This paper reports a continuous and around-the-clock cuffless method of arterial blood pressure (BP) monitoring. We contrive a brand-new and proof-to-concept computational model for estimating arterial BP, by leveraging high-density sensor array that enable intimate location-stable contact with skin, yielding pressure distribution matrixes. A deep learning model then is developed to create the mapping between pressure feature matrix and BP to estimate systolic BP (SBP) and diastolic BP (DBP) precisely, which complies the international standard. The sensor array enables the continuous and accurate estimating of BP, which provides a promising feasibility for monitoring BP in the long-term, home-based, and wearable scenario.

This paper reports a flexible tactile sensing dense-array to locate blood vessels when arterial pulse monitoring or autonomous blood sampling without visual input in an intelligent medical system. With a deep learning neural network, a dense-array with 18 pressure sensing chips for tactile-force detection is able to distinguish 6 diverse body parts on the forearm surface: artery, 2 veins, bone, tendon and muscle. The time-variant tactile mappings are taken as images to train a six-layer convolutional neural network (CNN) and the overall recognition precision of this multi-classification model reaches 93.90%. Thereafter the flexible array is compliantly attached onto a silicone cylinder. While the cylinder is rolling in the target region on the forearm, the real-time vascular localization is thereupon automatically performed, which facilitates the following pulse signal acquisition at the radial artery or blood drawing at the elbow. Compared with vision-based approaches, our tactile strategy requires smaller data size, leading to less computing resources and faster identifications, which are of great concern in wearable applications.

This paper reports an innovative, non-invasive and instant method of arterial stiffness measurement. We delineate the tactile signals of arteries with varying stiffness using a dense sensor array, and analyze the factors affecting human tactility of stiffness and softness at fingertip with a deep learning model. Based on the most influential factor, an algorithm to instantaneously estimate the arterial stiffness is developed for the first time. The five stiffness grades ranked in order of the stiffness index (SI) may serve as an indicator of arterial aging and are expected to assist in early screening for certain cardiovascular diseases (CVD).

BACKGROUND:Lung immune prognostic index (LIPI) refers to a biomarker combining derived neutrophil-to-lymphocyte ratio (dNLR) and lactate dehydrogenase (LDH). Its prognostic effect on advanced small cell lung cancer (SCLC) patients receiving programmed cell death 1/programmed cell death ligand-1 (PD-1/PD-L1) inhibitors plus chemotherapy as first-line treatment remains unclear. Our research investigated the relationship between pretreatment LIPI and the prognosis of patients receiving first-line PD-1/PD-L1 inhibitors plus chemotherapy.METHODS:Advanced SCLC patients receiving PD-1/PD-L1 inhibitors plus chemotherapy as first-line treatment from Jan 2015 to Oct 2020 were included. Based on the values of dNLR and LDH, the study population was divided into two groups: LIPI good and LIPI intermediate/poor. The Kaplan-Meier method was used to compute the median survival time and the log-rank test was used to compare the two groups. Univariate and multivariate analyses were used to examine the correlation between the pretreatment LIPI and clinical outcomes.RESULTS:One hundred patients were included in this study, of which, 64% were LIPI good (dNLR < 4.0 and LDH < 283 U/L), 11% were LIPI poor (dNLR ≥ 4.0 and LDH ≥ 283 U/L), and the remaining 25% were LIPI intermediate. The LIPI good group had better progression-free survival (PFS) (median: 8.4 vs 4.7 months, p = 0.02) and overall survival (OS) (median: 23.8 vs 13.3 months, p = 0.0006) than the LIPI intermediate/poor group. Multivariate analysis showed that pretreatment LIPI intermediate/poor was an independent risk factor for OS (HR: 2.34; 95%CI, 1.13, 4.86; p = 0.02). Subgroup analysis showed that pretreatment LIPI good was associated with better PFS and OS in males, extensive disease (ED), PD-1 inhibitor treatment, smokers, and liver metastasis (p < 0.05).CONCLUSIONS:Pretreatment LIPI could serve as a prognostic biomarker for advanced SCLC patients receiving first-line PD-1/PD-L1 inhibitors plus chemotherapy.

In this study, we developed a radial artery pulse acquisition system based on finger-worn dense pressure sensor arrays to enable three-dimensional pulse signals acquisition. The finger-worn dense pressure-sensor arrays were fabricated by packaging 18 ultra-small MEMS pressure sensors (0.4 mm × 0.4 mm × 0.2 mm each) with a pitch of 0.65 mm on flexible printed circuit boards. Pulse signals are measured and recorded simultaneously when traditional Chinese medicine practitioners wear the arrays on the fingers while palpating the radial pulse. Given that the pitches are much smaller than the diameter of the human radial artery, three-dimensional pulse envelope images can be measured with the system, as can the width and the dynamic width of the pulse signals. Furthermore, the array has an effective span of 11.6 mm—3–5 times the diameter of the radial artery—which enables easy and accurate positioning of the sensor array on the radial artery. This study also outlines proposed methods for measuring the pulse width and dynamic pulse width. The dynamic pulse widths of three volunteers were measured, and the dynamic pulse width measurements were consistent with those obtained by color Doppler ultrasound. The pulse wave velocity can also be measured with the system by measuring the pulse transit time between the pulse signals at the brachial and radial arteries using the finger-worn sensor arrays.