
Dr Kiran Kumar Guruswamy Ravindran
Academic and research departments
Surrey Sleep Research Centre, Department of Clinical and Experimental Medicine, School of Biosciences, Faculty of Health and Medical Sciences.About
Biography
Currently I am working towards understanding the qualitative nature of sleep physiology in older adults using signal processing and machine learning tools.
Check out my Web of Science Researcher Profile here or one of the other profiles and website links above for more info on my publications and peer review work.
Areas of specialism
My qualifications
News
In the media
ResearchResearch interests
- Sleep Electrophysiology
- Dementia
- Digital health
- Sleep technology evaluation (Wearables and Contactless sleep technologies)
- Signal Processing and Subspace learning
- Artificial Intelligence
- Brain computer interfaces (SSVEP)
Indicators of esteem
Awarded the UK Dementia Research Institute (UK DRI) Pilot Award (Feb 2023) for my Project titled ‘Developing Tools for Round-the-Clock Monitoring of Sleep and Vital Signs in Community Dwelling Older Adults Using High Sampling Rate Inertial Measurement Units’. UK DRI Pilot Award is an initiative designed to encourage UK DRI early career researchers to take the next step towards forming an independent lab group, and consider new and innovative avenues of research aimed at treating or advancing understanding of dementia.
Awarded the ‘Prof S Radhakrishnan Award for best PhD Thesis in Biomedical Engineering, Oct 2020’ during the 57th Convocation of Indian Institute of Technology (IIT) Madras.
Awarded the ‘Institute Research Award 2019-20’ as a recognition of Quality and Quantity of Research work done during my MS-PhD degree at the Indian Institute of Technology (IIT) Madras.
Research interests
- Sleep Electrophysiology
- Dementia
- Digital health
- Sleep technology evaluation (Wearables and Contactless sleep technologies)
- Signal Processing and Subspace learning
- Artificial Intelligence
- Brain computer interfaces (SSVEP)
Indicators of esteem
Awarded the UK Dementia Research Institute (UK DRI) Pilot Award (Feb 2023) for my Project titled ‘Developing Tools for Round-the-Clock Monitoring of Sleep and Vital Signs in Community Dwelling Older Adults Using High Sampling Rate Inertial Measurement Units’. UK DRI Pilot Award is an initiative designed to encourage UK DRI early career researchers to take the next step towards forming an independent lab group, and consider new and innovative avenues of research aimed at treating or advancing understanding of dementia.
Awarded the ‘Prof S Radhakrishnan Award for best PhD Thesis in Biomedical Engineering, Oct 2020’ during the 57th Convocation of Indian Institute of Technology (IIT) Madras.
Awarded the ‘Institute Research Award 2019-20’ as a recognition of Quality and Quantity of Research work done during my MS-PhD degree at the Indian Institute of Technology (IIT) Madras.
Publications
Background: Contactless sleep technologies (CSTs) hold promise for longitudinal, unobtrusive sleep monitoring in health and disease at scale, particularly in older people where the increased incidence of sleep abnormalities with aging is considered a risk factor for several neurodegenerative disorders. However, few CST have been evaluated in older people. Objective: To evaluate the performance of three contactless sleep technologies (a bedside radar [Somnofy] and two under-mattress devices [Withings Sleep Analyser and Emfit-QS]) compared to polysomnography (PSG) and actigraphy [Actiwatch Spectrum] recorded during a first night in a sleep laboratory, 10-hour time in bed protocol, which induced mild sleep disturbance. Methods: Thirty-five older men and women (70.8±4.9 years; 14 women) several of whom had comorbidities and/or sleep apnoea, participated in the study. Devices were evaluated by estimating a range of performance metrics for classification of sleep vs wake, and NREM and REM sleep stages (sleep summary and epoch by epoch concordance) and comparing to PSG metrics. Results: All three CSTs overestimated total sleep time (bias [mean]: > 90 min) and sleep efficiency (bias: > 13 %) with an associated underestimation of wake after sleep onset (bias: > 50 min). Sleep onset latency was accurately detected by the bedside radar (bias: 16 mins). CSTs did not perform as well as actigraphy in estimating the all-night sleep summary measures. The bedside radar performed better in discriminating sleep vs wake (MCC [mean and 95% CI]: 0.63 [0.57 0.69]) than the under-mattress devices (MCC: =0.41 [0.36 0.46]; Emfit-QS =0.35 [0.26 0.43]). Accuracy of identifying REM and Light sleep was poor across all CSTs while deep sleep was predicted with moderate accuracy (MCC: >0.45) by both Somnofy and Withings Sleep Analyser. The deep sleep duration estimates of Somnofy was found to be significantly correlated (r2=0.6, p
