Real-time analysis of physiological data to support medical applications
Abstract
This paper presents a flexible framework that performs real-time analysis of physiological data to monitor people's health conditions in any context (e.g., during daily activities, in hospital environments). Given historical physiological data, different behavioral models tailored to specific conditions (e.g., a particular disease, a specific patient) are automatically learnt. A suitable model for the currently monitored patient is exploited in the real-time stream classification phase. The framework has been designed to perform both instantaneous evaluation and stream analysis over a sliding time window. To allow ubiquitous monitoring, real-time analysis could also be executed on mobile devices. As a case study, the framework has been validated in the intensive care scenario. Experimental validation, performed on 64 patients affected by different critical illnesses, demonstrates the effectiveness and the flexibility of the proposed framework in detecting different severity levels of monitored people's clinical situations.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
For filtering artifacts, designed modules have usually applied threshold-based methods or used statistical tools to interpolate missing data points.
“According to the literature, for filtering artifacts, designed modules have usually applied threshold-based methods to filter sensor data [36,60] or used statistical tools to interpolate the missing data points [61].”
From Data Mining for Wearable Sensors in Health Monitoring Systems: A Review of Recent Trends and Challenges (2013) · cites this paper as [61]
In the time domain, extracted features usually include basic waveform characters and statistical parameters such as mean, variance, pick counts.
“In the time domain, the extracted features usually include basic waveform characters and statistical parameters related to the visible attributes in data stream such as mean, variance, pick counts, etc. [36,61].”
From Data Mining for Wearable Sensors in Health Monitoring Systems: A Review of Recent Trends and Challenges (2013) · cites this paper as [61]
Besides time and frequency domain features, other considered features include heuristic and specific field features.
“Besides the features from these domains, there are other considered features which such as heuristic and specific field features [61].”
From Data Mining for Wearable Sensors in Health Monitoring Systems: A Review of Recent Trends and Challenges (2013) · cites this paper as [61]
Other tools for feature selection used in literature include threshold-based rules, ANOVA, and Fourier transforms.
“Other tools for feature selection used in the literature includes threshold-based rules [61], analysis of variance (ANOVA) [51], and Fourier transforms [52].”
From Data Mining for Wearable Sensors in Health Monitoring Systems: A Review of Recent Trends and Challenges (2013) · cites this paper as [61]
In most research in health monitoring systems, simple statistical parameters or statistical functions are adequate to formulate the data and retrieve expected information.
“In the most of research in health monitoring systems, dealing with the simple statistical parameters (e.g., mean, variance etc.) or statistical functions e.g., risk function [61], factor analysis [68]) would be adequate to formulate the data and retrieve the expected information [38].”
From Data Mining for Wearable Sensors in Health Monitoring Systems: A Review of Recent Trends and Challenges (2013) · cites this paper as [61]
Some data analysis systems in healthcare were designed to process short signals such as few minutes of ECG data, a few hours of heart rate or oxygen saturation, and measurement of blood pressures for a day.
“Some data analysis systems in healthcare were designed to process short signals such as few minutes of ECG data [74,92], a few hours of heart rate or oxygen saturation [60,61] and the measurement of blood pressures for a day [56].”
From Data Mining for Wearable Sensors in Health Monitoring Systems: A Review of Recent Trends and Challenges (2013) · cites this paper as [61]
The citation lists haven’t been fetched yet
References 26 · Cited by 87
- Authors
- Apiletti, D., Baralis, E., Bruno, G., & Cerquitelli, T.
- Affiliations
- Politecnico di Torino (IT)
- Venue
- IEEE Transactions on Information Technology in Biomedicine
- Published
- 2009-05
- Volume
- 13
- Issue
- 3
- Pages
- 313-321
- ISSN
- 1089-7771 (ISSN-L)
- OpenAlex
- W2131747629
- Cited by
- 87
- References
- 26
- Citations by year
- 2026: 2 · 2025: 1 · 2024: 2 · 2023: 5 · 2022: 7 · 2021: 5 · 2020: 4 · 2019: 8 · 2018: 5 · 2017: 4 · 2016: 7 · 2015: 8 · 2014: 4 · 2013: 8 · 2012: 12
- FWCI
- 5.75
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Information Technology in Biomedicine (publishedVersion)
- PubMed (publishedVersion)
- PORTO@Iris (submittedVersion)
- PORTO Publications Open Repository TOrino (Politecnico di Torino) (submittedVersion)
- Topics
- Health Sciences › Medicine › Surgery › Healthcare Technology and Patient Monitoring
- Physical Sciences › Computer Science › Artificial Intelligence › Data Stream Mining Techniques
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- health monitoring, stream classification, sliding window, intensive care, ubiquitous health monitoring, mobile devices, clinical decision support
- MeSH terms
- Algorithms, Artificial Intelligence, Data Interpretation, Statistical, Humans, Models, Biological, Monitoring, Physiologic, Prognosis, Risk Factors, Signal Processing, Computer-Assisted, Reproducibility of Results, Cluster Analysis
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review