Rajdeep Kumar Nath

Rajdeep Kumar Nath

Auto-generated profile, based on publicly available information

Rajdeep Kumar Nath

Department of Technical Physics University of Eastern Finland Kuopio Finland

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 December 2023 in SLEEP Advances
Verified
Journal Article
Open access
PDF file
MPMinna Pitkänen
Minna Pitkänen
RNRajdeep Kumar Nath
Rajdeep Kumar Nath
HKHenri Korkalainen
Henri Korkalainen
SNSami Nikkonen
Sami Nikkonen
AMAlaa Mahamid
Alaa Mahamid
Timo LeppänenTimo Leppänen
Timo Leppänen
Polygraphy (PG) is often used to diagnose obstructive sleep apnea (OSA). However, it does not use electroencephalography, and therefore cannot estimate sleep time or score arousals and related hypopneas. Consequently, the PG-derived respiratory event index (REI) differs from the polysomnography (PSG)-derived apnea-hypopnea index (AHI). In this study, we comprehensively analyzed the differences between AHI and REI. Conventional AHI and REI were calculated based on total sleep time (TST) and total analyzed time (TAT), respectively, from two different PSG datasets (n = 1561). Moreover, TAT-based AHI (AHITAT) and TST-based REI (REITST) were calculated. These indices were compared keeping AHI as the gold standard. The REI, AHITAT, and REITST were significantly lower than AHI (p < 0.0001, p ≤ 0.002, and p ≤ 0.01, respectively). The total classification accuracy of OSA severity based on REI was 42.1% and 72.8% for two datasets. Based on AHITAT, the accuracies were 68.4% and 85.9%, and based on REITST, they were 65.9% and 88.5% compared to AHI. AHI was most correlated with REITST (r = 0.98 and r = 0.99 for the datasets) and least with REI (r = 0.92 and r = 0.97). Compared to AHI, REI had the largest mean absolute errors (13.9 and 6.7) and REITST the lowest (5.9 and 1.9). REI had the lowest sensitivities (42.1% and 72.8%) and specificities (80.7% and 90.9%) in both datasets. Based on these present results, REI underestimates AHI. Furthermore, these results indicate that arousal-related hypopneas are an important measure for accurately classifying OSA severity.

8 October 2023
Verified
Conference Paper
Open access
JTJaakko Tervonen
Jaakko Tervonen
RNRajdeep Kumar Nath
Rajdeep Kumar Nath
Kati PetterssonKati Pettersson
Kati Pettersson
JNJohanna Närväinen
Johanna Närväinen
JMJani Mäntyjärvi
Jani Mäntyjärvi
Human physiology and reactions to external stimuli differ between individuals. Researchers have developed strategies to adapt to these differences but the adaptations generally require data from each individual beforehand. A cold-start occurs when there is no data from a new individual. To address this, current study proposes user calibration which uses short segments of easily obtainable baseline data to adapt to new individuals. Experiments were conducted on two public stress and affect detection datasets, WESAD and SWELL-KW, to assess the effectiveness of the proposed calibration method and to determine suitable duration of the baseline measurement. Results showed that user calibration always beat the non-personalized model and segments of 3-8 minutes seemed to be most promising to consider for future use.

8 October 2023
Verified
Conference Paper
Open access
RNRajdeep K Nath
Rajdeep K Nath
JTJaakko Tervonen
Jaakko Tervonen
JNJohanna Närväinen
Johanna Närväinen
Kati PetterssonKati Pettersson
Kati Pettersson
JMJani Mäntyjärvi
Jani Mäntyjärvi
This paper presents a novel approach of an ECG-based mental health biometric system that relies on ultra-short duration (2 seconds) of one-channel ECG signal segments from acute stress data for accurate user identification and authentication. The proposed method uses a simple framework for contrastive learning (SimCLR) to train the user identification and authentication models. The performance of the proposed ECG-based biometric system was evaluated for a single-session use case using an in-house dataset. The dataset consisted of ECG signals acquired during a study protocol designed to induce physical and mental stress. The proposed biometric system was able to achieve an accuracy of 98% for user identification and an equal error rate (EER) of 0.02 when trained and tested with a balanced condition with stress and baseline/recovery. Our proposed system was able to retain its accuracy to 95% and the EER to 0.05 even when the training size was significantly reduced.

5 June 2023
Verified
Conference Paper
Open access
RNRajdeep K. Nath
Rajdeep K. Nath
JTJaakko Tervonen
Jaakko Tervonen
JNJohanna Närväinen
Johanna Närväinen
Kati PetterssonKati Pettersson
Kati Pettersson
JMJani Mäntyjärvi
Jani Mäntyjärvi
We present a novel application of contrastive learning technique in learning the feature representation of ECG signal in a self-supervised manner for the classification of acute stress types. Acute stress types that occur for a very short period and are rapidly changing and alternating in nature are difficult to classify using conventional ECG features. This is because the change in conventional ECG features due to rapid and alternating acute stressors do not reflect instantaneously. We hypothesize that deep-learned features from ECG signals can better distinguish between the different stress types than conventional ECG features. Our proposed approach can generate distinct feature representations for the physical and mental stress task type using very short window lengths. Our results show that the deep-learned features perform better in terms of accuracy and F1 score in distinguishing between physical and mental stress task types. In the future, our proposed method can be used in a real world setting for understanding the dynamics of different stressors in a self-supervised fashion without the need for human labeling.

4 November 2024 in Journal of Sleep Research
Verified
Journal Article
Open access
MPMinna Pitkänen
Minna Pitkänen
HPHenna Pitkänen
Henna Pitkänen
RNRajdeep Kumar Nath
Rajdeep Kumar Nath
SNSami Nikkonen
Sami Nikkonen
SKSamu Kainulainen
Samu Kainulainen
Timo LeppänenTimo Leppänen
Timo Leppänen
Summary: Obstructive sleep apnea diagnosis is based on the manual scoring of respiratory events. The agreement in the manual scoring of the respiratory events lacks an in‐depth investigation as most of the previous studies reported only the apnea–hypopnea index or overall agreement, and not temporal, second‐by‐second or event subtype agreement. We hypothesized the temporal and subtype agreement to be low because the event duration or subtypes are not generally considered in current clinical practice. The data comprised 50 polysomnography recordings scored by 10 experts. The respiratory event agreement between the scorers was calculated using kappa statistics in a second‐by‐second manner. Obstructive sleep apnea severity categories (no obstructive sleep apnea/mild/moderate/severe) were compared between scorers. The Fleiss' kappa value for binary (event/no event) respiratory event scorings was 0.32. When calculated separately within N1, N2, N3 and R, the Fleiss' kappa values were 0.12, 0.23, 0.22 and 0.23, respectively. Binary analysis conducted separately for the event subtypes showed the highest Fleiss' kappa for hypopneas to be 0.26. In 34% of the participants, the obstructive sleep apnea severity category was the same regardless of the scorer, whereas in the rest of the participants the category changed depending on the scorer. Our findings indicate that the agreement of manual scoring of respiratory events depends on the event type and sleep stage. The manual scoring has discrepancies, and these differences affect the obstructive sleep apnea diagnosis. This is an alarming finding, as ultimately these differences in the scorings affect treatment decisions.