Research Technician In Biomedical Signals And Non-Invasive Cardiorespiratory Monitoring.

Organisation/Company Universitat Politècnica de Catalunya (UPC)- BarcelonaTECH Research Field Engineering » Biomedical engineering Technology » Medical technology Researcher Profile First Stage Researcher (R1) Positions Research Support Positions Application Deadline 2 Nov ***:00 (Europe/Madrid) Country Spain Type of Contract Temporary Job Status Part-time Hours Per Week 25 Offer Starting Date 9 Nov Is the job funded through the EU Research Framework Programme? Not funded by a EU programme Reference Number *** Is the Job related to staff position within a Research Infrastructure? No
Offer Description
Industrial doctoral project ** DI 113 on new intelligent indices of respiration and blood pressure with non-invasive methods, oriented towards application in clinical practice.
Data is obtained with a non-invasive monitoring system that integrates ECG, heart sounds and thoracic accelerometry. Algorithms are developed to facilitate continuous monitoring and clinical interpretation.
The research combines signal processing, statistical models and machine learning, with validation against reference measurements and transfer of results to clinical practice.
Mission:
Develop intelligent and interpretable indices for cardiorespiratory monitoring, especially respiration and blood pressure, through the integration and analysis of non-invasive physiological signals from ECG, heart sounds and thoracic movement.
Functions to be developed:
Review the literature and support protocols for synchronized acquisition of ECG, phonocardiogram (PCG) and accelerometry with non-invasive monitoring devices, and the creation of an annotated and quality-controlled database.
Contribute to portable and accessible monitoring systems, validate indices with reference measures and facilitate their application in clinical practice to support clinical decision-making in real time.
Implement filtering, artifact rejection and signal segmentation. Extract R peaks, S1/S2 sounds, respiratory cycles, cardiac variability and time intervals between ECG and PCG.
Develop and calibrate statistical and machine learning models to estimate respiratory rate and blood pressure and obtain interpretable cardiorespiratory indices.
Integrate validated algorithms into Java/Android software tools for real-time calculation and visualization and facilitate their application in clinical practice.
Document the methods and results and support the scientific dissemination of the project.
Validate indices with reference measures and across participants and registration conditions. Analyze accuracy, robustness and clinical relevance with MAE, RMSE and concordance analyses.
Statistical modeling and machine learning.
Development of medical software and real-time monitoring.
Processing and analysis of signals and biomedical data: processing of time series and clinical data using MATLAB/Python (pandas, NumPy) and R.
Other requirements to consider:
Ability to work independently and in a multidisciplinary team, organize tasks and communicate effectively with clinical and technical interlocutors.
Analytical rigor, attention to the integrity and quality of data and respect for the confidentiality of clinical information.
Specific Requirements
Knowledge:
Reproducible data engineering and management: building integration flows, cleaning, standardization, SQL queries and implementing documented quality controls.
Cardiorespiratory physiology, biomedical instrumentation and principles of non-invasive monitoring with ECG, PCG and accelerometry.
Extraction of physiological features: R peaks, S1/S2 heart sounds, respiratory cycles, heart rate variability and ECG-PCG intervals.
Biostatistics and biomedical data modeling: regression, multivariate analysis and evaluation with MAE, RMSE and Bland-Altman analysis.
Digital signal processing: sampling, synchronization, filtering, artifact rejection, segmentation and temporal and frequency analysis.
Supervised and unsupervised machine learning, feature selection, model calibration and validation, interpretability and generalization between participants.
Quality control and privacy of health data.
Protocols, technical documentation and results reports.
It will be assessed:
Master's degree in Biomedical Engineering or similar studies and postgraduate training in health data science, completed or in progress.
Professional Experience:
In data science applied to real clinical datasets: cleaning, integration, standardization and validation with MATLAB/Python and SQL, and automation of analysis processes.
In statistical programming and machine learning with R, Python and MATLAB to the modeling of physiological signals and the extraction of biomedical features.
Have conducted research on mHealth tools for non-invasive diagnosis, collaboration in multidisciplinary teams and support for study