Machine learning approaches for practical predicting outpatient near-future AECOPD based on nationwide electronic medical records.

In this research, we aimed to harness machine learning to predict the imminent risk of acute exacerbation in chronic obstructive pulmonary disease (AECOPD) patients. Utilizing retrospective data from electronic medical records of two Taiwanese hospitals, we identified 26 critical features. To predict 3- and 6-month AECOPD occurrences, we deployed five distinct machine learning algorithms alongside ensemble learning. The 3-month risk prediction was best realized by the XGBoost model, achieving an AUC of 0.795, whereas the XGBoost was superior for the 6-month prediction with an AUC of 0.813. We conducted an explainability analysis and found that the episode of AECOPD, mMRC score, CAT score, respiratory rate, and the use of inhaled corticosteroids were the most impactful features. Notably, our approach surpassed predictions that relied solely on CAT or mMRC scores. Accordingly, we designed an interactive prediction system that provides physicians with a practical tool to predict near-term AECOPD risk in outpatients.

Trend Analysis of Palliative Care Utilization in Patients with Chronic Obstructive Pulmonary Disease During Hospitalization from 2007 to 2018 in Taiwan.

Purpose: Palliative care utilization among hospitalized patients with advanced chronic obstructive pulmonary disease (COPD) in Taiwan remains low despite its costs making it eligible for reimbursement since 2009. Few studies have examined the trends of palliative care utilization. We analyzed the annual rate, associated factors, and timing of the inpatient palliative care utilization by hospitalized patients with COPD. Patients and Methods: We conducted a cross-sectional observational study between 1 January 2007 and 31 December 2018. Population-based claims data were extracted from Taiwan's National Health Insurance Research Database to identify patients aged ≧40 years with COPD five years before the first instance of inpatient palliative care utilization. Results: There were 24,502 patients with COPD receiving inpatient palliative care. Our results indicated that older age, concomitant chronic conditions-especially cancer-and severity of comorbidities were associated with a higher rate of palliative care utilization by hospitalized patients with chronic obstructive pulmonary disease. In our study, the proportion of hospitalized patients with COPD receiving inpatient palliative care and having a Charlson comorbidity index score of 1-2 was lower than that of patients with cancer and a Charlson comorbidity index score ≧3 during the 12-year study-observation period. In addition, approximately 50% of hospitalized patients with COPD received palliative care within 18 months after their initial admission for COPD during the study period. However, individuals with a CCI score of 1-2 exhibited a slower entry into palliative care, with nearly 50% initiating it within the first two years. Conclusion: Inpatient palliative care utilization by hospitalized patients with advanced COPD remains low due to various causes. Our findings highlight that palliative care may be considered by professional care providers as routine care and as a way to manage problematic symptoms during hospitalization.

An artificial intelligence system to predict the optimal timing for mechanical ventilation weaning for intensive care unit patients: A two-stage prediction approach.

Background: For the intensivists, accurate assessment of the ideal timing for successful weaning from the mechanical ventilation (MV) in the intensive care unit (ICU) is very challenging. Purpose: Using artificial intelligence (AI) approach to build two-stage predictive models, namely, the try-weaning stage and weaning MV stage to determine the optimal timing of weaning from MV for ICU intubated patients, and implement into practice for assisting clinical decision making. Methods: AI and machine learning (ML) technologies were used to establish the predictive models in the stages. Each stage comprised 11 prediction time points with 11 prediction models. Twenty-five features were used for the first-stage models while 20 features were used for the second-stage models. The optimal models for each time point were selected for further practical implementation in a digital dashboard style. Seven machine learning algorithms including Logistic Regression (LR), Random Forest (RF), Support Vector Machines (SVM), K Nearest Neighbor (KNN), lightGBM, XGBoost, and Multilayer Perception (MLP) were used. The electronic medical records of the intubated ICU patients of Chi Mei Medical Center (CMMC) from 2016 to 2019 were included for modeling. Models with the highest area under the receiver operating characteristic curve (AUC) were regarded as optimal models and used to develop the prediction system accordingly. Results: A total of 5,873 cases were included in machine learning modeling for Stage 1 with the AUCs of optimal models ranging from 0.843 to 0.953. Further, 4,172 cases were included for Stage 2 with the AUCs of optimal models ranging from 0.889 to 0.944. A prediction system (dashboard) with the optimal models of the two stages was developed and deployed in the ICU setting. Respiratory care members expressed high recognition of the AI dashboard assisting ventilator weaning decisions. Also, the impact analysis of with- and without-AI assistance revealed that our AI models could shorten the patients' intubation time by 21 hours, besides gaining the benefit of substantial consistency between these two decision-making strategies. Conclusion: We noticed that the two-stage AI prediction models could effectively and precisely predict the optimal timing to wean intubated patients in the ICU from ventilator use. This could reduce patient discomfort, improve medical quality, and lower medical costs. This AI-assisted prediction system is beneficial for clinicians to cope with a high demand for ventilators during the COVID-19 pandemic.

