Purpose: To develop a machine learning (ML) classifier for predicting post-induction hypotension (PIH) in non-cardiac surgeries. Materials and Methods: Preoperative data and early vital signs were obtained from 3669 cases in the VitalDB database, an opensource registry. PIH was defined as sustained mean arterial pressure (MAP) <65 mm Hg within 20 minutes since induction or from induction to incision. Six different ML algorithms were used to create binary classifiers to predict PIH. The primary outcome was the area under the receiver operating characteristic curve (AUROC) of ML classifiers. Results: A total of 2321 (63.3%) cases exhibited PIH. Among ML classifiers, the random forest regressor and extremely gradient boosting regressor showed the highest AUROC, both recording a value of 0.772. Excluding these models, the light gradient boosting machine regressor showed the second highest AUROC [0.769; 95% confidence interval (CI), 0.767–0.771], followed by the gradient boosting regressor (0.768; 95% CI, 0.763–0.772), AdaBoost regressor (0.752; 95% CI, 0.743–0.761), and automatic relevance determination regression (0.685; 95% CI, 0.669–0.701). The top three important features were mean diastolic blood pressure (DBP), minimum MAP, and minimum DBP from anesthetic induction to tracheal intubation, and these features were lower in cases with PIH (all p<0.001). Conclusion ML classifiers exhibited moderate performance in predicting PIH, and have the potential for real-time prediction.

Objectives: . Head and neck squamous cell carcinoma (HNSCC) exhibits high recurrence rates, particularly in cases of radioresistant HNSCC (RR-HNSCC). Non-thermal plasma (NTP) therapy effectively suppresses the progression of HNSCC. However, the therapeutic mechanisms of NTP therapy in treating RR-HNSCC are not well understood. In this study, we explored the regulatory role of NTP in the RR-HNSCC signaling pathway and identified its signature genes. Methods: . After constructing two RR-HNSCC cell lines, we prepared cell lysates from cells treated or not treated with NTP-activated media (NTPAM) and performed RNA sequencing to determine their mRNA expression profiles. Based on the RNA sequencing results, we identified differentially expressed genes (DEGs), followed by a bioinformatics analysis to identify candidate molecules potentially associated with NTPAM therapy for RR-HNSCC. Results: . NTPAM reduced RR-HNSCC cell viability in vitro. RNA sequencing results indicated that NTPAM treatment activated the reactive oxygen species (ROS) pathway and induced ferroptosis in RR-HNSCC cell lines. Among the 1,924 genes correlated with radiation treatment, eight showed statistical significance in both the cell lines and The Cancer Genome Atlas (TCGA) cohort. Only five genes—ABCC3, DUSP16, PDGFB, RAF1, and THBS1—showed consistent results between the NTPAM data sequencing and TCGA data. LASSO regression analysis revealed that five genes were associated with cancer prognosis, with a hazard ratio of 2.26. In RR-HNSCC cells, NTPAM affected DUSP16, PDGFB, and THBS1 as activated markers within 6 hours, and this effect persisted for 12 hours. Furthermore, enrichment analysis indicated that these three DEGs were associated with the extracellular matrix, transforming growth factor-beta, phosphoinositide 3-kinase/protein kinase B, and mesenchymal-epithelial transition factor pathways. Conclusion . NTPAM therapy exerts cytotoxic effects in RR-HNSCC cell lines by inducing specific ROS-mediated ferroptosis. DUSP16, PDGFB, and THBS1 were identified as crucial targets for reversing the radiation resistance induced by NTPAM therapy, providing insights into the mechanisms and clinical applications of NTPAM treatment in RR-HNSCC.

