Remote photoplethysmography is a method of measuring physiological parameters such as heart rate from facial video.For overcoming the difficulties in achieving both high accuracy and lightweight by the existing heart rate measurement methods,an improved three-dimensional convolution network model is proposed to realize non-contact physiological parameter detection in facial video.In the pre-processing,YuNet model takes place of the traditional face detector,so that the face region can be recognized quickly and accurately.In addition,attention mechanisms and residual modules are embed into three-dimensional convolution network to extract key channel and spatial features,with long short-term memory networks used as period memory modules to capture long-term dependencies in the data.The experimental results show that the proposed Res-CHATM model achieves excellent results of MAE=2.19 BPM,RMSE=7.02 BPM,C=0.95,and MAE=1.65 BPM,RMSE=3.44 BPM,C=0.98 in the cross experiments on public datasets UBFC-rPPG and PURE for heart rate estimation.The consistency between the predicted value and the real value and the effectiveness of the fusion module are further verified,demonstrating the potential of efficient lightweight model in remote photoplethysmography.

Objectives:Coronary slow flow(CSF)has long been regarded as a marker of coronary microvascular dysfunction(CMD).This study aims to evaluate the diagnostic value of CSF for CMD in patients with angina and nonobstructive coronary arteries(ANOCA).Methods:The study data were derived from the ANOCA-CMD prospective cohort study.All enrolled patients underwent coronary angiography and concurrent coronary physiological assessments in the left anterior descending artery using pressure-wire and thermodilution techniques to obtain coronary flow reserve(CFR)and the index of microcirculatory resistance(IMR).Based on the results,CMD was classified into four subtypes:CMD with elevated IMR(IMR≥25),CMD with reduced CFR(CFR<2.5),CMD with either reduced CFR or elevated IMR(CFR<2.5 or IMR≥25),and CMD with both reduced CFR and elevated IMR(CFR<2.5 and IMR≥25).The corrected thrombolysis in myocardial infarction(TIMI)frame count(CTFC)in the left anterior descending artery was calculated from coronary angiography images,with CSF defined as CTFC>27.This study evaluated the correlation between CTFC,CFR,and IMR,and investigated the diagnostic value of CSF for CMD in ANOCA patients.Results:A total of 103 ANOCA patients were enrolled in this study,with a mean age of(64.2±10.6)years,and 53.4％were female.Among them,57 patients(55.3％)were diagnosed with coronary slow flow.Patients with slow flow had higher IMR(P<0.001)and CFR(P=0.041).Similarly,the proportion of CMD with elevated IMR was higher in the slow flow group(P<0.001),while the proportion of CMD with reduced CFR was lower(P=0.044).There was no significant difference between the groups in the proportions of CMD with either reduced CFR or elevated IMR or CMD with both reduced CFR and elevated IMR(all P>0.05).CTFC was positively correlated with hyperemic mean transit time(r=0.424,P<0.001),IMR(r=0.430,P<0.001),and CFR(r=0.211,P=0.032).The area under the curve(AUC)of CTFC for diagnosing CMD with elevated IMR was 0.721(95％CI:0.623-0.819)with an accuracy of 67％(57％,76％),for diagnosing CMD with reduced CFR was 0.610(95％CI:0.499-0.720)with an accuracy of 60％(50％,70％),for diagnosing CMD with either reduced CFR or elevated IMR was 0.549(95％CI:0.425-0.673)with an accuracy of 47％(37％,57％),and for diagnosing CMD with both reduced CFR and elevated IMR was 0.582(95％CI:0.471-0.693)with an accuracy of 47％(37％,57％).Thus,CSF demonstrated limited diagnostic values across all subtypes of CMD.Conclusions:In ANOCA patients,CSF cannot serve as an effective diagnostic marker for CMD.Therefore,in clinical practice,the slow flow phenomenon should not be directly equated with the presence of coronary microvascular dysfunction in ANOCA patients.

There is limited research on semantic segmentation of pulse diagrams using deep learning models.Therefore,an improved DeepLabv3+algorithm specifically for semantic segmentation of pulse diagrams is proposed.DeepLabv3+is served as the basic framework model,with its backbone network replaced by MobileNetV2 in the coding structure.This modification effectively reduces model size and parameter redundancy.Moreover,an improved bottleneck series fusion multi-scale pyramid pooling module is constructed to effectively expand the receptive field,improve segmentation accuracy,and further reduce parameter redundancy.An improved channel-spatial serial attention mechanism is integrated into the decoding structure for improving model performance.Concurrently,the sampling multiple is reduced for mitigating feature information loss.The improved DeepLabv3+model for semantic segmentation of pulse diagrams demonstrates exceptional capability in simultaneously and quickly detecting and identifying pulse curves and multiple elements in pulse diagrams.With a segmentation speed of 98.7 frames/s,the model achieves excellent performance metrics including 95.35%MPA and 88.66%MIoU,while maintaining a compact size of only 16.8 MB.Notably,the visualized segmentation results confirmes the superior performance of the proposed model over other models.These results suggest that the proposed model is particularly well-suited for efficient and fast semantic segmentation of pulse diagrams.

