Applied artificial intelligence in healthcare: Listening to the winds of change in a post-COVID-19 world

This editorial article aims to highlight advances in artificial intelligence (AI) technologies in five areas: Collaborative AI, Multimodal AI, Human-Centered AI, Equitable AI, and Ethical and Value-based AI in order to cope with future complex socioeconomic and public health issues.     

High-intensity endurance training increases nocturnal heart rate variability in sedentary participants

The effects of endurance training on endurance performance characteristics and cardiac autonomic modulation during night sleep were investigated during two 4-week training periods. After the first 4-week training period (3 x 40 min per week, at 75% of HRR) the subjects were divided into HIGH group (n = 7), who performed three high-intensity endurance training sessions per week; and CONTROL group (n = 8) who did not change their training. An incremental treadmill test was performed before and after the two 4-week training periods. Furthermore, nocturnal RR-intervals were recorded after each training day. In the second 4-week training period HIGH group increased their VO₂max (P = 0.005) more than CONTROL group. At the same time, nocturnal HR decreased (P = 0.039) and high-frequency power (HFP) increased (P = 0.003) in HIGH group while no changes were observed in CONTROL group. Furthermore, a correlation was observed between the changes in nocturnal HFP and changes in VO₂max during the second 4-week training period (r = 0.90, P < 0.001). The present study showed that the increased HFP is related to improved VO₂max in sedentary subjects suggesting that nocturnal HFP can provide a useful method in monitoring individual responses to endurance training.     

Artificial intelligence in the diagnosis of COVID-19: challenges and perspectives

Artificial intelligence (AI) is being used to aid in various aspects of the COVID-19 crisis, including epidemiology, molecular research and drug development, medical diagnosis and treatment, and socioeconomics. The association of AI and COVID-19 can accelerate to rapidly diagnose positive patients. To learn the dynamics of a pandemic with relevance to AI, we search the literature using the different academic databases (PubMed, PubMed Central, Scopus, Google Scholar) and preprint servers (bioRxiv, medRxiv, arXiv). In the present review, we address the clinical applications of machine learning and deep learning, including clinical characteristics, electronic medical records, medical images (CT, X-ray, ultrasound images, etc.) in the COVID-19 diagnosis. The current challenges and future perspectives provided in this review can be used to direct an ideal deployment of AI technology in a pandemic.     

Heart rate dynamics in iNOS knockout mice

Nitric oxide has both an inhibitory and excitatory role in the regulation of pre-ganglionic sympathetic neurons, involving the iNOS and nNOS systems respectively. The aim of the present study was to examine cardiovascular autonomic activity in iNOS knockout mice using spectral analysis of heart rate variability (HRV), and to determine the role of iNOS in altered HRV in endotoxaemia. Electrocardiograms were recorded in anaesthetised mice, and the R-R intervals digitized for spectral analysis of HRV and cardiac rhythm regularity using sample entropy analysis. The basal heart rate was higher in iNOS knockout mice compared with controls (465+/-8 vs 415+/-13 beat/min P<0.05), with a significant increase in the low frequency power of HRV spectra in iNOS knockout mice compared with controls (49.4+/-4.3 vs 33.8+/-5.6 normalized units, P<0.05), consistent with increased cardiac sympathetic activity. Endotoxaemia is known to decrease HRV, but the role of iNOS is unknown. LPS (20 mg/kg i.p) increased basal heart rate in both wild type and iNOS knockout mice, but caused a depression of HRV and sample entropy in both groups. Studies in isolated beating atria showed that the changes of HRV under basal or post-LPS conditions disappeared in vitro, suggesting that the autonomic system is responsible for altered HRV. We conclude that disruption of iNOS gene leads to an increase in the low frequency power of HRV consistent with increased cardiac sympathetic activity. These data also demonstrate that LPS-induced decrease of HRV is independent of iNOS.     

The circadian rhythm of heart rate variability

Purpose: In recent years, the measurement of heart rate variability (HRV) has gained ground even outside research settings in everyday clinical and outpatient practice and in health promotion. Methods: Using the search terms “heart rate variability”, “hrv” and “circadian”, a systematic review was carried out in the PubMed database to find original work that analysed the course of HRV parameters over a 24-h period. Results: A total of 26 original studies were found. Almost all the studies detected a circadian rhythm for the HRV parameters analysed. HRV increased during the night in particular and a nighttime peak during the second half of the night was identified. Conclusions: HRV follows a circadian rhythm. But until today, there isn′t any possibility to make quantitative statements about changes over the course of the day for planning short-term measurements. More qualitative studies must be carried in order to close this knowledge gaps.     