Development of an Interactive AI System for the Optimal Timing Prediction of Successful Weaning from Mechanical Ventilation for Patients in Respiratory Care Centers.

Successful weaning from prolonged mechanical ventilation (MV) is an important issue in respiratory care centers (RCCs). Delayed or premature extubation increases both the risk of adverse outcomes and healthcare costs. However, the accurate evaluation of the timing of successful weaning from MV is very challenging in RCCs. This study aims to utilize artificial intelligence algorithms to build predictive models for the successful timing of the weaning of patients from MV in RCCs and to implement a dashboard with the best model in RCC settings. A total of 670 intubated patients in the RCC in Chi Mei Medical Center were included in the study. Twenty-six feature variables were selected to build the predictive models with artificial intelligence (AI)/machine-learning (ML) algorithms. An interactive dashboard with the best model was developed and deployed. A preliminary impact analysis was then conducted. Our results showed that all seven predictive models had a high area under the receiver operating characteristic curve (AUC), which ranged from 0.792 to 0.868. The preliminary impact analysis revealed that the mean number of ventilator days required for the successful weaning of the patients was reduced by 0.5 after AI intervention. The development of an AI prediction dashboard is a promising method to assist in the prediction of the optimal timing of weaning from MV in RCC settings. However, a systematic prospective study of AI intervention is still needed.

The Impact of the Pay-for-Performance Program on the Outcome of COPD Patients in Taiwan After One Year.

Objective: To investigate the impact of a multidisciplinary intervention on the clinical outcomes of patients with COPD. Methods: This study retrospectively extracted the data of patients enrolled in the national pay-for-performance (P4P) program for COPD in four hospitals. Only COPD patients who received regular follow-up for at least one year in the P4P program between September 2018 and December 2020 were included. Results: A total of 1081 patients were included in this study. Among them, 424 (39.2%), 287 (26.5%), 179 (16.6%), and 191 (17.7%) patients were classified as COPD Groups A, B, C, and D, respectively. Dual therapy with long-acting ß2-agonist (LABA)/long-acting muscarinic antagonist (LAMA) was the most used inhaled bronchodilator at baseline (n = 477, 44.1%) patients, followed by LAMA monotherapy (n = 195, 18.0%), triple therapy with inhaled corticosteroid (ICS)/LABA/LAMA (n = 184, 17.0%), and ICS/LABA combination (n = 165, 15.3%). After one year of intervention, 374 (34.6%) and 323 (29.9%) patients had their pre- and post-bronchodilator-forced expiratory volume in one second (FEV1) increase of more than 100 mL. Both the COPD Assessment Test (CAT) and modified British Medical Research Council (mMRC) scores had a mean change of -2.2 ± 5.5 and -0.3 ± 0.9, respectively. The improvement in pulmonary function and symptom score were observed across four groups. The decreased number of exacerbations was only observed in Groups C and D, and not in Groups A and B. Conclusion: This real-world study demonstrated that the intervention in the P4P program could help improve the clinical outcome of COPD patients. It also showed us a different view on the use of dual therapy, which has a lower cost in Taiwan.

Burden of Healthcare Utilization among Chronic Obstructive Pulmonary Disease Patients with and without Cancer Receiving Palliative Care: A Population-Based Study in Taiwan.