Objectives:Coronary slow flow(CSF)has long been regarded as a marker of coronary microvascular dysfunction(CMD).This study aims to evaluate the diagnostic value of CSF for CMD in patients with angina and nonobstructive coronary arteries(ANOCA).Methods:The study data were derived from the ANOCA-CMD prospective cohort study.All enrolled patients underwent coronary angiography and concurrent coronary physiological assessments in the left anterior descending artery using pressure-wire and thermodilution techniques to obtain coronary flow reserve(CFR)and the index of microcirculatory resistance(IMR).Based on the results,CMD was classified into four subtypes:CMD with elevated IMR(IMR≥25),CMD with reduced CFR(CFR<2.5),CMD with either reduced CFR or elevated IMR(CFR<2.5 or IMR≥25),and CMD with both reduced CFR and elevated IMR(CFR<2.5 and IMR≥25).The corrected thrombolysis in myocardial infarction(TIMI)frame count(CTFC)in the left anterior descending artery was calculated from coronary angiography images,with CSF defined as CTFC>27.This study evaluated the correlation between CTFC,CFR,and IMR,and investigated the diagnostic value of CSF for CMD in ANOCA patients.Results:A total of 103 ANOCA patients were enrolled in this study,with a mean age of(64.2±10.6)years,and 53.4％were female.Among them,57 patients(55.3％)were diagnosed with coronary slow flow.Patients with slow flow had higher IMR(P<0.001)and CFR(P=0.041).Similarly,the proportion of CMD with elevated IMR was higher in the slow flow group(P<0.001),while the proportion of CMD with reduced CFR was lower(P=0.044).There was no significant difference between the groups in the proportions of CMD with either reduced CFR or elevated IMR or CMD with both reduced CFR and elevated IMR(all P>0.05).CTFC was positively correlated with hyperemic mean transit time(r=0.424,P<0.001),IMR(r=0.430,P<0.001),and CFR(r=0.211,P=0.032).The area under the curve(AUC)of CTFC for diagnosing CMD with elevated IMR was 0.721(95％CI:0.623-0.819)with an accuracy of 67％(57％,76％),for diagnosing CMD with reduced CFR was 0.610(95％CI:0.499-0.720)with an accuracy of 60％(50％,70％),for diagnosing CMD with either reduced CFR or elevated IMR was 0.549(95％CI:0.425-0.673)with an accuracy of 47％(37％,57％),and for diagnosing CMD with both reduced CFR and elevated IMR was 0.582(95％CI:0.471-0.693)with an accuracy of 47％(37％,57％).Thus,CSF demonstrated limited diagnostic values across all subtypes of CMD.Conclusions:In ANOCA patients,CSF cannot serve as an effective diagnostic marker for CMD.Therefore,in clinical practice,the slow flow phenomenon should not be directly equated with the presence of coronary microvascular dysfunction in ANOCA patients.

There is limited research on semantic segmentation of pulse diagrams using deep learning models.Therefore,an improved DeepLabv3+algorithm specifically for semantic segmentation of pulse diagrams is proposed.DeepLabv3+is served as the basic framework model,with its backbone network replaced by MobileNetV2 in the coding structure.This modification effectively reduces model size and parameter redundancy.Moreover,an improved bottleneck series fusion multi-scale pyramid pooling module is constructed to effectively expand the receptive field,improve segmentation accuracy,and further reduce parameter redundancy.An improved channel-spatial serial attention mechanism is integrated into the decoding structure for improving model performance.Concurrently,the sampling multiple is reduced for mitigating feature information loss.The improved DeepLabv3+model for semantic segmentation of pulse diagrams demonstrates exceptional capability in simultaneously and quickly detecting and identifying pulse curves and multiple elements in pulse diagrams.With a segmentation speed of 98.7 frames/s,the model achieves excellent performance metrics including 95.35%MPA and 88.66%MIoU,while maintaining a compact size of only 16.8 MB.Notably,the visualized segmentation results confirmes the superior performance of the proposed model over other models.These results suggest that the proposed model is particularly well-suited for efficient and fast semantic segmentation of pulse diagrams.