Heart Rate Variability During 24 Hours in Asthmatic Children

The autonomic circadian rhythm plays an important role in asthma. In recent years it has become possible to evaluate autonomic nervous function (ANF) using analysis of heart rate variability (HRV). We analyzed the HRV in the 24h period following the state without an asthma attack in order to study the relationship between asthma and ANF. The HRV was analyzed in 94 asthmatic children (ages 5–15 years). These subjects were divided into groups according to the severity of their asthma. After recording a 24h ambulatory electrocardiograph (AECG), the HRV was analyzed by a computer. Evaluation of the HRV was carried out using time-domain and frequency-domain analyses. The ANF of asthma subjects was decreased in comparison to the normal group. The severity of asthma had a significant effect on the %RR50 (the proportion of cycles during which the difference is > 50 ms), the SD (standard deviation; mean of standard deviation of all normal RR intervals for all 5-minute periods), the low-frequency (LF) band (0.04 to 0.15 Hz), and the high-frequency (HF) band (0.15 to 0.4 Hz) (%RR50: F = 4.31, p = 0.01; SD: F=3.48, p = 0.03; LF: F=3.67, p = 0.02; HF: F=3.41, p = 0.03). These values were lowest in the severe asthma group. With regard to the therapy grouping, the index that exhibited a significant difference was the NNA (mean of normal-to-normal RR intervals over 24h) (F = 4.43, p = 0.01) In conclusion, even in the normal condition in which the patient is free of an asthma attack, the ANF of asthma sufferers differs from that of normal children. It is possible that the different ANF of asthma sufferers is related to the severity of the asthma. (Chronobiology International, 14(6), 597–606, 1997)     

Heart rate variability analysis in revascularized individuals submitted to an anaerobic potency test

The objective of this study was to analyze the behavior of autonomic modulation before, during and after the Modified Wingate Test (WanMT), through the analysis of Heart Rate Variability (HRV). Six volunteers between the ages of 40 and 70, post-revascularization procedures (angioplasty and/or surgery, mean duration 10 months), were submitted to supervised training for at least 10 to 14 months. The following protocol, divided into 5 phases, was used: 1) Rest Phase (RP): 180 seconds; 2) Submaximum Phase (SP): 30 seconds; 3) Maximum Phase (MP): 30 seconds; 4) Active Recuperation Phase (ARP); 120 seconds and; 5) Passive Recuperation Phase (PRP): 180 seconds. For the WanMT Test, we selected the load of 3.75% of corporal weight for all volunteers. To analyze the HRV, we used the following parameters: the interval RRr, MNN, SDNN, RMSSD and PNN50. We only observed results for the group according to RMSSD parameters during the rest phase of the test protocol in which the group remained in vagal presence and during all other phases in vagal depression. However, when we analyzed the PNN50, we observed that the group was in medium vagal presence during all of the phases of the test though there was no statistically significant difference (p> 0.05) between the phases. Therefore, we can say that all of the individuals had a similar profile in the autonomic response to the WanMT, confirmed by the parameters studied in the analysis of the HRV in the time domain.     

Heart rate variability in exercising humans: effect of water immersion

Power spectrum analysis of heart-rate variability was made in seven men [mean age 22 (SEM 1) years] in head-out water immersion (W) and in air (A, control) at rest and during steady-state cycling to maximal intensity (maximum oxygen uptake, V˙O_2max). At rest W resulted in a trebled increase in the total power (P < 0.05), coupled with minimal changes in the power (as a percentage of the total) of the high frequency peak (HF, centred at 0.26 Hz; 18% vs 28%) and of the low frequency peak (LF, 0.1 Hz; 24% vs 32%). A third peak at about 0.03 Hz (very low frequency, VLF) represented the remaining power both in W and A. These changes as a whole indicated that immersion caused a vagal dominance in cardiac autonomic interaction, due to the central pooling of blood and/or the pressure of water on the trunk. Exercise caused a decrease in the total power in W and A. The LF% did not change up to about 50% V˙O_2max, thereafter decreasing towards nil in both conditions. The HF% decreased in similar ways in W and A to about half at 55%–60% V˙O_2max and then increased to reach 1.5 times the resting values at V˙O_2max. The central frequency of HF increased linearly with oxygen uptake, showing a tendency to be higher in W than in A at medium to high intensities. The VLF% remained unchanged. The lack of differences in the LF peak between W and A during exercise would suggest that blood distribution had no effect on the readjustments in control mechanisms of arterial pressure. On the other hand, the findings of similar HF powers and the very similar values for ventilation in W and A confirmed the direct effect of the respiratory activity in heart rate modulation during exercise. Accepted: 25 August 1997     

