Template-based synergy extrapolation analysis for prediction of muscle excitations.

OBJECTIVE: Accurate prediction of unmearsured muscle excitations can reduce the required wearable surface electromyography (sEMG) sensors, which is a critical factor in the study of physiological measurement. Synergy extrapolation uses synergy excitations as building blocks to reconstruct muscle excitations. However, the practical application of synergy extrapolation is still limited as the extrapolation process utilizes unmeasured muscle excitations it seeks to reconstruct. This paper aims to propose and derive methods to provide an avenue for the practical application of synergy extrapolation with non-negative matrix factorization (NMF) methods. APPROACH: Specifically, a tunable Gaussian-Laplacian mixture distribution NMF (GLD-NMF) method and related multiplicative update rules are derived to yield appropriate synergy excitations for extrapolation. Furthermore, a template-based extrapolation structure (TBES) is proposed to extrapolate unmeasured muscle excitations based on synergy weighting matrix templates totally extracted from measured sEMG datasets, improving the extrapolation performance. Moreover, we applied the proposed GLD-NMF method and TBES to selected muscle excitations acquired from a series of single-leg stance (SLS) tests, walking tests and upper limb reaching tests. MAIN RESULTS: Experimental results show that the proposed GLD-NMF and TBES could extrapolate unmeasured muscle excitations accurately. Moreover, introducing synergy weighting matrix templates could decrease the number of sEMG sensors in a series of experiments. In addition, verification results demonstrate the feasibility of applying synergy extrapolation with NMF methods. SIGNIFICANCE: With the TBES method, synergy extrapolation could play a significant role in reducing data dimensions of sEMG sensors, which will improve the portability of sEMG sensors-based systems and promotes applications of sEMG signals in human-machine interfaces scenarios.

Therapeutic efficacy of compound organic acids administration on methicillin-resistant Staphylococcus aureus-induced arthritis in broilers.

Avian arthritis is a common disease in the poultry industry, and the etiology is complex. Bacterial arthritis is usually caused by Staphylococcus aureus (S. aureus) infection. This study explored the minimum inhibitory concentration (MIC) of different organic acids against S. aureus MRSA85 and found that vanillic acid, suberic acid, itaconic acid, salicylic acid, and other organic acids had significant inhibitory effects on this strain, especially cinnamic acid, which exhibited the best inhibitory effect. The Fractional Inhibitory Concentration Index (FICI) test further revealed the synergistic effect among some compound organic acids, which can significantly enhance the antibacterial efficiency against MRSA85 while reducing the risk of bacterial resistance. Under the low concentrations (1/2 or 1/4 MIC) conditions, the MIC of the compound organic acids against S. aureus remains unchanged, and it can even enhance the sensitivity of antibiotic-resistant S. aureus to Oxacillin. Furthermore, the compound organic acids could effectively promote the recovery of S. aureus-induced arthritis in broiler models, reduce inflammatory responses, and lower down bacterial loads and inflammatory cytokine levels in joints, which indicated that the effects of the Compound 2 is comparable to that of the trimethoprim-sulfamethoxazole group. These results support the potential and application value of organic acids and their compounds, including Compound 1 to 3, as novel antibacterial agents in the treatment of S. aureus infections.

Prognostic implications of residual mild coarctation gradient after interventional repair.

