arXiv subjects

Manasi Nandi

Publications and source records attributed to Manasi Nandi.

5 recordsLinked to original sources

arXiv2026

Attractor Image-Based Deep Learning of Arterial Pulse Waves for Age Classification

Arterial pulse waveform morphology evolves with age, reflecting structural and functional changes in the cardiovascular system. Thus, vascular age is a valuable surrogate marker of cardiovascular health, and premature vascular ageing can indicate increased disease risk. Pulse wave analysis could support risk stratification in otherwise asymptomatic adults. We transformed pulse wave time-series data from photoplethysmography (PPG) and arterial tonometry into images, using the Symmetric Projection Attractor Reconstruction (SPAR) method. These SPAR images were used to train a convolutional neural network to classify healthy subjects into two closely spaced age groups (35-40 and 50-55 years). The model demonstrated consistent classification performance across internal and external test sets, achieving F1 scores above 70% for both PPG and tonometry signals. These results suggest that SPAR-derived pulse wave images contain discriminative morphological features even among healthy adults close in age. This proof-of-concept lays the groundwork for future research into the use of SPAR for early risk detection using smart wearables.

cs.LG↗

arXiv2026

Benchmark Problems and Benchmark Datasets for the evaluation of Machine and Deep Learning methods on Photoplethysmography signals: the D4 report from the QUMPHY project

This report is part of the Qumphy project (22HLT01 Qumphy) that is funded by the European Union and is dedicated to the development of measures to quantify the uncertainties associated with Machine Learning algorithms applied to medical problems, in particular the analysis and processing of Photoplethysmography (PPG) signals. In this report, a list of six medical problems that are related to PPG signals and serve as Benchmark Problems is given. Suitable Benchmark datasets and their usage are described also.

cs.LG↗

arXiv2025

Machine-learning for photoplethysmography analysis: Benchmarking feature, image, and signal-based approaches

Photoplethysmography (PPG) is a widely used non-invasive physiological sensing technique, suitable for various clinical applications. Such clinical applications are increasingly supported by machine learning methods, raising the question of the most appropriate input representation and model choice. Comprehensive comparisons, in particular across different input representations, are scarce. We address this gap in the research landscape by a comprehensive benchmarking study covering three kinds of input representations, interpretable features, image representations and raw waveforms, across prototypical regression and classification use cases: blood pressure and atrial fibrillation prediction. In both cases, the best results are achieved by deep neural networks operating on raw time series as input representations. Within this model class, best results are achieved by modern convolutional neural networks (CNNs). but depending on the task setup, shallow CNNs are often also very competitive. We envision that these results will be insightful for researchers to guide their choice on machine learning tasks for PPG data, even beyond the use cases presented in this work.

cs.LG↗

arXiv2024

Using Photoplethysmography to Detect Real-time Blood Pressure Changes with a Calibration-free Deep Learning Model

Blood pressure (BP) changes are linked to individual health status in both clinical and non-clinical settings. This study developed a deep learning model to classify systolic (SBP), diastolic (DBP), and mean (MBP) BP changes using photoplethysmography (PPG) waveforms. Data from the Vital Signs Database (VitalDB) comprising 1,005 ICU patients with synchronized PPG and BP recordings was used. BP changes were categorized into three labels: Spike (increase above a threshold), Stable (change within a plus or minus threshold), and Dip (decrease below a threshold). Four time-series classification models were studied: multi-layer perceptron, convolutional neural network, residual network, and Encoder. A subset of 500 patients was randomly selected for training and validation, ensuring a uniform distribution across BP change labels. Two test datasets were compiled: Test-I (n=500) with a uniform distribution selection process, and Test-II (n=5) without. The study also explored the impact of including second-deviation PPG (sdPPG) waveforms as additional input information. The Encoder model with a Softmax weighting process using both PPG and sdPPG waveforms achieved the highest detection accuracy--exceeding 71.3% and 85.4% in Test-I and Test-II, respectively, with thresholds of 30 mmHg for SBP, 15 mmHg for DBP, and 20 mmHg for MBP. Corresponding F1-scores were over 71.8% and 88.5%. These findings confirm that PPG waveforms are effective for real-time monitoring of BP changes in ICU settings and suggest potential for broader applications.

eess.SP↗

arXiv2015

Mathematical Modelling of Heart Rate Changes in the Mouse

The CVS is composed of numerous interacting and dynamically regulated physiological subsystems which each generate measurable periodic components such that the CVS can itself be presented as a system of weakly coupled oscillators. The interactions between these oscillators generate a chaotic blood pressure waveform signal, where periods of apparent rhythmicity are punctuated by asynchronous behaviour. It is this variability which seems to characterise the normal state. We used a standard experimental data set for the purposes of analysis and modelling. Arterial blood pressure waveform data was collected from conscious mice instrumented with radiotelemetry devices over $24$ hours, at a $100$ Hz and $1$ kHz time base. During a $24$ hour period, these mice display diurnal variation leading to changes in the cardiovascular waveform. We undertook preliminary analysis of our data using Fourier transforms and subsequently applied a series of both linear and nonlinear mathematical approaches in parallel. We provide a minimalistic linear and nonlinear coupled oscillator model and employed spectral and Hilbert analysis as well as a phase plane analysis. This provides a route to a three way synergistic investigation of the original blood pressure data by a combination of physiological experiments, data analysis viz. Fourier and Hilbert transforms and attractor reconstructions, and numerical solutions of linear and nonlinear coupled oscillator models. We believe that a minimal model of coupled oscillator models that quantitatively describes the complex physiological data could be developed via such a method. Further investigations of each of these techniques will be explored in separate publications.

q-bio.TO↗