Study Objectives To compare the 24-hour sleep assessment capabilities of two contactless sleep technologies (CSTs) to actigraphy in community-dwelling older adults. Methods We collected 7–14 days of data at home from 35 older adults (age: 65–83), some with medical conditions, using Withings Sleep Analyser (WSA, n = 29), Emfit QS (Emfit, n = 17), a standard actigraphy device (Actiwatch Spectrum [AWS, n = 34]), and a sleep diary (n = 35). We compared nocturnal and daytime sleep measures estimated by the CSTs and actigraphy without sleep diary information (AWS-A) against sleep-diary-assisted actigraphy (AWS|SD). Results Compared to sleep diary, both CSTs accurately determined the timing of nocturnal sleep (intraclass correlation [ICC]: going to bed, getting out of bed, time in bed >0.75), whereas the accuracy of AWS-A was much lower. Compared to AWS|SD, the CSTs overestimated nocturnal total sleep time (WSA: +92.71 ± 81.16 minutes; Emfit: +101.47 ± 75.95 minutes) as did AWS-A (+46.95 ± 67.26 minutes). The CSTs overestimated sleep efficiency (WSA: +9.19% ± 14.26%; Emfit: +9.41% ± 11.05%), whereas AWS-A estimate (−2.38% ± 10.06%) was accurate. About 65% (n = 23) of participants reported daytime naps either in bed or elsewhere. About 90% in-bed nap periods were accurately determined by WSA while Emfit was less accurate. All three devices estimated 24-hour sleep duration with an error of ≈10% compared to the sleep diary. Conclusions CSTs accurately capture the timing of in-bed nocturnal sleep periods without the need for sleep diary information. However, improvements are needed in assessing parameters such as total sleep time, sleep efficiency, and naps before these CSTs can be fully utilized in field settings.
Background Nocturnal disturbance is frequently observed in dementia and is a major contributor to institutionalisation. Unobtrusive technology that can quantify sleep/wake and determine bed occupancy during the major nocturnal sleep episode may be beneficial for long-term clinical monitoring and the carer. Such technologies have, however, not been validated in older people. Here we assessed the performance of the Withings Sleep Mattress (WSM) in a heterogenous older population to ensure external validity. Method Eighteen participants (65 – 80 years, 10M:8F) completed 7-12 days of sleep/wake monitoring at home prior to an overnight laboratory session. WSM performance was compared to gold-standard (laboratory polysomnography [PSG] with video) and silver standard (actiwatch [AWS] and sleep diary at home). WSM data were downloaded from a third party API and the minute-to-minute sleep/wake timeseries extracted and time-ordered to create a sleep profile. Discontinuities in the timeseries were labelled as ‘missing data’ events. Results Participants contributed 107 nights with WSM and PSG or AWS data. In the laboratory, the overall epoch to epoch agreement (accuracy) of sleep/wake detection of WSM compared to PSG was 0.71 (sensitivity 0.8; specificity 0.45) and to AWS was 0.74 (sensitivity 0.77; specificity 0.53). Visual inspection of video recordings demonstrated that 20 of 21 ‘missing data’ events were true ‘out of bed’ events. These events were always associated with an increase in activity (AWS). At home, all 97 WSM ‘missing data’ events that occurred within the major nocturnal sleep episode defined by sleep diary data, were associated with an increase in activity levels in the AWS data and 36 of these events were also associated with an increase in light levels, indicating that the participant had left the bed. In several participants, data recorded by the WSM during daytime coincided with reported naps in the sleep diary. Conclusion Although WSM cannot reliably distinguish between sleep and wake, the presence/absence of data in WSM seem to be an accurate representation of whether older people are in or out of bed (bed occupancy). Thus, in dementia, this contactless, low-burden technology may be able to provide information about nocturnal disturbances and daytime naps in bed.