Heart rate variability in women exposed to very cold air (−110 °C) during whole-body cryotherapy

Heart rate monitoring was used to measure heart rate variability (HRV) at thermoneutral conditions (Ta 24 °C) in healthy women resting in supine position before and after acute and after repeated (3 times a week during a 3-month period) whole-body cryotherapies (WBC), at −110 °C. The observed acute cooling-related increase in high frequency power (HFP) of RR-intervals indicates an increase in cardiac parasympathetic modulation. After 3 months of repeated WBC the increase in parasympathetic tone was attenuated, which may be interpreted as an adaptation of autonomic function. The repeated WBC exposures-related increase in resting low frequency power (LFP) of RR-intervals during the 3 months resembles the response observed related to exercise training.     

心率变异性评估运输应激对Beagle犬自主神经功能的影响

目的 基于心率变异性(heart rate variability,HRV)分析评估运输应激对Beagle犬自主神经功能的影响,并界定其恢复期.方法 16只Beagle犬随机分成两组(每组8只),即对照组和运输应激组,利用大动物无创生理信号遥测技术,分别监测清醒自由活动状态下对照组和运输应激组应激4 h后、恢复1、2、...     

心率与血压的变异性：分析方法,生理意义及其应用

本文回顾了关心回顾变异性及血压变异性的最新进展。在分析方法方面介绍了单一生理变量多变量系统的线性分析技术及其主要结果。对ＨＲＶ／ＢＰＶ谱的生理意义及其应用问题,也进行了回顾了评述。     

Novel artificial intelligence machine learning approaches to precisely predict survival and site-specific recurrence in cervical cancer: A multi-institutional study

BackgroundMachine learning (ML) has been gradually integrated into oncologic research but seldom applied to predict cervical cancer (CC), and no model has been reported to predict survival and site-specific recurrence simultaneously. Thus, we aimed to develop ML models to predict survival and site-specific recurrence in CC and to guide individual surveillance.MethodsWe retrospectively collected data on CC patients from 2006 to 2017 in four hospitals. The survival or recurrence predictive value of the variables was analyzed using multivariate Cox, principal component, and K-means clustering analyses. The predictive performances of eight ML models were compared with logistic or Cox models. A novel web-based predictive calculator was developed based on the ML algorithms.ResultsThis study included 5112 women for analysis (268 deaths, 343 recurrences): (1) For site-specific recurrence, larger tumor size was associated with local recurrence, while positive lymph nodes were associated with distant recurrence. (2) The ML models exhibited better prognostic predictive performance than traditional models. (3) The ML models were superior to traditional models when multiple variables were used. (4) A novel predictive web-based calculator was developed and externally validated to predict survival and site-specific recurrence.ConclusionML models might be a better analytic approach in CC prognostic prediction than traditional models as they can predict survival and site-specific recurrence simultaneously, especially when using multiple variables. Moreover, our novel web-based calculator may provide clinicians with useful information and help them make individual postoperative follow-up plans and further treatment strategies.     

Supine and standing sympathovagal balance in athletes and controls

Differences in autonomic nerve activity between athletes and controls during supine rest and standing were investigated by recording the cardiac rhythm in 18 professional cyclists and 11 controls. We computed four indexes of autonomic control: the standard deviation (SD) of the interbeat intervals, the coefficient of variance (CV) of the interbeat intervals, the percentage of successive intervals differing by more than 50 ms (pNN50), and the fraction low-frequency (0.07–0.14 Hz) spectral power (LF), and we also measured the mean interbeat interval (MI). Significant differences (Student's t-test, P < 0.005) between the athletes and the controls in the supine position were found for pNN50 [mean 52.6 (SEM 2.5) vs 37.1 (SEM 3.4)%], LF [mean 32.2 (SEM 1.6) vs 40.7 (SEM 2.1) normalized units], and MI [mean 1241 (SEM 20) vs 1021 (SEM 25) ms]. A significant difference between the athletes and the controls in the standing position was found for MI [mean 888 (SEM 13) vs 801 (SEM 23) ms]. These results would suggest that there is a parasympathetic predominance in athletes in the supine, but not in the standing position. The finding that pNN50 and LF, but not SD and CV, differed between the athletes and the controls, would seem to demonstrate that the differences in autonomic control between the athletes and the controls are reflected in the quality (balance between slow and fast heart rate fluctuations) rather than in the quantity of heart rate variability.     

