Ensemble Extreme Learning Machine Method for Hemoglobin Estimation Based on PhotoPlethysmoGraphic Signals.

Non-invasive detection of hemoglobin (Hb) concentration is of great clinical value for health screening and intraoperative blood transfusion. However, the accuracy and stability of non-invasive detection still need to be improved to meet clinical requirement. This paper proposes a non-invasive Hb detection method using ensemble extreme learning machine (EELM) regression based on eight-wavelength PhotoPlethysmoGraphic (PPG) signals. Firstly, a mathematical model for non-invasive Hb detection based on the Beer-Lambert law is established. Secondly, the captured eight-channel PPG signals are denoised and fifty-six feature values are extracted according to the derived mathematical model. Thirdly, a recursive feature elimination (RFE) algorithm is used to select the features that contribute most to the Hb prediction. Finally, a regression model is built by integrating several independent ELM models to improve prediction stability and accuracy. Experiments conducted on 249 clinical data points (199 cases as the training dataset and 50 cases as the test dataset) evaluate the proposed method, achieving a root mean square error (RMSE) of 1.72 g/dL and a Pearson correlation coefficient (PCC) of 0.76 (p < 0.01) between predicted and reference values. The results demonstrate that the proposed non-invasive Hb detection method exhibits a strong correlation with traditional invasive methods, suggesting its potential for non-invasive detection of Hb concentration.

Does seasonality affect snoring? A study based on international data from the past decade.

BACKGROUND: Though snoring is often regarded as a harmless condition that coincides with sound sleep, it is a sleep disorder that can be a potential indicator of more severe conditions such as sleep apnea syndrome. In the present study, we investigated the association between seasonal variations and snoring. METHOD: Search index for snoring (SIS) data were obtained from Google Trends and Baidu Index. SIS data were collected for the USA, India, Germany, Russia, Japan, Australia, China, and Brazil from 2011 to 2020, with the periodicity of the relationship between seasonal time series data and snoring evaluated using a time series decomposition model. RESULT: The highest average SIS growth rates from 2011 to 2020 were observed for Brazil, Japan, and Germany, with average SIS values of 94%, 68%, and 49%, respectively. The SIS of the USA, Russia, Japan, Brazil, Australia, Germany, and India increased by 22.3%, 12.4%, 11.9%, 35.4%, 12.3%, 28.0%, and 55.8%, respectively, in comparison with their SIS values in 2019, whereas for China, it decreased by 13.7%. Relative to countries in the southern hemisphere, those in the northern hemisphere showed comparable SIS trends, increasing from September to February and decreasing from March to August. CONCLUSION: The SIS data showed cyclical changes over the study period. The search index for snoring increased during the cold season or the heating season, suggesting that snoring is associated with seasonal changes.

Gesture Recognition by Ensemble Extreme Learning Machine Based on Surface Electromyography Signals.

In the recent years, gesture recognition based on the surface electromyography (sEMG) signals has been extensively studied. However, the accuracy and stability of gesture recognition through traditional machine learning algorithms are still insufficient to some actual application scenarios. To enhance this situation, this paper proposed a method combining feature selection and ensemble extreme learning machine (EELM) to improve the recognition performance based on sEMG signals. First, the input sEMG signals are preprocessed and 16 features are then extracted from each channel. Next, features that mostly contribute to the gesture recognition are selected from the extracted features using the recursive feature elimination (RFE) algorithm. Then, several independent ELM base classifiers are established using the selected features. Finally, the recognition results are determined by integrating the results obtained by ELM base classifiers using the majority voting method. The Ninapro DB5 dataset containing 52 different hand movements captured from 10 able-bodied subjects was used to evaluate the performance of the proposed method. The results showed that the proposed method could perform the best (overall average accuracy 77.9%) compared with decision tree (DT), ELM, and random forest (RF) methods.

Prophylaxis of neutropenia with mecapegfilgrastim in patients with non-myeloid malignancies: a real-world study.