Purpose: To develop a machine learning (ML) classifier for predicting post-induction hypotension (PIH) in non-cardiac surgeries. Materials and Methods: Preoperative data and early vital signs were obtained from 3669 cases in the VitalDB database, an opensource registry. PIH was defined as sustained mean arterial pressure (MAP) <65 mm Hg within 20 minutes since induction or from induction to incision. Six different ML algorithms were used to create binary classifiers to predict PIH. The primary outcome was the area under the receiver operating characteristic curve (AUROC) of ML classifiers. Results: A total of 2321 (63.3%) cases exhibited PIH. Among ML classifiers, the random forest regressor and extremely gradient boosting regressor showed the highest AUROC, both recording a value of 0.772. Excluding these models, the light gradient boosting machine regressor showed the second highest AUROC [0.769; 95% confidence interval (CI), 0.767–0.771], followed by the gradient boosting regressor (0.768; 95% CI, 0.763–0.772), AdaBoost regressor (0.752; 95% CI, 0.743–0.761), and automatic relevance determination regression (0.685; 95% CI, 0.669–0.701). The top three important features were mean diastolic blood pressure (DBP), minimum MAP, and minimum DBP from anesthetic induction to tracheal intubation, and these features were lower in cases with PIH (all p<0.001). Conclusion ML classifiers exhibited moderate performance in predicting PIH, and have the potential for real-time prediction.

Objectives: . Head and neck squamous cell carcinoma (HNSCC) exhibits high recurrence rates, particularly in cases of radioresistant HNSCC (RR-HNSCC). Non-thermal plasma (NTP) therapy effectively suppresses the progression of HNSCC. However, the therapeutic mechanisms of NTP therapy in treating RR-HNSCC are not well understood. In this study, we explored the regulatory role of NTP in the RR-HNSCC signaling pathway and identified its signature genes. Methods: . After constructing two RR-HNSCC cell lines, we prepared cell lysates from cells treated or not treated with NTP-activated media (NTPAM) and performed RNA sequencing to determine their mRNA expression profiles. Based on the RNA sequencing results, we identified differentially expressed genes (DEGs), followed by a bioinformatics analysis to identify candidate molecules potentially associated with NTPAM therapy for RR-HNSCC. Results: . NTPAM reduced RR-HNSCC cell viability in vitro. RNA sequencing results indicated that NTPAM treatment activated the reactive oxygen species (ROS) pathway and induced ferroptosis in RR-HNSCC cell lines. Among the 1,924 genes correlated with radiation treatment, eight showed statistical significance in both the cell lines and The Cancer Genome Atlas (TCGA) cohort. Only five genes—ABCC3, DUSP16, PDGFB, RAF1, and THBS1—showed consistent results between the NTPAM data sequencing and TCGA data. LASSO regression analysis revealed that five genes were associated with cancer prognosis, with a hazard ratio of 2.26. In RR-HNSCC cells, NTPAM affected DUSP16, PDGFB, and THBS1 as activated markers within 6 hours, and this effect persisted for 12 hours. Furthermore, enrichment analysis indicated that these three DEGs were associated with the extracellular matrix, transforming growth factor-beta, phosphoinositide 3-kinase/protein kinase B, and mesenchymal-epithelial transition factor pathways. Conclusion . NTPAM therapy exerts cytotoxic effects in RR-HNSCC cell lines by inducing specific ROS-mediated ferroptosis. DUSP16, PDGFB, and THBS1 were identified as crucial targets for reversing the radiation resistance induced by NTPAM therapy, providing insights into the mechanisms and clinical applications of NTPAM treatment in RR-HNSCC.

Purpose: To develop a machine learning (ML) classifier for predicting post-induction hypotension (PIH) in non-cardiac surgeries. Materials and Methods: Preoperative data and early vital signs were obtained from 3669 cases in the VitalDB database, an opensource registry. PIH was defined as sustained mean arterial pressure (MAP) <65 mm Hg within 20 minutes since induction or from induction to incision. Six different ML algorithms were used to create binary classifiers to predict PIH. The primary outcome was the area under the receiver operating characteristic curve (AUROC) of ML classifiers. Results: A total of 2321 (63.3%) cases exhibited PIH. Among ML classifiers, the random forest regressor and extremely gradient boosting regressor showed the highest AUROC, both recording a value of 0.772. Excluding these models, the light gradient boosting machine regressor showed the second highest AUROC [0.769; 95% confidence interval (CI), 0.767–0.771], followed by the gradient boosting regressor (0.768; 95% CI, 0.763–0.772), AdaBoost regressor (0.752; 95% CI, 0.743–0.761), and automatic relevance determination regression (0.685; 95% CI, 0.669–0.701). The top three important features were mean diastolic blood pressure (DBP), minimum MAP, and minimum DBP from anesthetic induction to tracheal intubation, and these features were lower in cases with PIH (all p<0.001). Conclusion ML classifiers exhibited moderate performance in predicting PIH, and have the potential for real-time prediction.