Background The incidence of sleep disturbances increases with normal aging and is highly prevalent among people living with dementia (PLWD). To facilitate management and improvement of sleep quality in PLWD, validated unintrusive contactless technologies for long term objective monitoring of sleep are needed. Here we evaluate the ability of a contactless sleep tracker to accurately determine Time in Bed (TIB), Wake vs Sleep and Sleep stages (wake, light, deep, and REM sleep). Method We deployed the Emfit (Emfit QS), a contactless sleep tracker placed under the mattress. The Emfit uses ballistography to estimate respiration and heart rate and sleep stages. We collected data from 16 participants (Age: Mean‐72.12; SD‐4.6 years [6F:10M]) at home for a 14‐day period followed by a single overnight laboratory polysomnography (PSG) sleep assessment. The Emfit outputs a) timeseries at 30 s intervals (four sleep stages) and b) overnight summary sleep parameters. Sleep staging and sleep parameter estimation by Emfit was compared to, a) in‐lab gold standard PSG, and b) at‐home wristworn accelerometer (Actiwatch spectrum (AWS)) and sleep diary (SD) data. The epoch‐to‐epoch sleep staging concordance of Emfit was estimated over the total recording interval (∼10hrs) of the PSG for the laboratory session and between 1800hrs and 1200hrs for each SD entry for the home recordings. The concordance analysis for the sleep parameters, bed entry and exit times were performed using the summary data automatically generated by Emfit. Result The concordance between the four‐class sleep staging of the Emfit and PSG was poor (Figure 1). The two class (sleep/wake) analysis (Table 1) showed high sleep classification accuracy (sensitivity) but poor wake classification accuracy (specificity) compared to PSG. The sleep parameter estimates of Emfit also showed poor agreement with PSG (Figure 2). The home analysis indicated excellent accuracy for Time in Bed (TIB) (i.e., the bed entry and exit times) as registered by the SD (Table 2) and total sleep time (TST) for both sleep diary and AWS (Figure 3). Conclusion : The contactless sleep tracker provides accurate information about Time in Bed (TIB), but there is a lack of consensus of the sleep state classification with the PSG.
Recently, filter bank analysis has been used in several detection methods to extract selective frequency features across multiple brain computer interface (BCI) modalities due to its effectiveness and simple structure. In this work, we propose filter bank technique as a standard preprocessing method for popular training free multi-channel steady-state visual evoked potential (SSVEP) detection methods to overcome subject-specific performance differences and a general improvement in detection accuracy. Our study validates the effectiveness of filter bank extensions by comparing performance differences of multichannel methods with their filter bank counterparts using a forty target SSVEP benchmark dataset collected across thirty five subjects. The results demonstrate that the proposed two stage (a filter bank stage followed by SSVEP detection) implementation of popular multichannel algorithms provide significant improvement in performance at short datalengths of < 2.75 s (p < 0.001) and can be viewed as a potential standard detection approach across all SSVEP identification problems.
Study Objective: To compare the 24-hour sleep assessment capabilities of two contactless sleep technologies (CSTs) to actigraphy in community-dwelling older adults. Methods: We collected 7 to 14 days of data at home from 35 older adults (age: 65-83), some with medical conditions, using Withings Sleep Analyser (WSA, n=29), Emfit-QS (Emfit, n=17), a standard actigraphy device (Actiwatch Spectrum [AWS, n=34]) and a sleep diary. We compared nocturnal and daytime sleep measures estimated by the CSTs and actigraphy without sleep diary information (AWS-A) against sleep diary assisted actigraphy (AWS|SD). Results: Compared to sleep diary, both CSTs accurately determined the timing of nocturnal sleep (ICC: going to bed, getting out of bed, time in bed > 0.75) whereas the accuracy of AWSA was much lower. Compared to AWS|SD, the CSTs overestimated nocturnal total sleep time (WSA: +92.71±81.16 min; Emfit: +101.47±75.95 min) as did AWS-A (+46.95±67.26 min). The CSTs overestimated sleep efficiency (WSA: +9.19±14.26 %; Emfit: +9.41±11.05 %) whereas AWS-A estimate (-2.38±10.06 %) was accurate. About 65% (n=23) of participants reported daytime naps either in-bed or elsewhere. About 90% in-bed nap periods were accurately determined by WSA while Emfit was less accurate. All three devices estimated 24-h sleep duration with an error of ≈10% compared to the sleep diary. Conclusions: CSTs accurately capture the timing of in-bed nocturnal sleep periods without the need for sleep diary information. However, improvements are needed in assessing parameters such as total sleep time, sleep efficiency and naps before these CSTs can be fully utilized in field settings. Statement of Significance: Contactless sleep technologies that do not pose a burden on participants are promising tools for longitudinal monitoring of sleep in the community. In a comparison with sleep diary assisted actigraphy, we show that two under-mattress devices used without sleep diary information, provide accurate information on nocturnal sleep timing and 24-hr bed presence. The study population comprised community-dwelling older adults, several of whom had medical conditions such as sleep apnea, arthritis, and type-2 diabetes, which adds to the relevance of these data. With further improvements in their performance, these unobtrusive sleep technologies have significant potential for at scale and longitudinal monitoring of 24-h sleep-wake patterns in older adults without the burden of completing sleep diaries.
