROC). An explainable AI technique was employed to identify the inference evidence underlying the predictions of deep learning models. Results: The AUROC for early diagnosis of PAF was 0.905 ± 0.007. The findings reveal that the vicinity of the T wave, including the ST segment and S-peak, significantly influences the ability of the trained neural network to diagnose PAF. Additionally, comparing the summarized ECG in NSR with those in PAF revealed that nonspecific ST-T abnormalities and inverted T waves were associated with PAF. Conclusions Deep learning can predict AF onset from NSR while detecting key features that influence decisions. This suggests that identifying undetected AF may serve as a predictive tool for PAF screening, offering valuable insights into cardiac dysfunction and stroke risk.

Purpose: To report a case of macular serous retinal detachment and macular thinning associated with optic disc pit maculopathy successfully treated with vitrectomy, fovea-sparing internal limiting membrane (ILM) peeling, and inverted ILM flap technique.Case summary: A 27-year-old male patient presented with a 1-month history of decreased right eye vision. Corrected visual acuity in the right eye was 0.025 at initial visit. Fundus examination revealed an oval, deep-seated defect in the inferotemporal portion of the optic nerve and a chorioretinal coloboma located inferior to the optic nerve with a one-third disc diameter. Optical coherence tomography (OCT) showed severe macular serous detachment and central foveal thinning. Surgical treatment comprised vitrectomy, ILM peeling preserving an amount of ILM equivalent to the diameter of one disc in the central fovea and covering the optic disc pit with an inverted ILM flap from its nasal portion. The flap was fixed with a dispersible viscoelastic material and intravitreal 20% sulfur hexafluoride gas injection. The patient was maintained in a facedown position for 3 days postoperatively. After 15 months, the best-corrected visual acuity of the right eye improved to 0.63. Repeat OCT revealed resolution of retinoschisis and serous retinal detachment, with the ILM flap effectively covering the optic disc pit. Conclusions Fovea-sparing ILM peeling with an inverted ILM flap on the nasal side over the optic disc pit in patients with thin inner retinal layers and excessive serous retinal detachment effectively prevent the occurrence of macular holes and treat optic disc pit maculopathy.

Purpose: To report a case of macular serous retinal detachment and macular thinning associated with optic disc pit maculopathy successfully treated with vitrectomy, fovea-sparing internal limiting membrane (ILM) peeling, and inverted ILM flap technique.Case summary: A 27-year-old male patient presented with a 1-month history of decreased right eye vision. Corrected visual acuity in the right eye was 0.025 at initial visit. Fundus examination revealed an oval, deep-seated defect in the inferotemporal portion of the optic nerve and a chorioretinal coloboma located inferior to the optic nerve with a one-third disc diameter. Optical coherence tomography (OCT) showed severe macular serous detachment and central foveal thinning. Surgical treatment comprised vitrectomy, ILM peeling preserving an amount of ILM equivalent to the diameter of one disc in the central fovea and covering the optic disc pit with an inverted ILM flap from its nasal portion. The flap was fixed with a dispersible viscoelastic material and intravitreal 20% sulfur hexafluoride gas injection. The patient was maintained in a facedown position for 3 days postoperatively. After 15 months, the best-corrected visual acuity of the right eye improved to 0.63. Repeat OCT revealed resolution of retinoschisis and serous retinal detachment, with the ILM flap effectively covering the optic disc pit. Conclusions Fovea-sparing ILM peeling with an inverted ILM flap on the nasal side over the optic disc pit in patients with thin inner retinal layers and excessive serous retinal detachment effectively prevent the occurrence of macular holes and treat optic disc pit maculopathy.

BACKGROUND/OBJECTIVES: This study aimed to use plasma metabolites to identify clusters of breast cancer survivors and to compare their dietary characteristics and health-related factors across the clusters using unsupervised machine learning. SUBJECTS/METHODS: A total of 419 breast cancer survivors were included in this crosssectional study. We considered 30 plasma metabolites, quantified by high-throughput nuclear magnetic resonance metabolomics. Clusters were obtained based on metabolites using 4 different unsupervised clustering methods: k-means (KM), partitioning around medoids (PAM), self-organizing maps (SOM), and hierarchical agglomerative clustering (HAC). The t-test, χ2 test, and Fisher’s exact test were used to compare sociodemographic, lifestyle, clinical, and dietary characteristics across the clusters. P-values were adjusted through a false discovery rate (FDR). RESULTS: Two clusters were identified using the 4 methods. Participants in cluster 2 had lower concentrations of apolipoprotein A1 and large high-density lipoprotein (HDL) particles and smaller HDL particle sizes, but higher concentrations of chylomicrons and extremely large very-low-density-lipoprotein (VLDL) particles and glycoprotein acetyls, a higher ratio of monounsaturated fatty acids to total fatty acids, and larger VLDL particle sizes compared with cluster 1. Body mass index was significantly higher in cluster 2 compared with cluster 1 (FDR adjusted-PKM < 0.001; PPAM = 0.001; PSOM < 0.001; and PHAC = 0.043). CONCLUSION The breast cancer survivors clustered on the basis of plasma metabolites had distinct characteristics. Further prospective studies are needed to investigate the associations between metabolites, obesity, dietary factors, and breast cancer prognosis.

Background/Aims: Atrial fibrillation (AF) significantly contributes to global morbidity and mortality. Paroxysmal atrial fibrillation (PAF) is particularly common among patients with cryptogenic strokes or transient ischemic attacks and has a silent nature. This study aims to develop reliable artificial intelligence (AI) algorithms to detect early signs of AF in patients with normal sinus rhythm (NSR) using a 12-lead electrocardiogram (ECG). Methods: Between 2013 and 2020, 552,372 ECG traces from 318,321 patients were collected and split into training (n = 331,422), validation (n = 110,475), and test sets (n = 110,475). Deep neural networks were then trained to predict AF onset within one month of NSR. Model performance was evaluated using the area under the receiver operating characteristic curve (AUROC). An explainable AI technique was employed to identify the inference evidence underlying the predictions of deep learning models. Results: The AUROC for early diagnosis of PAF was 0.905 ± 0.007. The findings reveal that the vicinity of the T wave, including the ST segment and S-peak, significantly influences the ability of the trained neural network to diagnose PAF. Additionally, comparing the summarized ECG in NSR with those in PAF revealed that nonspecific ST-T abnormalities and inverted T waves were associated with PAF. Conclusions Deep learning can predict AF onset from NSR while detecting key features that influence decisions. This suggests that identifying undetected AF may serve as a predictive tool for PAF screening, offering valuable insights into cardiac dysfunction and stroke risk.