Purpose: To develop a machine learning (ML) classifier for predicting post-induction hypotension (PIH) in non-cardiac surgeries. Materials and Methods: Preoperative data and early vital signs were obtained from 3669 cases in the VitalDB database, an opensource registry. PIH was defined as sustained mean arterial pressure (MAP) <65 mm Hg within 20 minutes since induction or from induction to incision. Six different ML algorithms were used to create binary classifiers to predict PIH. The primary outcome was the area under the receiver operating characteristic curve (AUROC) of ML classifiers. Results: A total of 2321 (63.3%) cases exhibited PIH. Among ML classifiers, the random forest regressor and extremely gradient boosting regressor showed the highest AUROC, both recording a value of 0.772. Excluding these models, the light gradient boosting machine regressor showed the second highest AUROC [0.769; 95% confidence interval (CI), 0.767–0.771], followed by the gradient boosting regressor (0.768; 95% CI, 0.763–0.772), AdaBoost regressor (0.752; 95% CI, 0.743–0.761), and automatic relevance determination regression (0.685; 95% CI, 0.669–0.701). The top three important features were mean diastolic blood pressure (DBP), minimum MAP, and minimum DBP from anesthetic induction to tracheal intubation, and these features were lower in cases with PIH (all p<0.001). Conclusion ML classifiers exhibited moderate performance in predicting PIH, and have the potential for real-time prediction.

Objectives: . Head and neck squamous cell carcinoma (HNSCC) exhibits high recurrence rates, particularly in cases of radioresistant HNSCC (RR-HNSCC). Non-thermal plasma (NTP) therapy effectively suppresses the progression of HNSCC. However, the therapeutic mechanisms of NTP therapy in treating RR-HNSCC are not well understood. In this study, we explored the regulatory role of NTP in the RR-HNSCC signaling pathway and identified its signature genes. Methods: . After constructing two RR-HNSCC cell lines, we prepared cell lysates from cells treated or not treated with NTP-activated media (NTPAM) and performed RNA sequencing to determine their mRNA expression profiles. Based on the RNA sequencing results, we identified differentially expressed genes (DEGs), followed by a bioinformatics analysis to identify candidate molecules potentially associated with NTPAM therapy for RR-HNSCC. Results: . NTPAM reduced RR-HNSCC cell viability in vitro. RNA sequencing results indicated that NTPAM treatment activated the reactive oxygen species (ROS) pathway and induced ferroptosis in RR-HNSCC cell lines. Among the 1,924 genes correlated with radiation treatment, eight showed statistical significance in both the cell lines and The Cancer Genome Atlas (TCGA) cohort. Only five genes—ABCC3, DUSP16, PDGFB, RAF1, and THBS1—showed consistent results between the NTPAM data sequencing and TCGA data. LASSO regression analysis revealed that five genes were associated with cancer prognosis, with a hazard ratio of 2.26. In RR-HNSCC cells, NTPAM affected DUSP16, PDGFB, and THBS1 as activated markers within 6 hours, and this effect persisted for 12 hours. Furthermore, enrichment analysis indicated that these three DEGs were associated with the extracellular matrix, transforming growth factor-beta, phosphoinositide 3-kinase/protein kinase B, and mesenchymal-epithelial transition factor pathways. Conclusion . NTPAM therapy exerts cytotoxic effects in RR-HNSCC cell lines by inducing specific ROS-mediated ferroptosis. DUSP16, PDGFB, and THBS1 were identified as crucial targets for reversing the radiation resistance induced by NTPAM therapy, providing insights into the mechanisms and clinical applications of NTPAM treatment in RR-HNSCC.

