BACKGROUND Heart failure with preserved ejection fraction(HFpEF)accounts for approximately half of heart failure cases and is associated with high morbidity and mortality.Beta-blockers(BB)and calcium channel blockers(...BACKGROUND Heart failure with preserved ejection fraction(HFpEF)accounts for approximately half of heart failure cases and is associated with high morbidity and mortality.Beta-blockers(BB)and calcium channel blockers(CCB)are commonly used for symptom control and comorbidity management,but their comparative effectiveness and safety remain unclear.AIM To compare the effectiveness and safety of BB vs CCB in patients with HFpEF using simulated real-world data and propensity score-matched analyses.METHODS Simulated data for 4000 HFpEF patients(2000 BB,2000 CCB)were generated based on distributions extracted from electronic medical records spanning 2014-2023.Inclusion criteria included adults with left ventricular ejection fraction≥50%and initiation of BB or CCB.Effectiveness outcomes encompassed mortality,heart failure hospitalizations,and changes in clinical parameters.Safety outcomes included bradycardia,hypotension,and drug discontinuation.Statistical analyses used t-tests,χ2 tests,Cox proportional hazards models for hazard ratios(HR),and incidence rate ratios(IRR)in R software.Propensity score matching(PSM)was performed to balance baseline characteristics,with outcomes reassessed in the matched cohort.RESULTS Baseline characteristics were largely balanced,with minor differences in sex,chronic kidney disease,systolic blood pressure,and left atrial volume index.BB demonstrated lower all-cause mortality(crude HR 0.78,95%CI:0.70-0.87,P=0.003),heart failure hospitalization(crude HR 0.86,95%CI:0.77-0.96,P=0.031),and composite endpoint(crude HR 0.85,95%CI:0.79-0.91,P<0.001)rates compared to CCB.IRR for heart failure hospitalizations and emergency visits favored BB.Safety profiles showed higher symptomatic bradycardia(9.2%vs 4.9%,P<0.001)and drug discontinuation(11.3%vs 9.3%,P=0.043)with BB,and higher hypotension(7.2%vs 11.5%,P<0.001)with CCB.Matched analyses showed all-cause mortality rates of 0.0622 per person-year for BB vs 0.0649 for CCB(HR 0.96,95%CI:0.85-1.08),heart failure hospitalization rates of 0.0751 vs 0.0888(HR 0.84,95%CI:0.75-0.94),and IRR for number of heart failure hospitalizations of 1.65 for CCB vs BB(95%CI:1.51-1.80,P<0.001).CONCLUSION BB may offer potential advantages in reducing mortality and hospitalizations in HFpEF compared to CCB,with distinct safety considerations.PSM confirmed these trends with reduced confounding.Personalized therapy is recommended,warranting prospective trials for validation.展开更多
Cyber-attacks pose a significant challenge to the security of Internet of Things(IoT)sensor networks,necessitating the development of robust countermeasures tailored to their unique characteristics and limitations.Var...Cyber-attacks pose a significant challenge to the security of Internet of Things(IoT)sensor networks,necessitating the development of robust countermeasures tailored to their unique characteristics and limitations.Various prevention and detection techniques have been proposed to mitigate these attacks.In this paper,we propose an integrated security framework using blockchain and Machine Learning(ML)to protect IoT sensor networks.The framework consists of two modules:a blockchain prevention module and an ML detection module.The blockchain prevention module has two lightweight mechanisms:identity management and trust management.Identity management employs a lightweight Smart Contract(SC)to manage node registration and authentication,ensuring that unauthorized entities are prohibited from engaging in any tasks,while trust management uses a lightweight SC that is responsible for maintaining trust and credibility between sensor nodes throughout the network’s lifetime and tracking historical node behaviors.Consensus and transaction validation are achieved through a Verifiable Byzantine Fault Tolerance(VBFT)mechanism to ensure network reliability and integrity.The ML detection module utilizes the Light Gradient Boosting Machine(LightGBM)algorithm to classify malicious nodes and notify the blockchain network if it must make decisions to mitigate their impacts.We investigate the performance of several off-the-shelf ML algorithms,including Logistic Regression,Complement Naive Bayes,Nearest Centroid,and Stacking,using the WSN-DS dataset.LightGBM is selected following a detailed comparative analysis conducted using accuracy,precision,recall,F1-score,processing time,training time,prediction time,computational complexity,and Matthews Correlation Coefficient(MCC)evaluation metrics.展开更多