Chronic obstructive pulmonary disease (COPD) is a chronic disease that burdens patients worldwide. This study aims to discover the burdens of health services among COPD patients who received palliative care (PC). Study subjects were identified as COPD patients with ICU and PC records between 2009 and 2013 in Taiwan's National Health Insurance Research Database. The burdens of healthcare utilization were analyzed using logistic regression to estimate the difference between those with and without cancer. Of all 1215 COPD patients receiving PC, patients without cancer were older and had more comorbidities, higher rates of ICU admissions, and longer ICU stays than those with cancer. COPD patients with cancer received significantly more blood transfusions (Odds Ratio, OR: 1.66; 95% C.I.: 1.11-2.49) and computed tomography scans (OR: 1.88; 95% C.I.: 1.10-3.22) compared with those without cancer. Bronchoscopic interventions (OR: 0.26; 95% C.I.: 0.07-0.97) and inpatient physical restraints (OR: 0.24; 95% C.I.: 0.08-0.72) were significantly more utilized in patients without cancer. COPD patients without cancer appeared to receive more invasive healthcare interventions than those without cancer. The unmet needs and preferences of patients in the life-limiting stage should be taken into consideration for the quality of care in the ICU environment.

The Outcomes and Prognostic Factors of the Very Elderly Requiring Prolonged Mechanical Ventilation in a Single Respiratory Care Center.

This study investigated the outcomes and the prognostic factors among the very elderly (patients ≥80 years old) requiring prolonged mechanical ventilation (PMV).Between 2006 and 2014, all of the very elderly patients of age 80 or more transferred to respiratory care center (RCC) of a tertiary medical center were retrospectively identified, and only patients who used mechanical ventilation (MV) for >3 weeks were included in this study.A total of 510 very elderly patients undergoing PMV were identified. The mean age of the patients was 84.3 ±â€Š3.3 years, and it ranged from 80 to 96 years. Male comprised most of the patients (n = 269, 52.7%), and most of the patients were transferred to RCC from medical ICU (n = 357, 70.0%). The APACHE II scores on RCC admission was 17.6 ±â€Š6.0. At least 1 comorbidity was found in 419 (82.2%) patients. No significant differences of gender, disease severity, diagnosis, dialysis, laboratory examinations, comorbidities, and outcome were found between octogenarians (aged 80-89) and nonagenarians (aged ≥ 90). The overall in-hospital mortality rate was 21.8%. In the multivariate analysis, patients who had APACHE II score ≥ 15(odds ratio [OR], 2.30, 95% confidence interval [CI], 1.36-3.90), or albumin ≤ 2 g/dL (OR, 3.92, 95% CI, 2.17-7.01) were more likely to have significant in-hospital mortality (P < 0.05).The in-hospital mortality rate of the very elderly PMV patients in our RCC is 21.8%, and poor outcomes in this specific population were found to be associated with a higher APACHE II score and lower albumin level.

Increased Risk of Dementia in Patients With Chronic Obstructive Pulmonary Disease.

Neurodegenerative disease in patients with chronic obstructive pulmonary disease (COPD) was observed. We aim to clarify the risk of dementia in patients with COPD. The study used claims data from Taiwan's National Health Insurance Research Database. Subjects were those who received a discharge diagnosis of COPD between January 1, 2002 and December 31, 2011. Only the first hospitalization was enrolled, and the index date was the first day of admission. Patients younger than 40 years or those with a history of Alzheimer disease (AD) or Parkinson disease (PD) before the index date were excluded. The patients with COPD were then followed until receiving a diagnosis of AD or PD, death, or the end of the study. Control subjects were selected from hospitalized patients without a history of COPD, AD, or PD and were matched according to age (±3 years), gender, and the year of admission at a 2:1 ratio. The comorbidities were measured from 1 year before the index date based on the ICD-9-CM codes. The study included 8640 patients with COPD and a mean age of 68.76 (±10.74) years. The adjusted hazard ratio of developing dementia (AD or PD) was 1.74 (95% confidence interval = 1.55-1.96) in patients with COPD compared with patients without COPD after adjusting for age, gender, and comorbidities. This nationwide cohort study demonstrates that the risk of dementia, including AD and PD, is significantly increased in patients with COPD compared with individuals in the general population.

Epidermal growth factor protects squamous cell carcinoma against cisplatin-induced cytotoxicity through increased interleukin-1ß expression.