Remote photoplethysmography is a method of measuring physiological parameters such as heart rate from facial video.For overcoming the difficulties in achieving both high accuracy and lightweight by the existing heart rate measurement methods,an improved three-dimensional convolution network model is proposed to realize non-contact physiological parameter detection in facial video.In the pre-processing,YuNet model takes place of the traditional face detector,so that the face region can be recognized quickly and accurately.In addition,attention mechanisms and residual modules are embed into three-dimensional convolution network to extract key channel and spatial features,with long short-term memory networks used as period memory modules to capture long-term dependencies in the data.The experimental results show that the proposed Res-CHATM model achieves excellent results of MAE=2.19 BPM,RMSE=7.02 BPM,C=0.95,and MAE=1.65 BPM,RMSE=3.44 BPM,C=0.98 in the cross experiments on public datasets UBFC-rPPG and PURE for heart rate estimation.The consistency between the predicted value and the real value and the effectiveness of the fusion module are further verified,demonstrating the potential of efficient lightweight model in remote photoplethysmography.

Objective:To investigate the value of peripheral blood neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR) and serum lactate dehydrogenase (LDH) levels for predicting the occurrence of radiation pneumonia (RP) in small cell lung cancer.Methods:A total of 84 patients with small cell lung cancer who received image-guided radiotherapy in Xuzhou Cancer Hospital between September 2019 and September 2022 were retrospectively analyzed. They were divided into an RP group ( n = 25) and a non-RP group ( n = 59) according to whether RP occurred. Peripheral blood NLR and PLR and serum LDH levels were compared between the two groups before and after radiotherapy. The receiver operating characteristic curve (ROC curve) was used to analyze the value of peripheral blood NLR, PLR, and serum LDH levels for the diagnosis of RP in small cell lung cancer. Results:Before radiotherapy, there were no significant differences in peripheral blood NLR and PLR between the two groups (both P > 0.05). After radiotherapy, peripheral blood NLR and PLR in the RP group were (3.39 ± 0.81) and (129.06 ± 24.90), respectively, which were significantly higher than those in the non-RP group [(2.54 ± 0.71), (104.76 ± 26.26), t = 3.61, 3.83, both P < 0.05]. The NLR (2.86 ± 0.30) and PLR (110.07 ± 10.05) were the lowest in patients with grade 2 RP and they were highest in patients with grade 4 RP [(4.49 ± 0.63), (168.88 ± 14.11)]. The grade of RP was positively correlated with peripheral blood NLR and PLR. The sensitivity of peripheral blood NLR in the diagnosis of RP was 88.0%, the specificity was 66.1%, and the area under the curve (AUC) was 0.791. The sensitivity of PLR in the diagnosis of RP was 48.0%, the specificity was 94.9%, and the AUC was 0.735. The sensitivity of NLR combined with PLR in the diagnosis of RP was 92.0%, the specificity was 59.3%, and the AUC was 0.801. There was no significant difference in serum LDH levels between the two groups before and after radiotherapy (both P > 0.05). Logistic regression analysis showed that NLR and PLR were risk factors for RP in patients with small cell lung cancer ( OR = 2.309, 1.037; 95% CI: 1.061-5.024, 1.004-1.071). Conclusion:In patients with small cell lung cancer who develop RP, peripheral blood NLR, and PLR are markedly elevated compared with those in patients who do not develop RP, and combined detection of peripheral blood NLR and PLR has a high value for early diagnosis of RP in patients with small cell lung cancer.