Several cellular pathways contribute to neurodegenerative tauopathy-related disorders. Microglial activation, a major component of neuroinflammation, is an early pathological hallmark that correlates with cognitive decline, while the unfolded protein response (UPR) contributes to synaptic pathology. Sleep disturbances are prevalent in tauopathies and may also contribute to disease progression. Few studies have investigated whether manipulations of sleep influence cellular pathological and behavioural features of tauopathy. We investigated whether trazodone, a licensed antidepressant with hypnotic efficacy in dementia, can reduce disease-related cellular pathways and improve memory and sleep in male rTg4510 mice with a tauopathy-like phenotype. In a 9-week dosing regimen, trazodone decreased microglial NLRP3 inflammasome expression and phosphorylated p38mitogen-activated protein kinase levels which correlated with the NLRP3 inflammasome, the UPR effector ATF4, and total tau levels. Trazodone reduced theta oscillations during REM sleep and enhanced rapid eye movement (REM) sleep duration. Olfactory memory transiently improved, and memory performance correlated with REM sleep duration and theta oscillations. These findings on the effects of trazodone on the NLRP3 inflammasome, the unfolded protein response and behavioural hallmarks of dementia warrant further studies on the therapeutic value of sleep-modulating compounds for tauopathies.
Traditional spatial filters used for steady-state visual evoked potential (SSVEP) extraction such as minimum energy combination (MEC) require the estimation of the background electroencephalogram (EEG) noise components. Even though this leads to improved performance in low signal to noise ratio (SNR) conditions, it makes such algorithms slow compared to the standard detection methods like canonical correlation analysis (CCA) due to the additional computational cost. In this paper, Periodic component analysis (πCA) is presented as an alternative spatial filtering approach to extract the SSVEP component effectively without involving extensive modelling of the noise. The πCA can separate out components corresponding to a given frequency of interest from the background electroencephalogram (EEG) by capturing the temporal information and does not generalize SSVEP based on rigid templates. Data from ten test subjects were used to evaluate the proposed method and the results demonstrate that the periodic component analysis acts as a reliable spatial filter for SSVEP extraction. Statistical tests were performed to validate the results. The experimental results show that πCA provides significant improvement in accuracy compared to standard CCA and MEC in low SNR conditions. The results demonstrate that πCA provides better detection accuracy compared to CCA and on par with that of MEC at a lower computational cost. Hence πCA is a reliable and efficient alternative detection algorithm for SSVEP based brain-computer interface (BCI).
Objective. This study introduces and evaluates a novel target identification method, latent common source extraction (LCSE), that uses subject-specific training data for the enhancement of detection of steady-state visual evoked potential (SSVEP). Approach. LCSE seeks to construct a common latent representation of the SSVEP signal subspace that is stable across multiple trials of electroencephalographic (EEG) data. The spatial filter thus obtained improves the signal-to-noise ratio (SNR) of the SSVEP components by removing nuisance signals that are irrelevant to the generalized signal representation learnt from the given data. In this study a comparison of SSVEP identification performance between the proposed method, extended canonical correlation analysis (ExtCCA) and multiset canonical correlation analysis (MsetCCA) was conducted using SSVEP benchmark data of 40 targets recorded from 35 subjects to validate the effectiveness of the LCSE framework. Main results. The results indicate that the LCSE framework significantly outperforms the other two methods in terms of both classification accuracy and information transfer rates (ITRs). Significance. The significant improvement in the target identification performance demonstrates that the proposed LCSE method can be seen as a promising potential candidate for efficient SSVEP detection in brain-computer interface (BCI) systems.
This study illustrates and evaluates a novel subject-specific target detection framework, sum of squared correlations (SSCOR), for improving the performance of steady-state visual evoked potential (SSVEP) based brain-computer interfaces (BCIs). The SSCOR spatial filter learns a common SSVEP representation space through the optimization of the individual SSVEP templates. The projection onto this SSVEP response subspace improves the signal to noise ratio (SNR) of the SSVEP components embedded in the recorded electroencephalographic (EEG) data. To demonstrate the effectiveness of the proposed framework, the target detection performance of the SSCOR method is compared with the state of the art task-related component analysis (TRCA). The evaluation is conducted on a 40 target SSVEP benchmark data collected from 35 subjects. The results of the extensive comparisons of the performance metrics show that the proposed SSCOR method outperforms the TRCA method. The ensemble version of the SSCOR framework provides an offline simulated information transfer rate (ITR) of 387 ± 9 bits/min which is much higher than that of the ensemble TRCA approach (max. ITR 216 ± 27 bits/min). The significant improvement in the detection accuracy and simulated ITR demonstrates the efficacy of the proposed framework for target detection in SSVEP based BCI applications.
