Prediction models for lymph node metastasis in cervical cancer based on preoperative heart rate variability.

Background: The occurrence of lymph node metastasis (LNM) is one of the critical factors in determining the staging, treatment and prognosis of cervical cancer (CC). Heart rate variability (HRV) is associated with LNM in patients with CC. The purpose of this study was to validate the feasibility of machine learning (ML) models constructed with preoperative HRV as a feature of CC patients in predicting CC LNM. Methods: A total of 292 patients with pathologically confirmed CC admitted to the Department of Gynecological Oncology of the First Affiliated Hospital of Bengbu Medical University from November 2020 to September 2023 were included in the study. The patient' preoperative 5-min electrocardiogram data were collected, and HRV time-domain, frequency-domain and non-linear analyses were subsequently performed, and six ML models were constructed based on 32 parameters. Model performance was assessed using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity. Results: Among the 6 ML models, the random forest (RF) model showed the best predictive performance, as specified by the following metrics on the test set: AUC (0.852), accuracy (0.744), sensitivity (0.783), and specificity (0.785). Conclusion: The RF model built with preoperative HRV parameters showed superior performance in CC LNM prediction, but multicenter studies with larger datasets are needed to validate our findings, and the physiopathological mechanisms between HRV and CC LNM need to be further explored.

Value of dual-layer spectral detector CT in predicting lymph node metastasis of non-small cell lung cancer.

Background: The accurate assessment of lymph node metastasis (LNM) is crucial for the staging, treatment, and prognosis of lung cancer. In this study, we explored the potential value of dual-layer spectral detector computed tomography (SDCT) quantitative parameters in the prediction of LNM in non-small cell lung cancer (NSCLC). Methods: In total, 91 patients presenting with solid solitary pulmonary nodules (8 mm < diameter ≤30 mm) with pathologically confirmed NSCLC (57 without LNM, and 34 with LNM) were enrolled in the study. The patients' basic clinical data and the SDCT morphological features were analyzed using the chi-square test or Fisher's exact test. The Mann-Whitney U-test and independent sample t-test were used to analyze the differences in multiple SDCT quantitative parameters between the non-LNM and LNM groups. The diagnostic efficacy of the corresponding parameters in predicting LNM in NSCLC was evaluated by plotting the receiver operating characteristic (ROC) curves. A multivariate logistic regression analysis was conducted to determine the independent predictive factors of LNM in NSCLC. Interobserver agreement was assessed using intraclass correlation coefficients (ICCs) and Bland-Altman plots. Results: There were no significant differences between the non-LNM and LNM groups in terms of age, sex, and smoking history. Lesion size and vascular convergence sign differed significantly between the two groups (P<0.05), but there were no significant differences in the six tumor markers. The SDCT quantitative parameters [SAR40keV, SAR70keV, Δ40keV, Δ70keV, CER40keV, CER70keV, NEF40keV, NEF70keV, λ, normalized iodine concentration (NIC) and NZeff] were significantly higher in the non-LNM group than the LNM group (P<0.05). The ROC analysis showed that CER40keV, NIC, and CER70keV had higher diagnostic efficacy than other quantitative parameters in predicting LNM [areas under the curve (AUCs) =0.794, 0.791, and 0.783, respectively]. The multivariate logistic regression analysis showed that size, λ, and NIC were independent predictive factors of LNM. The combination of size, λ, and NIC had the highest diagnostic efficacy (AUC =0.892). The interobserver repeatability of the SDCT quantitative and derived quantitative parameters in the study was good (ICC: 0.801-0.935). Conclusions: The SDCT quantitative parameters combined with the clinical data have potential value in predicting LNM in NSCLC. The size + λ + NIC combined parameter model could further improve the prediction efficacy of LNM.

Multimodal Gait Abnormality Recognition Using a Convolutional Neural Network-Bidirectional Long Short-Term Memory (CNN-BiLSTM) Network Based on Multi-Sensor Data Fusion.