BACKGROUND: Chemotherapy-induced neutropenia is commonly encountered in clinical practice. The management of neutropenia has been evolving from short-acting granulocyte colony-stimulating factors (G-CSFs) to long-acting G-CSFs. However, an evaluation of the safety and effectiveness of long-acting G-CSFs in clinical practice is still lacking. METHODS: This multicenter, non-interventional study was aimed at exploring the safety and effectiveness of mecapegfilgrastim in different cancer patients in China. All patients provided written informed consent prior to the study and were treated according to routine clinical practice. Different prophylactic strategies (primary or secondary prophylaxis) were also compared. RESULTS: This study included 638 patients from May 2019 to November 2020. More than half of the participants were breast cancer patients. The mean age of all the patients was 56 years. White blood cell increase (6.2%) was the most frequently reported adverse event (AE) possibly related to the study drug. No unexpected AEs were reported. Grade ≥3 neutropenia in chemotherapy treatment cycle 1 was reported in 36 (5.6%) patients. Incidence of grade ≥3 neutropenia in cycle 1 in the primary and secondary prophylaxis subgroups were of 4.3% and 9.2%, respectively. A decreasing trend of severe neutropenia incidence was observed from cycle 1 to cycle 4. CONCLUSIONS: Mecapegfilgrastim was generally well tolerated, and no unexpected AEs were observed in this study. Primary administration of mecapegfilgrastim led to a lower incidence of neutropenia than did secondary administration. Continuous administration of mecapegfilgrastim could keep the incidence of neutropenia to a relatively low level.

Efficacy and safety of apatinib plus docetaxel as the second or above line treatment in advanced nonsquamous NSCLC: A multi center prospective study.

BACKGROUND: Apatinib is an oral small-molecule tyrosine kinase inhibitor targeting vascular endothelial growth factor receptor 2 (VEGFR-2). Some clinical trials have demonstrated that apatinib is efficacious against advanced nonsquamous NSCLC. OBJECTIVE: This study aimed to probe efficacy and safety of apatinib plus docetaxel, as the second or above line treatment, in advanced nonsquamous NSCLC. DESIGN: Multicenter, prospective, single arm study. SETTING: Three teaching hospitals centers in the Sichuan. PARTICIPANTS: Fourteen patients with stage IVA/B nonsquamous NSCLC had previously received at least 1 platinum-based chemotherapy regimen. INTERVENTION: Patients who were enrolled between November 2016 and January 2018 were given docetaxel (75 mg/m, i.v., d1) plus oral apatinib (250 mg/d), 4 weeks as one cycle, until disease progression or intolerance to adverse events (AE). MAIN OUTCOME MEASURES: The primary endpoint was progression-free survival (PFS). The secondary endpoints comprised objective response rate (ORR), disease control rate (DCR), overall survival (OS), and AE incidence rate. RESULTS: All patients carried adenocarcinoma by pathological type. The median follow-up duration was 9.76 months. Out of 14 cases, 12 were evaluable, showing ORR of 33.33%, DCR of 66.67%, DCR of 50% in cases with brain metastasis, median PFS of 2.92 months (95% CI: 1.38-4.48), and 6-month OS of 80%. Primary AEs encompassed: leukopenia in 7 cases (58.33%), hand-foot skin reaction in 5 cases (41.67%), and diarrhea in 4 cases (33.33%). Among them, grade 3 AEs were: leukopenia in 4 cases (33.33%), and hand-foot skin reaction in 1 case (8.33%). No grade 4/5 AEs were reported. Univariate and multivariate analysis were conducted respectively for PFS and OS. These factors encompassed: gender, age, gene mutations, clinical stage, ECOG scores, quantity of metastatic foci, brain metastasis, and hand-foot skin reaction. Results demonstrated zero risk factors for PFS or OS. CONCLUSION: Apatinib plus docetaxel, as the second or above line treatment, is effective and safe against advanced nonsquamous NSCLC, with good tolerance profile. TRIAL REGISTRATION: NCT03416231.

Cuffless and Continuous Blood Pressure Estimation from the Heart Sound Signals.

