Estimation of aortic stiffness by finger photoplethysmography using enhanced pulse wave analysis and machine learning

Introduction

Aortic stiffness plays a critical role in the evolution of cardiovascular diseases, but the assessment requires specialized equipment. Photoplethysmography (PPG) and single-lead electrocardiogram (ECG) are readily available in healthcare and wearable devices. We studied whether a brief PPG registration, alone or in combination with single-lead ECG, could be used to reliably estimate aortic stiffness.

Methods

A proof-of-concept study with simultaneous high-resolution index finger recordings of infrared PPG, single-lead ECG, and finger blood pressure (Finapres) was performed in 33 participants [median age 44 (range 21-66) years, 19 men] and repeated within 2 weeks. Carotid-femoral pulse wave velocity (cfPWV; two-site tonometry with SphygmoCor) was used as a reference. A brachial single-cuff oscillometric device assessed aortic pulse wave velocity (aoPWV; Arteriograph) for further comparisons. We extracted 136 established PPG waveform features and engineered 13 new with improved coupling to the finger blood pressure curve. Height-normalized pulse arrival time (NPAT) was derived using ECG. Machine learning methods were used to develop prediction models.

Results

The best PPG-based models predicted cfPWV and aoPWV well (root-mean-square errors of 0.70 and 0.52 m/s, respectively), with minor improvements by adding NPAT. Repeatability and agreement were on par with the reference equipment. A new PPG feature, an amplitude ratio from the early phase of the waveform, was most important in modelling, showing strong correlations with cfPWV and aoPWV (r = -0.81 and -0.75, respectively, both P < 0.001).

Conclusion

Using new features and machine learning methods, a brief finger PPG registration can estimate aortic stiffness without requiring additional information on age, anthropometry, or blood pressure. Repeatability and agreement were comparable to those obtained using non-invasive reference equipment. Provided further validation, this readily available simple method could improve cardiovascular risk evaluation, treatment, and prognosis.

Epithelioid leiomyoma of the larynx

We describe the pathological features of a case of laryngeal epithelioid leiomyoma (leiomyoblastoma) which, to our knowledge, is the second case to be reported in the world literature. A review of the literature confirmed that leiomyoma as such is a very rare neoplasm in the larynx, and only 33 cases have been previously reported. The neoplasm was located in the left vocal cord and consisted of mainly epithelioid, round or spindle-shaped cells, often with clear cytoplasm, which were arranged predominantly in solid nests and sheets. The tumour cells showed positive immunoreactivity for smooth muscle actin and desmin. The tumour showed low mitotic activity and immunostaining with MIB 1 (Ki-67) accordingly revealed the occasional cell only to be positive, confirming a low proliferative activity in agreement with a benign neoplasm. Epithelioid leiomyomas located in other sites have been shown to act occasionally in a malignant fashion, and the necessity for careful long-term follow-up of the patient is therefore emphasized.

Skull distortion of bone conducted signals

A previously essentially unknown type of distortion of bone conduction (BC) signal has been studied on the skulls of four human cadavers. The method was based on a miniature accelerometer, rigidly attached to the cranial bone, converting the skull vibration close to the cochlea into an electrical signal which was analysed with regard to harmonic distortion. The BC signals, pure tones, were presented by means of a high-quality vibrator. The distortion was found to be limited to the lower audiometric frequencies, with a maximum around 500 Hz, and of such a degree as to be able to significantly influence the results of BC audiometry. The distortion is probably caused by nonlinear mechanical properties of the human skull.

Adenocarcinoma originating in the thyroglossal duct

Eighty-six cases of carcinoma of the thyroglossal duct have been reported in the literature, most of these being well-differentiated adenocarcinomas. Three new cases of the latter type are presented. Cases where carcinoma of the thyroglossal duct is suspected should be investigated with fine-needle biopsy, thyroid scintigraphy, skeletal and pulmonary X-ray, determination of TSH, T 3, PBI and blood serum calcium. The treatment of well-differentiated adenocarcinomas is a combination of surgical and medical procedures.