Global aging leads to a surge in neurological diseases. Quantitative gait analysis for the early detection of neurological diseases can effectively reduce the impact of the diseases. Recently, extensive research has focused on gait-abnormality-recognition algorithms using a single type of portable sensor. However, these studies are limited by the sensor's type and the task specificity, constraining the widespread application of quantitative gait recognition. In this study, we propose a multimodal gait-abnormality-recognition framework based on a Convolutional Neural Network-Bidirectional Long Short-Term Memory (CNN-BiLSTM) network. The as-established framework effectively addresses the challenges arising from smooth data interference and lengthy time series by employing an adaptive sliding window technique. Then, we convert the time series into time-frequency plots to capture the characteristic variations in different abnormality gaits and achieve a unified representation of the multiple data types. This makes our signal processing method adaptable to several types of sensors. Additionally, we use a pre-trained Deep Convolutional Neural Network (DCNN) for feature extraction, and the consequently established CNN-BiLSTM network can achieve high-accuracy recognition by fusing and classifying the multi-sensor input data. To validate the proposed method, we conducted diversified experiments to recognize the gait abnormalities caused by different neuropathic diseases, such as amyotrophic lateral sclerosis (ALS), Parkinson's disease (PD), and Huntington's disease (HD). In the PDgait dataset, the framework achieved an accuracy of 98.89% in the classification of Parkinson's disease severity, surpassing DCLSTM's 96.71%. Moreover, the recognition accuracy of ALS, PD, and HD on the PDgait dataset was 100%, 96.97%, and 95.43% respectively, surpassing the majority of previously reported methods. These experimental results strongly demonstrate the potential of the proposed multimodal framework for gait abnormality identification. Due to the advantages of the framework, such as its suitability for different types of sensors and fewer training parameters, it is more suitable for gait monitoring in daily life and the customization of medical rehabilitation schedules, which will help more patients alleviate the harm caused by their diseases.

Prognostic role of short-term heart rate variability and deceleration/acceleration capacities of heart rate in extensive-stage small cell lung cancer.

Background: Prior research suggests that autonomic modulation investigated by heart rate variability (HRV) might act as a novel predictive biomarker for cancer prognosis, such as in breast cancer and pancreatic cancer. It is not clear whether there is a correlation between autonomic modulation and prognosis in patients with extensive-stage small cell lung cancer (ES-SCLC). Therefore, the purpose of the study was to examine the association between short-term HRV, deceleration capacity (DC) and acceleration capacity (AC) of heart rate and overall survival in patients with ES-SCLC. Methods: We recruited 40 patients with ES-SCLC, and 39 were included in the final analysis. A 5-min resting electrocardiogram of patients with ES-SCLC was collected using a microelectrocardiogram recorder to analyse short-term HRV, DC and AC. The following HRV parameters were used: standard deviation of the normal-normal intervals (SDNN) and root mean square of successive interval differences (RMSSD). Overall survival of patients with ES-SCLC was defined as time from the date of electrocardiogram measurement to the date of death or the last follow-up. Follow-up was last performed on 07 June 2023. There was a median follow-up time of 42.2 months. Results: Univariate analysis revealed that the HRV parameter SDNN, as well as DC significantly predicted the overall survival of ES-SCLC patients (all p < 0.05). Multivariate analysis showed that the HRV parameters SDNN (hazard ratio = 5.254, 95% CI: 1.817-15.189, p = 0.002), RMSSD (hazard ratio = 3.024, 95% CI: 1.093-8.372, p = 0.033), as well as DC (hazard ratio = 3.909, 95% CI: 1.353-11.293, p = 0.012) were independent prognostic factors in ES-SCLC patients. Conclusion: Decreased HRV parameters (SDNN, RMSSD) and DC are independently associated with shorter overall survival in ES-SCLC patients. Autonomic nervous system function (assessed based on HRV and DC) may be a new biomarker for evaluating the prognosis of patients with ES-SCLC.

Assessment of short-term effects of thoracic radiotherapy on the cardiovascular parasympathetic and sympathetic nervous systems.

