Tuberculosis treatment course completion is crucial to protect patients against prolonged infectiousness, relapse, lengthened and more expensive therapy due to multidrug resistance TB. Up to 50% of all patients do not...Tuberculosis treatment course completion is crucial to protect patients against prolonged infectiousness, relapse, lengthened and more expensive therapy due to multidrug resistance TB. Up to 50% of all patients do not complete treatment course. To solve this problem, TB treatment with patient supervision and support as an element of the “global plan to stop TB” was considered by the World Health Organization. The plan may require a model to predict the outcome of DOTS therapy;then, this tool may be used to determine how intensive the level of providing services and supports should be. This work applied and compared machine learning techniques initially to predict the outcome of TB therapy. After feature analysis, models by six algorithms including decision tree (DT), artificial neural network (ANN), logistic regression (LR), radial basis function (RBF), Bayesian networks (BN), and support vector machine (SVM) developed and validated. Data of training (N = 4515) and testing (N = 1935) sets were applied and models evaluated by prediction accuracy, F-measure and recall. Seventeen significantly correlated features were identified (P CI = 0.001 - 0.007);DT (C 4.5) was found to be the best algorithm with %74.21 prediction accuracy in comparing with ANN, BN, LR, RBF, and SVM with 62.06%, 57.88%, 57.31%, 53.74%, and 51.36% respectively. Data and distribution may create the opportunity for DT out performance. The predicted class for each TB case might be useful for improving the quality of care through making patients’ supervision and support more case—sensitive in order to enhance the quality of DOTS therapy.展开更多
Aim:We report an exploratory analysis of cfRNA as a biomarker to monitor clinical responses in non-small cell lung cancer(NSCLC),breast cancer,and colorectal cancer(CRC).An analysis of cfRNA as a method for measuring ...Aim:We report an exploratory analysis of cfRNA as a biomarker to monitor clinical responses in non-small cell lung cancer(NSCLC),breast cancer,and colorectal cancer(CRC).An analysis of cfRNA as a method for measuring PD-L1 expression with comparison to clinical responses was also performed in the NSCLC cohort.Methods:Blood samples were collected from 127 patients with metastatic disease that were undergoing therapy,52 with NSCLC,50 with breast cancer,and 25 with CRC.cfRNA was purified from fractionated plasma,and following reverse transcription(RT),total cfRNA and gene expression of PD-L1were analyzed by real-time polymerase chain reaction(qPCR)using beta-actin expression as a surrogate for relative amounts of cfDNA and cfRNA.For the concordance study of liquid biopsies and tissue biopsies,the isolated RNA was analyzed by RNAseq for the expressions of 13 genes.We had to close the study early due to a lack of follow-up during the Covid-19 pandemic.Results:We collected a total of 373 blood samples.Mean cfRNA PCR signals after RT were about 50-fold higher than those of cfDNA.cfRNA was detected in all patients,while cfDNA was detected in 88%of them.A high concordance was found for the expression levels of 13 genes between blood and solid tumor tissue.Changes in cfRNA levels followed over the course of treatments were associated with response to therapy,increasing in progressive disease(PD)and falling when a partial response(PR)occurred.The expression of PD-L1 over time in patients treated with immunotherapy decreased with PR but increased with PD.Pre-treatment levels of PD-L1 were predictive of response in patients treated with immunotherapy.Conclusion:Changes in cfRNA correlate with clinical response to the therapy.Total cfRNA may be useful in predicting clinical outcomes.PD-L1 gene expression may provide a biomarker to predict response to PD-L1 inhibition.展开更多
文摘Tuberculosis treatment course completion is crucial to protect patients against prolonged infectiousness, relapse, lengthened and more expensive therapy due to multidrug resistance TB. Up to 50% of all patients do not complete treatment course. To solve this problem, TB treatment with patient supervision and support as an element of the “global plan to stop TB” was considered by the World Health Organization. The plan may require a model to predict the outcome of DOTS therapy;then, this tool may be used to determine how intensive the level of providing services and supports should be. This work applied and compared machine learning techniques initially to predict the outcome of TB therapy. After feature analysis, models by six algorithms including decision tree (DT), artificial neural network (ANN), logistic regression (LR), radial basis function (RBF), Bayesian networks (BN), and support vector machine (SVM) developed and validated. Data of training (N = 4515) and testing (N = 1935) sets were applied and models evaluated by prediction accuracy, F-measure and recall. Seventeen significantly correlated features were identified (P CI = 0.001 - 0.007);DT (C 4.5) was found to be the best algorithm with %74.21 prediction accuracy in comparing with ANN, BN, LR, RBF, and SVM with 62.06%, 57.88%, 57.31%, 53.74%, and 51.36% respectively. Data and distribution may create the opportunity for DT out performance. The predicted class for each TB case might be useful for improving the quality of care through making patients’ supervision and support more case—sensitive in order to enhance the quality of DOTS therapy.
基金Supported by a grant of the Broward Foundation,Nant Health and Burning Rock.
文摘Aim:We report an exploratory analysis of cfRNA as a biomarker to monitor clinical responses in non-small cell lung cancer(NSCLC),breast cancer,and colorectal cancer(CRC).An analysis of cfRNA as a method for measuring PD-L1 expression with comparison to clinical responses was also performed in the NSCLC cohort.Methods:Blood samples were collected from 127 patients with metastatic disease that were undergoing therapy,52 with NSCLC,50 with breast cancer,and 25 with CRC.cfRNA was purified from fractionated plasma,and following reverse transcription(RT),total cfRNA and gene expression of PD-L1were analyzed by real-time polymerase chain reaction(qPCR)using beta-actin expression as a surrogate for relative amounts of cfDNA and cfRNA.For the concordance study of liquid biopsies and tissue biopsies,the isolated RNA was analyzed by RNAseq for the expressions of 13 genes.We had to close the study early due to a lack of follow-up during the Covid-19 pandemic.Results:We collected a total of 373 blood samples.Mean cfRNA PCR signals after RT were about 50-fold higher than those of cfDNA.cfRNA was detected in all patients,while cfDNA was detected in 88%of them.A high concordance was found for the expression levels of 13 genes between blood and solid tumor tissue.Changes in cfRNA levels followed over the course of treatments were associated with response to therapy,increasing in progressive disease(PD)and falling when a partial response(PR)occurred.The expression of PD-L1 over time in patients treated with immunotherapy decreased with PR but increased with PD.Pre-treatment levels of PD-L1 were predictive of response in patients treated with immunotherapy.Conclusion:Changes in cfRNA correlate with clinical response to the therapy.Total cfRNA may be useful in predicting clinical outcomes.PD-L1 gene expression may provide a biomarker to predict response to PD-L1 inhibition.