The expression of cytokines, such as IL-1ß, and the activation of the epidermal growth factor receptor (EGFR) are crucial regulators in the process of carcinogenesis. The correlation between growth factor and activated cytokine signals in the control of tumor development is a critical issue to be clarified. In our study, we found that the IL-1ß gene and protein expression were induced by EGF in squamous cell carcinoma. To clarify the mechanism involved in EGF-regulated IL-1ß expression, we examined the transcriptional activity and mRNA stability of IL-1ß in EGF-treated cells. We found that EGF induced the expression of IL-1ß and was mediated through transcriptional activation, but not through mRNA stability. The involvement of Akt and NF-κB signaling pathways in the EGF-induced IL-1ß gene expression was confirmed by knockdown of RelA and Akt in cells or treating cells with Akt and NF-κB inhibitors, LY294002 and parthenolide, respectively. The expression of dominant negative IκB also repressed the activation of NF-κB and inhibited EGF-induced IL-1ß expression. Using immunofluorescence staining assay, the EGF-stimulated nuclear translocation of NF-κB (p65) was inhibited by pre-treating cells with LY294002 and parthenolide. Furthermore, EGF increased the binding of NF-κB to the NF-κB binding site of the IL-1ß promoter through the activation of the Akt/NF-κB pathway, which resulted in activating IL-1ß promoter activity. The expression and secretion of IL-1ß induced by EGF considerably reduced chemotherapeutic drug cisplatin-induced cell death. These results showed that EGF enhanced the expression of IL-1ß, which was mediated by the Akt/NF-κB pathway. The activation of EGF signaling and increase of IL-1ß contributed to chemotherapeutic resistance of cancer cells, suggesting that the expression of IL-1ß may be used as a biomarker to evaluate successful cancer treatment.

α-Tomatine suppresses invasion and migration of human non-small cell lung cancer NCI-H460 cells through inactivating FAK/PI3K/Akt signaling pathway and reducing binding activity of NF-κB.

α-Tomatine, isolated from Lycopersicon esculentum Linn., is a naturally occurring steroidal glycoalkaloid in immature green tomatoes. Some reports demonstrated that α-tomatine had various anticarcinogenic properties. The purpose of this study is to investigate the anti-metastatic effect of α-tomatine in NCI-H460 human non-small cell lung cancer cells. First, the results showed that α-tomatine significantly suppressed the abilities of the adhesion, invasion, and migration of NCI-H460 cells under non-cytotoxic concentrations. Molecular data also showed α-tomatine could inhibit the activation of focal adhesion kinase (FAK) and phosphatidylinositol 3-kinase (PI3K)/Akt signal involve in the downregulation the enzyme activities, protein and messenger RNA levels of matrix metalloproteinase-7 (MMP-7). Next, α-tomatine also strongly inhibited the degradation of inhibitor of kappaBα (IκBα) and the nuclear levels of nuclear factor kappa B (NF-κB). Also, a dose-dependent inhibition on the binding ability of NF-κB by α-tomatine treatment was further observed. Furthermore, α-tomatine significantly decreased the levels of phospho-Akt and MMP-7 in Akt1-cDNA-transfected cells concomitantly with a marked reduction on cell invasion and migration. Presented results indicated α-tomatine might be further application for treating cancer metastasis.

Antimetastatic potential of fisetin involves inactivation of the PI3K/Akt and JNK signaling pathways with downregulation of MMP-2/9 expressions in prostate cancer PC-3 cells.

Fisetin (3,3',4',7-tetrahydroxyflavone), a naturally occurring flavonoid, has been reported to possess some anti-cancer and anti-inflammation capabilities. In this study, fisetin has exhibited inhibitory effects on the adhesion, migration, and invasion ability of a highly metastatic PC-3 cells under non-cytotoxic concentrations. Gelatin zymography assay showed that fisetin inhibited the matrix metalloproteinase-2 (MMP-2) and matrix metalloproteinase-9 (MMP-9) activities. Our result also showed that fisetin could inhibit the phosphorylation of c-Jun N-terminal kinase 1 and 2 (JNK1/2) and Akt. Moreover, fisetin significantly decreased the nuclear levels of nuclear factor kappa B (NF-kappaB), c-Fos, and c-Jun, and the binding abilities of NF-kappaB and activator protein-1 (AP-1). Also, the results showed that the protein and mRNA levels of MMP-2 and MMP-9 were significantly reduced by Western blot and semi-quantitative RT-PCR. Further, treating specific inhibitors for PI3K (Wortmannin) or JNK (SP600125) to PC-3 cells could reduce the protein expressions of MMP-2 and MMP-9. These results showed fisetin could inhibit the metastatic ability of PC-3 by reducing MMP-2 and MMP-9 expressions through suppressing phosphoinositide 3-kinase/Akt (PI3K/Akt) and JNK signaling pathways. This suggested fisetin can serve as a potential candidate for treating cancer metastasis.