Objective: To investigate the relationship of plasma albumin and hypersensitive C-reactive protein (Hs-CRP) with 5-year all-cause mortality among Chinese older adults aged 65 and older. Method: Data was collected in 8 longevity areas of the Chinese Longitudinal Healthy Longevity Survey (CLHLS) study conducted by Chinese Center for Disease Control and Prevention and Peking University at baseline survey in 2012 and 2014, the participants enrolled in 2012 was followed-up in 2014 and 2017, the participants enrolled in 2014 was followed-up in 2017 only. Finally, 3 118 older adults aged 65 and older with complete information on albumin, Hs-CRP and body mass index (BMI) were included in this study. Plasma samples of older adults were collected for the detection of albumin and Hs-CRP at baseline survey. Survival status and follow-up time was recorded for all participants. All older adults were divided into 4 groups according to the levels of plasma albumin and Hs-CRP, and Cox proportional hazard models were constructed to assess their influence on the risk of all-cause mortality. Results: Among 3 118 older adults included, the prevalence of hypoalbuminemia was 10.1% (316/3 118), and was 22.8% (711/3 118) for elevated Hs-CRP. During 10 132 person-years of follow-up, 1 212 participants died. Participants with hypoalbuminemia had increased risk of all-cause mortality, with an hazard ratio (HR) and 95% confidential interval (CI) of 1.18 (1.01-1.38), compared to participants with normal plasma albuminemia; participants with elevated Hs-CRP had increased risk of all-cause mortality, with an HR (95%CI) of 1.18 (1.04-1.35), compared to participants with normal plasma Hs-CRP. Participants with normal plasma albumin and elevated Hs-CRP, with hypoalbuminemia and normal Hs-CRP, with hypoalbuminemia and elevated Hs-CRP also had increased risk of all-cause mortality when compared to those with normal plasma albumin and normal Hs-CRP, the HR (95%CI) were 1.16 (1.01-1.34), 1.11 (0.91-1.37) and 1.43 (1.11-1.83), respectively. Conclusion Hypoalbuminemia and elevated Hs-CRP were responsible for increased risk of 5-year all-cause mortality among Chinese older adults from 8 longevity areas.

Objective To explore the factors related to the consumption of sugar-sweetened beverages (SSB) among middle school students in four provinces (municipality) in China.Methods A total of 3 469 middle school students were recruited from the Children health cohort in eight counties within the four provinces (municipality).We collected information regarding demography,lifestyle,and family and school situation as well as the consumption frequency of SSB in the previous week.High SSB consumption was defined as "positive" if the frequency was once a day or more.Mean consumption time was calculated,and then logistic regressions were performed to explore the factors influencing SSB consumption.Results Prevalence of high SSB consumption was 11.18％ among the subjects of the eight counties,and the consumption frequency of SSB was 0.21 times per day.Multivariate logistic regression analysis revealed that the following factors were associated with high consumption of SSB:higher grade,rural region,male gender,physical exercise,habit of eating snacks,eating out,and fast-food consumption (P＜0.01).Factors influencing high SSB consumption were not completely equal between genders:physical exercise at school was associated with high SSB consumption only in female students (P＜0.01),while higher grade and eating out in the past week were associated with high SSB consumption only in male students (P＜0.05).Conclusion Factors associated with high SSB consumption among middle school students included grade,region,physical exercise at school,snack consumption,eating out,and fast-food consumption.These factors differed between genders.Intervention programs addressing these factors may be beneficial in reducing SSB consumption in middle school students.

Objective To investigate the relationship of plasma albumin and hypersensitive C?reactive protein (Hs?CRP) with 5?year all?cause mortality among Chinese older adults aged 65 and older. Method Data was collected in 8 longevity areas of the Chinese Longitudinal Healthy Longevity Survey (CLHLS) study conducted by Chinese Center for Disease Control and Prevention and Peking University at baseline survey in 2012 and 2014, the participants enrolled in 2012 was followed?up in 2014 and 2017, the participants enrolled in 2014 was followed?up in 2017 only. Finally, 3 118 older adults aged 65 and older with complete information on albumin, Hs?CRP and body mass index (BMI) were included in this study. Plasma samples of older adults were collected for the detection of albumin and Hs?CRP at baseline survey. Survival status and follow?up time was recorded for all participants. All older adults were divided into 4 groups according to the levels of plasma albumin and Hs?CRP, and Cox proportional hazard models were constructed to assess their influence on the risk of all?cause mortality. Results Among 3 118 older adults included, the prevalence of hypoalbuminemia was 10.1% (316/3 118), and was 22.8% (711/3 118) for elevated Hs?CRP. During 10 132 person?years of follow?up, 1 212 participants died. Participants with hypoalbuminemia had increased risk of all?cause mortality, with an hazard ratio (HR) and 95% confidential interval (CI) of 1.18 (1.01-1.38), compared to participants with normal plasma albuminemia; participants with elevated Hs?CRP had increased risk of all?cause mortality, with an HR (95%CI) of 1.18 (1.04-1.35), compared to participants with normal plasma Hs?CRP. Participants with normal plasma albumin and elevated Hs?CRP, with hypoalbuminemia and normal Hs?CRP, with hypoalbuminemia and elevated Hs?CRP also had increased risk of all?cause mortality when compared to those with normal plasma albumin and normal Hs?CRP, the HR (95%CI) were 1.16 (1.01-1.34), 1.11 (0.91-1.37) and 1.43 (1.11-1.83), respectively. Conclusion Hypoalbuminemia and elevated Hs?CRP were responsible for increased risk of 5?year all?cause mortality among Chinese older adults from 8 longevity areas.