文摘BACKGROUND Heart failure with preserved ejection fraction(HFpEF)accounts for approximately half of heart failure cases and is associated with high morbidity and mortality.Beta-blockers(BB)and calcium channel blockers(CCB)are commonly used for symptom control and comorbidity management,but their comparative effectiveness and safety remain unclear.AIM To compare the effectiveness and safety of BB vs CCB in patients with HFpEF using simulated real-world data and propensity score-matched analyses.METHODS Simulated data for 4000 HFpEF patients(2000 BB,2000 CCB)were generated based on distributions extracted from electronic medical records spanning 2014-2023.Inclusion criteria included adults with left ventricular ejection fraction≥50%and initiation of BB or CCB.Effectiveness outcomes encompassed mortality,heart failure hospitalizations,and changes in clinical parameters.Safety outcomes included bradycardia,hypotension,and drug discontinuation.Statistical analyses used t-tests,χ2 tests,Cox proportional hazards models for hazard ratios(HR),and incidence rate ratios(IRR)in R software.Propensity score matching(PSM)was performed to balance baseline characteristics,with outcomes reassessed in the matched cohort.RESULTS Baseline characteristics were largely balanced,with minor differences in sex,chronic kidney disease,systolic blood pressure,and left atrial volume index.BB demonstrated lower all-cause mortality(crude HR 0.78,95%CI:0.70-0.87,P=0.003),heart failure hospitalization(crude HR 0.86,95%CI:0.77-0.96,P=0.031),and composite endpoint(crude HR 0.85,95%CI:0.79-0.91,P<0.001)rates compared to CCB.IRR for heart failure hospitalizations and emergency visits favored BB.Safety profiles showed higher symptomatic bradycardia(9.2%vs 4.9%,P<0.001)and drug discontinuation(11.3%vs 9.3%,P=0.043)with BB,and higher hypotension(7.2%vs 11.5%,P<0.001)with CCB.Matched analyses showed all-cause mortality rates of 0.0622 per person-year for BB vs 0.0649 for CCB(HR 0.96,95%CI:0.85-1.08),heart failure hospitalization rates of 0.0751 vs 0.0888(HR 0.84,95%CI:0.75-0.94),and IRR for number of heart failure hospitalizations of 1.65 for CCB vs BB(95%CI:1.51-1.80,P<0.001).CONCLUSION BB may offer potential advantages in reducing mortality and hospitalizations in HFpEF compared to CCB,with distinct safety considerations.PSM confirmed these trends with reduced confounding.Personalized therapy is recommended,warranting prospective trials for validation.
文摘Cyber-attacks pose a significant challenge to the security of Internet of Things(IoT)sensor networks,necessitating the development of robust countermeasures tailored to their unique characteristics and limitations.Various prevention and detection techniques have been proposed to mitigate these attacks.In this paper,we propose an integrated security framework using blockchain and Machine Learning(ML)to protect IoT sensor networks.The framework consists of two modules:a blockchain prevention module and an ML detection module.The blockchain prevention module has two lightweight mechanisms:identity management and trust management.Identity management employs a lightweight Smart Contract(SC)to manage node registration and authentication,ensuring that unauthorized entities are prohibited from engaging in any tasks,while trust management uses a lightweight SC that is responsible for maintaining trust and credibility between sensor nodes throughout the network’s lifetime and tracking historical node behaviors.Consensus and transaction validation are achieved through a Verifiable Byzantine Fault Tolerance(VBFT)mechanism to ensure network reliability and integrity.The ML detection module utilizes the Light Gradient Boosting Machine(LightGBM)algorithm to classify malicious nodes and notify the blockchain network if it must make decisions to mitigate their impacts.We investigate the performance of several off-the-shelf ML algorithms,including Logistic Regression,Complement Naive Bayes,Nearest Centroid,and Stacking,using the WSN-DS dataset.LightGBM is selected following a detailed comparative analysis conducted using accuracy,precision,recall,F1-score,processing time,training time,prediction time,computational complexity,and Matthews Correlation Coefficient(MCC)evaluation metrics.