Oxidative stress is associated with decreased heart rate variability in patients with chronic kidney disease

Objectives: Elevated oxidative stress and reduced heart rate variability (HRV) is prevalent in patients with chronic kidney disease (CKD) and is associated with increased morbidity and mortality. Previous studies have identified a positive association between elevated oxidative stress and autonomic dysfunction, however this relationship has not yet been investigated in the CKD population.

Methods: Plasma was collected from 78 patients with stage 3–4 CKD (estimated glomerular filtration rate 25–60?ml/min/1.73?m²) for the assessment of oxidative stress, including plasma total F2-isoprostanes, glutathione peroxidase activity and total antioxidant capacity. Time and frequency HRV parameters were measured from a three lead electrocardiogram.

Results: Participants with elevated F2-isoprostanes had reduced HRV compared to patients with normal levels of F2-isoprostanes. A number of HRV parameters were found to be inversely correlated with F2-isoprostanes in all CKD patients, including SDNN (r?=??0.337; P?r?=??0.281, P?=?0.01), LF (r?=??0.315, P?r?=??0.288, P?=?0.01). Multiple linear regression found F2-isoprostanes to be an independent predictor of SDNN (r²?=?0.287, β?=??0.272, P?=?0.01).

Discussion: Oxidative stress is significantly and independently associated with HRV in patients with CKD. Identifying oxidative stress in the pathogenesis of autonomic dysfunction may help target therapeutic strategies.     

2型糖尿病患者心率变异性与心率减速力的相关性及其对自主神经功能的评估价值

目的:探讨2型糖尿病(T2DM)患者心率变异性(HRV)与心率减速力(DC)的相关性及其对自主神经功能的评估价值。方法:选取2018年1月～2019年12月期间合肥市第一人民医院收治的120例T2DM患者为研究对象,纳入实验组,其中单纯T2DM患者69例(单纯T2DM组),T2DM伴周围神经病变(DPN)患者51例(DPN组),另选同期在我院进行心功能检查的健康志愿者120例作为对照组。所有受试者均进行24h动态心电图检查,根据检查结果计算HRV值[总标准差(SDNN)、两个相邻RR间期互差(PNN50)、差值均方根(RMSSD)]和DC值,根据各组受试者的DC值,统计对比各组的猝死风险,并分析T2DM患者DC值与HRV各项指标的相关性。结果:对照组、单纯T2DM组、DPN组的SDNN、PNN50、RMSSD、DC值依次降低(均P0.05)。对照组、单纯T2DM组、DPN组各猝死风险等级分布整体比较差异有统计学意义(P0.05),单纯T2DM组、DPN组猝死高危比例显著高于对照组,且DPN组猝死高危比例高于单纯T2DM组(均P0.05)。经Pearson相关分析,T2DM患者的DC值与SDNN、PNN50、RMSSD呈明显的正相关(P0.05)。结论:T2DM患者的DC值、HRV指标均低于正常人群,合并DPN的T2DM患者猝死风险明显提高,DC值与HRV指标间存在明显的正相关,可作为T2DM患者自主神经功能状态评估的重要指标。     

Autonomic control of heart rate in the neonatal rhesus monkey

Autonomic control of resting heart rate was assessed using atropine and propranolol in 20 neonatal (2 to 3 weeks old) male Rhesus monkeys. After release from restraint for placement of a venous catheter, the average heart rate significantly decreased from 220 +/- 7 beats/min to 181 +/- 6 beats/min within 15 minutes and remained stable for the 2 hours. Autonomic control of resting heart rate is mediated through both divisions of the autonomic nervous system with the sympathetic system having a dominant influence. This is in contrast to the adult Rhesus, where the parasympathetic nervous system controls resting heart rate.     

Impact of heart rate variability,a marker for cardiac health,on lupus disease activity