Purpose: To develop a machine learning (ML) classifier for predicting post-induction hypotension (PIH) in non-cardiac surgeries. Materials and Methods: Preoperative data and early vital signs were obtained from 3669 cases in the VitalDB database, an opensource registry. PIH was defined as sustained mean arterial pressure (MAP) <65 mm Hg within 20 minutes since induction or from induction to incision. Six different ML algorithms were used to create binary classifiers to predict PIH. The primary outcome was the area under the receiver operating characteristic curve (AUROC) of ML classifiers. Results: A total of 2321 (63.3%) cases exhibited PIH. Among ML classifiers, the random forest regressor and extremely gradient boosting regressor showed the highest AUROC, both recording a value of 0.772. Excluding these models, the light gradient boosting machine regressor showed the second highest AUROC [0.769; 95% confidence interval (CI), 0.767–0.771], followed by the gradient boosting regressor (0.768; 95% CI, 0.763–0.772), AdaBoost regressor (0.752; 95% CI, 0.743–0.761), and automatic relevance determination regression (0.685; 95% CI, 0.669–0.701). The top three important features were mean diastolic blood pressure (DBP), minimum MAP, and minimum DBP from anesthetic induction to tracheal intubation, and these features were lower in cases with PIH (all p<0.001). Conclusion ML classifiers exhibited moderate performance in predicting PIH, and have the potential for real-time prediction.

Background and Objectives: The clinical benefits of complete revascularization (CR) in acute myocardial infarction (AMI) patients are unclear. Moreover, the benefit of CR is unknown in AMI with diabetes mellitus (DM) patients. We sought to compare the prognosis of CR and incomplete revascularization (IR) in patients with AMI and multivessel disease, according to the presence of DM. Methods: A total of 2,150 AMI patients with multivessel coronary artery disease were analyzed. CR was defined based on the angiographic image. The primary endpoint of this study was the patient-oriented composite outcome (POCO) defined as a composite of allcause death, any myocardial infarction, and any revascularization within 3 years. Results: Overall, 3-year POCO was significantly lower in patients receiving angiographic CR (985 patients, 45.8%) compared with IR (1,165 patients, 54.2%). When divided into subgroups according to the presence of DM, CR reduced 3-year clinical outcomes in the nonDM group but not in the DM group (POCO: 11.7% vs. 23.2%, p<0.001, any revascularization:7.2% vs. 10.8%, p=0.024 in the non-DM group, POCO: 24.3% vs. 27.8%, p=0.295, any revascularization: 13.3% vs. 11.3%, p=0.448 in the DM group, for CR vs. IR). Multivariate analysis showed that CR significantly reduced 3-year POCO (hazard ratio, 0.52; 95% confidence interval, 0.36–0.75) only in the non-DM group. Conclusions In AMI patients with multivessel disease, CR may have less clinical benefit in DM patients than in non-DM patients.

Background and Objectives: The clinical benefits of complete revascularization (CR) in acute myocardial infarction (AMI) patients are unclear. Moreover, the benefit of CR is unknown in AMI with diabetes mellitus (DM) patients. We sought to compare the prognosis of CR and incomplete revascularization (IR) in patients with AMI and multivessel disease, according to the presence of DM. Methods: A total of 2,150 AMI patients with multivessel coronary artery disease were analyzed. CR was defined based on the angiographic image. The primary endpoint of this study was the patient-oriented composite outcome (POCO) defined as a composite of allcause death, any myocardial infarction, and any revascularization within 3 years. Results: Overall, 3-year POCO was significantly lower in patients receiving angiographic CR (985 patients, 45.8%) compared with IR (1,165 patients, 54.2%). When divided into subgroups according to the presence of DM, CR reduced 3-year clinical outcomes in the nonDM group but not in the DM group (POCO: 11.7% vs. 23.2%, p<0.001, any revascularization:7.2% vs. 10.8%, p=0.024 in the non-DM group, POCO: 24.3% vs. 27.8%, p=0.295, any revascularization: 13.3% vs. 11.3%, p=0.448 in the DM group, for CR vs. IR). Multivariate analysis showed that CR significantly reduced 3-year POCO (hazard ratio, 0.52; 95% confidence interval, 0.36–0.75) only in the non-DM group. Conclusions In AMI patients with multivessel disease, CR may have less clinical benefit in DM patients than in non-DM patients.