•A novel approach that maps EEG data onto an exactly periodic subspace is proposed.•EPSD employs the periodic characteristics of the SSVEP response to enhance its SNR.•EPSD exhibits robust performance compared to the other commonly used spatial filters.•The study confirms that EPSD is promising detection algorithm for SSVEP based BCI. A novel exactly periodic spatial filtering (EPSD) approach, that provides a robust detection performance, is introduced and evaluated in this study. The proposed method exploits the temporal properties of the steady-state visual evoked potential (SSVEP) response to construct an orthogonal and exactly periodic mapping that enhances the signal to noise ratio (SNR) of the SSVEP embedded in the electroencephalogram (EEG) data. The subspace of interest is constructed via the elimination of the signals spaces that does not constitute the exact period of the target frequency. The EPSD is evaluated on a 35 subject benchmark dataset collected using a 40 target SSVEP BCI system. The results reveal that the proposed EPSD spatial filter significantly enhances the performance of target detection. Further statistical tests also confirm that the EPSD is a potential alternative to the existing SSVEP spatial filters for realizing an efficient BCI system.
Wearable heart rate monitors offer a cost-effective way of non-invasive, long-term monitoring of cardiac health. Validation of wearable technologies in an older populations is essential for evaluating their effectiveness during deployment in healthcare settings. To this end, we evaluated the validity of heart rate measures from a wearable device, Empatica E4, and compared them to the electrocardiography (ECG). We collected E4 data simultaneously with ECG in thirty-five older men and women during an overnight sleep recording in the laboratory. We propose a robust approach to resolve the missing inter-beat interval (IBI) data and improve the quality of E4 derived measures. We also evaluated the concordance of heart rate (HR) and heart rate variability (HRV) measures with ECG. The results demonstrate that the automatic E4 heart rate measures capture long-term HRV whilst the short-term metrics are affected by missing IBIs. Our approach provides an effective way to resolve the missing IBI issue of E4 and extracts reliable heart rate measures that are concordant with ECG. Clinical Relevance— This work discusses data quality challenges in heart rate data acquired by wearables and provides an efficient and reliable approach for extracting heart rate measures from the E4 wearable device and validates the metrics in older adults
Introduction Disturbances of sleep/wake behaviour are amongst the most disabling symptoms of dementia, leading to increased carers’ burden and institutionalisation. The lack of unobtrusive, low- burden technologies validated to monitor sleep in patients living with dementia (PLWD) has prevented longitudinal studies of nocturnal disturbances and their correlates. Aims To examine the effect of medication changes and clinical status on the intraindividual variation in sleep/wake behaviour in PLWD. Methods Using under-mattress pressure-sensing mat in 46 PLWD, we monitored sleep/wake behavioural metrics for 13,711 nights between 2019-2021. Machine learning and >3.6million nightly summaries from 13,671 individuals from the general population were used to detect abnormalities in PLWD’s nightly sleep/wake metrics and convert them to risk scores. Additionally, GP records were reviewed for each patient to determine whether medication changes and clinical events affected sleep parameters. Results PLWD’s went to bed earlier and rose later than sex- and age-matched controls. They had more nocturnal awakenings with longer out-of-bed durations. Notably, at the individual patient level, increased metric-specific risk scores were temporally related to changes in antipsychotics and antidepressants, and acute illness, including UTI, cardiac events, and depressive episodes. Conclusions Passive monitoring of sleep/wake behaviours is a promising way to identify novel markers of disease progression and evaluate the effectiveness of pharmaceutical interventions in patients with dementia.
Nocturnal disturbance is frequently observed in dementia and is a major contributor to institutionalisation. Unobtrusive technology that can quantify sleep/wake and determine bed occupancy during the major nocturnal sleep episode may be beneficial for long-term clinical monitoring and the carer. Such technologies have, however, not been validated in older people. Here we assessed the performance of the Withings Sleep Mattress (WSM) in a heterogenous older population to ensure external validity.