Background: Prior research suggests that cardiovascular autonomic dysfunction might be an early marker of cardiotoxicity induced by antitumor treatment and act as an early predictor of cardiovascular disease-related morbidity and mortality. The impact of thoracic radiotherapy on the parasympathetic and sympathetic nervous systems, however, remains unclear. Therefore, this study aimed to evaluate the short-term effects of thoracic radiotherapy on the autonomic nervous system, using deceleration capacity (DC), acceleration capacity (AC) of heart rate, and heart rate variability (HRV) as assessment tools. Methods: A 5 min electrocardiogram was collected from 58 thoracic cancer patients before and after thoracic radiotherapy for DC, AC, and HRV analysis. HRV parameters employed included the standard deviation of the normal-normal interval (SDNN), root mean square of successive interval differences (RMSSD), low frequency power (LF), high frequency power (HF), total power (TP), and the LF to HF ratio. Some patients also received systemic therapies alongside radiotherapy; thus, patients were subdivided into a radiotherapy-only group (28 cases) and a combined radiotherapy and systemic therapies group (30 cases) for additional subgroup analysis. Results: Thoracic radiotherapy resulted in a significant reduction in DC (8.5 [5.0, 14.2] vs. 5.3 [3.5, 9.4], p = 0.002) and HRV parameters SDNN (9.9 [7.03, 16.0] vs. 8.2 [6.0, 12.4], p = 0.003), RMSSD (9.9 [6.9, 17.5] vs. 7.7 [4.8, 14.3], p = 0.009), LF (29 [10, 135] vs. 24 [15, 50], p = 0.005), HF (35 [12, 101] vs. 16 [9, 46], p = 0.002), TP (74 [41, 273] vs. 50 [33, 118], p < 0.001), and a significant increase in AC (-8.2 [-14.8, -4.9] vs. -5.8 [-10.1, -3.3], p = 0.003) and mean heart rate (79.8 ± 12.6 vs. 83.9 ± 13.6, p = 0.010). Subgroup analysis indicated similar trends in mean heart rate, DC, AC, and HRV parameters (SDNN, RMSSD, LF, HF, TP) in both the radiotherapy group and the combined treatment group post-radiotherapy. No statistically significant difference was noted in the changes observed in DC, AC, and HRV between the two groups pre- and post-radiotherapy. Conclusion: Thoracic radiotherapy may induce cardiovascular autonomic dysfunction by reducing parasympathetic activity and enhancing sympathetic activity. Importantly, the study found that the concurrent use of systemic therapies did not significantly amplify or contribute to the alterations in autonomic function in the short-term following thoracic radiotherapy. DC, AC and HRV are promising and feasible biomarkers for evaluating autonomic dysfunction caused by thoracic radiotherapy.

Early detection of the impact of combined taxane and carboplatin treatment on autonomic nerves in patients with cervical cancer: Measurement of heart rate variability.

Background: Previous studies have shown that heart rate variability (HRV) analysis is a sensitive indicator of chemotherapy-induced cardiotoxicity. However, most studies to date have observed long-term effects using long-term analyses. The main purpose of this study was to evaluate the acute effect of chemotherapy on the cardiac autonomic nervous system (ANS) in patients with cervical cancer (CC) by examining short-term HRV. Methods: Fifty patients with CC admitted to the Department of Gynecology and Oncology of the First Affiliated Hospital of Bengbu Medical College were enrolled in the study. Based on their chemotherapy regimens, the patients were divided into a DC group (docetaxel + carboplatin) and a TC group (paclitaxel + carboplatin). A 5-min resting electrocardiogram (ECG) was collected before and the day after chemotherapy: the time domain (standard deviation of normal-to-normal intervals (SDNN) and root mean square of successive differences (RMSSD)) and frequency domain (low-frequency power (LF), high-frequency power (HF), and (LF/HF)) parameters were analyzed, and the differences before and after chemotherapy were compared. Results: The results showed that SDNN, RMSSD and HF were significantly higher in the DC and TC groups after chemotherapy than before (p < 0.05, Cohen's d > 0.5). In addition, LF was significantly higher after TC than before chemotherapy (p < 0.05, Cohen's d > 0.3), and LF/HF was significantly lower after DC than before chemotherapy (p < 0.05, Cohen's d > 0.5). Conclusion: Chemotherapy combining taxane and carboplatin can increase the HRV of CC patients in the short term, and HRV may be a sensitive tool for the early detection of chemotherapy-induced cardiac ANS perturbations.