BackgroundDecreased heart rate variability (HRV) is associated with adverse outcomes in cardiovascular diseases and has been observed in patients with systemic lupus erythematosus (SLE). We examined the relationship of HRV with SLE disease activity and selected cytokine pathways.MethodsFifty-three patients from the Oklahoma Lupus Cohort were evaluated at two visits each. Clinical assessments included the Systemic Lupus Erythematosus Disease Activity Index (SLEDAI), British Isles Lupus Assessment Group (BILAG) index, physician global assessment (PGA), and Safety of Estrogens in Lupus Erythematosus National Assessment-SLEDAI Flare Index. HRV was assessed with a 5-minute electrocardiogram, and the following HRV parameters were calculated: square root of the mean of the squares of differences between adjacent NN intervals (RMSSD), percentage of pairs of adjacent NN intervals differing by more than 50 milliseconds (pNN50), high-frequency power (HF power), and low frequency to high frequency (LF/HF) ratio, which reflects sympathetic/vagal balance. Plasma cytokine levels were measured with a multiplex, bead-based immunoassay. Serum B lymphocyte stimulator (BLyS) and a proliferation-inducing ligand (APRIL) were measured with an enzyme-linked immunosorbent assay. Linear regression analysis was applied.ResultsBaseline HRV (pNN50, HF power, LF/HF ratio) was inversely related to disease activity (BILAG, PGA) and flare. Changes in RMSSD between visits were inversely related to changes in SLEDAI (p = 0.007). Age, caffeine, tobacco and medication use had no impact on HRV. Plasma soluble tumor necrosis factor receptor II (sTNFRII) and monokine induced by interferon gamma (MIG) were inversely related with all baseline measures of HRV (p = 0.039 to <0.001). Plasma stem cell factor (SCF), interleukin (IL)-1 receptor antagonist (IL-1RA), and IL-15 showed similar inverse relationships with baseline HRV, and weaker trends were observed for interferon (IFN)-α, interferon gamma-induced protein (IP)-10, and serum BLyS. Changes in the LF/HF ratio between visits were also associated with changes in sTNFRII (p = 0.021), MIG (p = 0.003), IFN-α (p = 0.012), SCF (p = 0.001), IL-1RA (p = 0.023), and IL-15 (p = 0.010). On the basis of multivariate linear regression, MIG was an independent predictor of baseline HRV after adjusting for plasma IL-1RA, SCF, IFN-α, IP-10, and serum BLyS. In a similar model, the sTNFRII impact remained significant after adjusting for the same variables.ConclusionsImpaired HRV, particularly the LF/HF ratio, is associated with lupus disease activity and several cytokines related to IFN type II and TNF pathways. The strongest association was with MIG and sTNFRII, expanding previous immune connections of vagal signaling.

Electronic supplementary material

The online version of this article (doi:10.1186/s13075-016-1087-x) contains supplementary material, which is available to authorized users.     

Recent trends in stem cell-based therapies and applications of artificial intelligence in regenerative medicine

Stem cells are undifferentiated cells that can self-renew and differentiate into diverse types of mature and functional cells while maintaining their original identity. This profound potential of stem cells has been thoroughly investigated for its significance in regenerative medicine and has laid the foundation for cell-based therapies. Regenerative medicine is rapidly progressing in healthcare with the prospect of repair and restoration of specific organs or tissue injuries or chronic disease conditions where the body’s regenerative process is not sufficient to heal. In this review, the recent advances in stem cell-based therapies in regenerative medicine are discussed, emphasizing mesenchymal stem cell-based therapies as these cells have been extensively studied for clinical use. Recent applications of artificial intelligence algorithms in stem cell-based therapies, their limitation, and future prospects are highlighted.     

Heart rate variability changes in business process outsourcing employees working in shifts

Background and Objectives

Irregular and poor quality sleep is common in business process outsourcing (BPO) employees due to continuous shift working. The influence of this on the cardiac autonomic activity was investigated by the spectral analysis of heart rate variability (HRV).

Methods

36 night shift BPO employees (working from 22:00 to 06:00h) and 36 age and sex matched day shift BPO employees (working from 08:00 to 16:00h) were recruited for the study. Five minute electrocardiogram (ECG) was recorded in all the subjects. Heart rate variability was analyzed by fast Fourier transformation using RMS Vagus HRV software. The results were analyzed using Mann Whitney U test, Student t-test, Wilcoxon signed rank test and were expressed as mean ± SD.

Results

Sleepiness was significantly higher among night shift workers as measured by Epworth Sleepiness Scale (p<0.001). Night shift BPO employees were found to have a trend towards lower values of vagal parameters - HF power (ms²), and higher values of sympathovagal parameters like LF Power (ms²) and the LF/HF power (%) suggesting decreased vagal activity and sympathetic over activity, when compared to day shift employees. However, HRV parameters did not vary significantly between the day shift employees and night shift workers baseline values, and also within the night shift group.

Interpretation and Conclusion

Night shift working increased the heart rate and shifted the sympathovagal balance towards sympathetic dominance and decreased vagal parameters of HRV. This is an indicator of unfavorable change in the myocardial system, and thus shows increased risk of cardiovascular disease among the night shift employees.