Cardiovascular disease, like hypertension, is one of the top killers of human life and early detection of cardiovascular disease is of great importance. However, traditional medical devices are often bulky and expensive, and unsuitable for home healthcare. In this paper, we proposed an easy and inexpensive technique to estimate continuous blood pressure from the heart sound signals acquired by the microphone of a smartphone. A cold-pressor experiment was performed in 32 healthy subjects, with a smartphone to acquire heart sound signals and with a commercial device to measure continuous blood pressure. The Fourier spectrum of the second heart sound and the blood pressure were regressed using a support vector machine, and the accuracy of the regression was evaluated using 10-fold cross-validation. Statistical analysis showed that the mean correlation coefficients between the predicted values from the regression model and the measured values from the commercial device were 0.707, 0.712, and 0.748 for systolic, diastolic, and mean blood pressure, respectively, and that the mean errors were less than 5 mmHg, with standard deviations less than 8 mmHg. These results suggest that this technique is of potential use for cuffless and continuous blood pressure monitoring and it has promising application in home healthcare services.

Validation of new and existing decision rules for the estimation of beat-to-beat pulse transit time.

Pulse transit time (PTT) is a pivotal marker of vascular stiffness. Because the actual PTT duration in vivo is unknown and the complicated variation in waveform may occur, the robust determination of characteristic point is still a very difficult task in the PTT estimation. Our objective is to devise a method for real-time estimation of PTT duration in pulse wave. It has an ability to reduce the interference caused by both high- and low-frequency noise. The reproducibility and performance of these methods are assessed on both artificial and clinical pulse data. Artificial data are generated to investigate the reproducibility with various signal-to-noise ratios. For all artificial data, the mean biases obtained from all methods are less than 1 ms; collectively, this newly proposed method has minimum standard deviation (SD, <1 ms). A set of data from 33 participants together with the synchronously recorded continuous blood pressure data are used to investigate the correlation coefficient (CC). The statistical analysis shows that our method has maximum values of mean CC (0.5231), sum of CCs (17.26), and median CC (0.5695) and has the minimum SD of CCs (0.1943). Overall, the test results in this study indicate that the newly developed method has advantages over traditional decision rules for the PTT measurement.

Time-frequency analysis of heart rate variability during the cold pressor test using a time-varying autoregressive model.

Heart rate variability is a useful clinical tool for autonomic function assessment and cardiovascular disease diagnosis. To investigate the dynamic changes of sympathetic and parasympathetic activities during the cold pressor test, we used a time-varying autoregressive model for the time-frequency analysis of heart rate variability in 101 healthy subjects. We found that there were two sympathetic peaks (or two parasympathetic valleys) when the abrupt changes of temperature (ACT) occurred at the beginning and the end of the cold stimulus and that the sympathetic and parasympathetic activities returned to normal in about the last 2 min of the cold stimulus. These findings suggested that the ACT rather than the low temperature was the major cause of the sympathetic excitation and parasympathetic withdrawal. We also found that the onsets of the sympathetic peaks were 4-26 s prior to the ACT and the returns to normal were 54-57 s after the ACT, which could be interpreted as the feedforward and adaptation of the autonomic regulation process in the human body, respectively. These results might be helpful for understanding the regulatory mechanisms of the autonomic system and its effects on the cardiovascular system.

[The association of paraoxonase 2 gene C311S variant with ischemic stroke in Chinese type 2 diabetes mellitus patients].

OBJECTIVE: To investigate the association between the C311S polymorphism of paraoxonase 2 (PON2) gene and ischemic stroke in Chinese type 2 diabetes mellitus (T2DM) patients. METHODS: A case-control study of 279 Chinese subjects (including 162 T2DM with or without ischemic stroke and 117 non-diabetic control) was performed. Genotype frequencies of C311S polymorphism were studied by polymerase chain reaction-restriction fragment length polymorphism(PCR-RFLP) analysis with DdeI digestion. RESULTS: C311S polymorphism of PON2 gene was detected in Chinese with the C/S allele frequencies 0.145 and 0.855. The frequency distribution showed significant difference between Chinese and Asian Indian. Furthermore, the genotype distribution (SS, CS and CC) of the PON2 C311S gene polymorphism exhibited a significant difference between T2DM patients complicated with ischemic stroke and T2DM without ischemic stroke, the former had a significantly higher C allele frequency(P<0.05). CONCLUSION: The above data indicate that the polymorphism at codon 311(Cys --> Ser)in the PON2 gene is associated with ischemic morbidity in Chinese T2DM patients and C allele might be a risk factor.