Non-invasive prognostic biomarker of lung cancer patients with brain metastases: Recurrence quantification analysis of heart rate variability.

Background: It has previously been shown that the time-domain characteristic of heart rate variability (HRV) is an independent prognostic factor for lung cancer patients with brain metastasis (LCBM). However, it is unclear whether the nonlinear dynamic features contained in HRV are associated with prognosis in patients with LCBM. Recurrence quantification analysis (RQA) is a common nonlinear method used to characterize the complexity of heartbeat interval time series. This study was aimed to explore the association between HRV RQA parameters and prognosis in LCBM patients. Methods: Fifty-six LCBM patients from the Department of Radiation Oncology, the First Affiliated Hospital of Bengbu Medical College, were enrolled in this study. Five-minute ECG data were collected by a mini-ECG recorder before the first brain radiotherapy, and then heartbeat interval time series were extracted for RQA. The main parameters included the mean diagonal line length (Lmean), maximal diagonal line length (Lmax), percent of recurrence (REC), determinism (DET) and Shannon entropy (ShanEn). Patients were followed up (the average follow-up time was 19.2 months, a total of 37 patients died), and the relationships between the RQA parameters and survival of LCBM patients were evaluated by survival analysis. Results: The univariate analysis showed that an Lmax of >376 beats portended worse survival in LCBM patients. Multivariate Cox regression analysis revealed that the Lmax was still an independent prognostic factor for patients with LCBM after adjusting for confounders such as the Karnofsky performance status (KPS) (HR = 0.318, 95% CI: 0.151-0.669, p = 0.003). Conclusion: Reduced heartbeat complexity indicates a shorter survival time in patients with LCBM. As a non-invasive biomarker, RQA has the potential for application in evaluating the prognosis of LCBM patients.

Low Heart Rate Variability Predicts Poor Overall Survival of Lung Cancer Patients With Brain Metastases.

BACKGROUND: The aim of this prospective study was to evaluate the association between heart rate variability (HRV) and overall survival of lung cancer patients with brain metastases (LCBM). METHODS: Fifty-six LCBM patients were enrolled in this study. Five-minute electrocardiograms were collected before the time to first brain radiotherapy. HRV was analyzed quantitatively by using the time domain parameters, i.e., the standard deviation of all normal-normal intervals (SDNN) and the root mean square of successive differences (RMSSD). Survival time for LCBM patients was defined as from the date of HRV testing to the date of death or the last follow-up. RESULTS: In the univariate analysis, SDNN ≤ 13 ms (P = 0.003) and RMSSD ≤ 4.8 ms (P = 0.014) significantly predicted poor survival. Multivariate analysis confirmed that RMSSD ≤ 4.8 ms (P = 0.013, hazard ratio = 3.457, 95% confidence interval = 1.303-9.171) was also an independent negative prognostic factor after adjusting for mean heart rate, Karnofsky performance status, and number of brain metastases in LCBM patients. CONCLUSION: Decreased RMSSD is independently associated with shorter survival time in LCBM patients. HRV might be a novel predictive biomarker for LCBM prognosis.

Critical phenomenon in the room-temperature ferromagnet Ce0.65Mg0.35Co3 prepared by high-pressure annealing.

Numerous studies have showed evidence that high-pressure annealing (HPA) can modify the crystal and electronic structure significantly, which thus probably alters the magnetic ordering with a different universality class. In this work, we investigate the effects of HPA on the critical behaviors of magnetization in a room-temperature ferromagnet Ce0.65Mg0.35Co3. We observe the HPA compound after annealing at 2 GPa undergoing a second-order phase transition with a decreased Curie temperature. Using the DC magnetization data, the critical exponents ß, γ and δ are calculated independently by three methods including the modified Arrott plot, the Kouvel-Fisher plot, and critical isotherm analysis. The obtained critical parameters together with the magnetization data obey the scaling equation of state, indicating that they are intrinsic and unambiguous. Furthermore, we notice that HPA not only reduces the intensity of exchange coupling, but also elongates the exchange range with J(r) ∼r-4.467, which leads to a universality class different from that of the conventional compound and the existing theoretical models.