There is limited data on the prognostic implications of residual mild coarctation (RMC) in patients with repaired native coarctation of the aorta (CoA). To explore the association of RMC with mid-term comorbidities in post-interventional patients, and the predictive value of the residual pressure gradient. The authors retrospectively analyzed 79 native CoA patients who received successful intervention at our hospital between October 2010 and June 2023. The outcomes of the study were late arterial hypertension (either raised blood pressure or commencement of hypotensive medications) only in normotensive patients at early follow-up and the composite mid-term comorbidities including new-onset aortic injury, re-stenosis, and re-intervention. At a median follow-up of 60 months, late hypertension and mid-term comorbidities occurred in 16 (28.1%) and nine (11.4%) patients, respectively. Multivariate Cox proportional hazard regression analysis identified invasive peak systolic CoA pressure gradient (PSPG) as the best independent predictor of both outcomes. The maximally selected rank statistics indicated 10 mm Hg as the best PSPG cut-off value for predicting late hypertension. Compared to patients with PSPG < 11 mm Hg, the cumulative event rates of both outcomes were higher in those with PSPG ≥ 11 mm Hg (log-rank test, p < .001 for both endpoints). PSPG ≥ 11 mm Hg was proved to be the independent predictor of late hypertension with a significantly increased risk. In patients with non-surgical CoA repair, the post-interventional RMC and PSPG ≥11 mm Hg are important predictors of clinical comorbidities at mid-term follow-up.

High-throughput UAV-based rice panicle detection and genetic mapping of heading-date-related traits.

Introduction: Rice (Oryza sativa) serves as a vital staple crop that feeds over half the world's population. Optimizing rice breeding for increasing grain yield is critical for global food security. Heading-date-related or Flowering-time-related traits, is a key factor determining yield potential. However, traditional manual phenotyping methods for these traits are time-consuming and labor-intensive. Method: Here we show that aerial imagery from unmanned aerial vehicles (UAVs), when combined with deep learning-based panicle detection, enables high-throughput phenotyping of heading-date-related traits. We systematically evaluated various state-of-the-art object detectors on rice panicle counting and identified YOLOv8-X as the optimal detector. Results: Applying YOLOv8-X to UAV time-series images of 294 rice recombinant inbred lines (RILs) allowed accurate quantification of six heading-date-related traits. Utilizing these phenotypes, we identified quantitative trait loci (QTL), including verified loci and novel loci, associated with heading date. Discussion: Our optimized UAV phenotyping and computer vision pipeline may facilitate scalable molecular identification of heading-date-related genes and guide enhancements in rice yield and adaptation.

Dynamics of extrachromosomal circular DNA in rice.

The genome's dynamic nature, exemplified by elements like extrachromosomal circular DNA (eccDNA), is crucial for biodiversity and adaptation. Yet, the role of eccDNA in plants, particularly rice, remains underexplored. Here, we identify 25,598 eccDNAs, unveiling the widespread presence of eccDNA across six rice tissues and revealing its formation as a universal and random process. Interestingly, we discover that direct repeats play a pivotal role in eccDNA formation, pointing to a unique origin mechanism. Despite eccDNA's prevalence in coding sequences, its impact on gene expression is minimal, implying its roles beyond gene regulation. We also observe the association between eccDNA's formation and minor chromosomal deletions, providing insights of its possible function in regulating genome stability. Further, we discover eccDNA specifically accumulated in rice leaves, which may be associated with DNA damage caused by environmental stressors like intense light. In summary, our research advances understanding of eccDNA's role in the genomic architecture and offers valuable insights for rice cultivation and breeding.

Hypotension prediction index for the prevention of hypotension during surgery and critical care: A narrative review.

Surgeons and anesthesia clinicians commonly face a hemodynamic disturbance known as intraoperative hypotension (IOH), which has been linked to more severe postoperative outcomes and increases mortality rates. Increased occurrence of IOH has been positively associated with mortality and incidence of myocardial infarction, stroke, and organ dysfunction hypertension. Hence, early detection and recognition of IOH is meaningful for perioperative management. Currently, when hypotension occurs, clinicians use vasopressor or fluid therapy to intervene as IOH develops but interventions should be taken before hypotension occurs; therefore, the Hypotension Prediction Index (HPI) method can be used to help clinicians further react to the IOH process. This literature review evaluates the HPI method, which can reliably predict hypotension several minutes before a hypotensive event and is beneficial for patients' outcomes.

BiGRU-attention for Continuous blood pressure trends estimation through single channel PPG.

BACKGROUND: Physiological parameter monitoring based on photoplethysmography (PPG) detection has the advantage of fast, portable, and non-invasive. