Noninvasive detection of lower extremity artery disease using multi-site photoplethysmographic signals and machine learning

Q: Why is early non-invasive detection of lower extremity artery disease important?

Early detection helps enable timely interventional or surgical treatment, improves limb salvage and functional outcomes, and supports better cardiovascular risk assessment. The disease can also lead to severe complications such as disability and amputations.

Q: What is the role of the ankle brachial index (ABI) in screening?

ABI is the first-line non-invasive screening and diagnostic test for LEAD by comparing systolic blood pressure in the leg artery with brachial systolic pressure. However, ABI cannot localize stenosis or describe underlying pathoanatomy.

Q: How does the proposed screening method work?

The method uses multi-site photoplethysmography measurements to extract morphological features from PPG signals. Machine learning then classifies patients into control or stenosis groups.

Aug 5, 2026

Upload by Seraphina

Lower extremity stenosis is a prevalent cardiovascular condition, yet current diagnostic pathways are invasive, operator-dependent, and limited in primary care availability. This study proposes a non-invasive screening approach using morphological features extracted from multi-site photoplethysmography (PPG) signals. In a proof-of-concept clinical setting, machine learning classified 42 patients with two measurements each at four locations (84 measurements; 336 signals) into control or stenosis groups. The model achieved 82.6% overall accuracy (sensitivity 0.750, specificity 0.865).

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

Background

Disease burden and need for early non-invasive detection

Conventional diagnosis and limitations

Proposed method

Multi-site PPG signals and morphological feature extraction

Machine learning classification approach

npj | biosensing Article [https://doi.org/10.1038/s44328-025-00044-z](https://doi.org/10.1038/s44328-025-00044-z) Noninvasive detection of lower extremity artery disease using multi-site photoplethysmographic signals and machine learning Check for updates Christian Teichert1, Urs Hackstein1, Tobias Krüger2,4 & Stefan Bernhard1,3 Lower extremity stenosis (LES) is a prevalent cardiovascular condition and a strong indicator of systemic arteriosclerosis. Existing diagnostic methods are invasive or operator-dependent and often unavailable at the primary care level. Here, we propose a non-invasive screening method based on morphological features extracted from multi-site PPG signals that were calculated from multi-site photoplethysmography measurements during a proof-of-concept clinical study at University Hospital Tübingen. Machine learning methods were used to classify 42 patients with 2 measurements each at four locations (i.e., a total of 84 measurements and 336 signals) into either the control or stenosis group. An overall classiﬁcation accuracy of 82.6%(sensitivity: 0.750, speciﬁcity: 0.865) is achieved. This result is clinically relevant and shows that the selected features are effective for detecting stenosis and could be used as a screening method at the primary physician level. Cardiovascular diseases are the leading causes of death and health impairments worldwide1. Lower extremity artery disease (LEAD) is the manifestation ofarteriosclerosis in the pelvic and leg arteries and occurs in3–10%of the population2. Prevalence of common iliac artery stenosis, on which we focus here, is up to 30% for patients with lower extremity artery disease3. Although LEAD is only responsible for 0.4% of cardiovascular deaths1, it causes chronic illness, loss of life quality, disability, increased health care costs, and it has been shown to be a strong indicator of systemic arteriosclerosis. Patients with LEAD have higher mortality compared to patients without this disease4. Moreover, LEAD can result in the need for amputations. An early non-invasive detection is therefore highly desirable. Diagnosis of lower extremity artery occlusive disease classically relies on the patient history ofa painfully limited walking distance and the clinical signs of unilaterally weakened pulse and tissue malperfusion5, eventhough only 5 to 10% of cases show the classical symptom of intermittent claudication6. Actually, the ankle brachial index (ABI) is the ﬁrst-line non-invasive test for screening and a diagnosis of LEAD: a blood pressure cuff is placed around the calf just above the angle, with a CW-Doppler-probe signal from the anterior or posterior tibial artery, a systolic blood pressure in the respective artery is measured and compared with the systolic blood-pressure from the brachial artery. An ABI <0.9 is indicative of LEAD5, however, the ABI allows no conclusions about the localization of the stenosis and the underlying pathoanatomy. The latter, however, is a domain of cross-sectional imaging methods such as Doppler-sonography or CT- or MRI-angiography. Doppler-sonography allows the simultaneous examination of pathoanatomyandhemodynamics7, but its accuracy depends on the physiognomy of the patient and the skills of the examiner. CT-and MRI-angiography are costly, of limited availability, and come with the risks associated with X-ray exposure and intravenous contrast agents2. Early diagnosis of lower extremity artery occlusive disease not only facilitates early interventional or surgical treatment, improves prognosis in terms of limb salvage and functional outcome8, but also enables a more comprehensive assessment of a patient’s individual cardiovascular risk proﬁle, and therefore is desirable5. The early diagnosis of lower extremity artery occlusive disease, however, depends on the diagnostic skills of the general practitioner and his ability to differentiate arterial occlusive disease from other pathologies causing reduced walk

FAQs

Why is early non-invasive detection of lower extremity artery disease important?

Early detection helps enable timely interventional or surgical treatment, improves limb salvage and functional outcomes, and supports better cardiovascular risk assessment. The disease can also lead to severe complications such as disability and amputations.

What is the role of the ankle brachial index (ABI) in screening?

ABI is the first-line non-invasive screening and diagnostic test for LEAD by comparing systolic blood pressure in the leg artery with brachial systolic pressure. However, ABI cannot localize stenosis or describe underlying pathoanatomy.

How does the proposed screening method work?

The method uses multi-site photoplethysmography measurements to extract morphological features from PPG signals. Machine learning then classifies patients into control or stenosis groups.

Aug 5, 2026

Upload by Seraphina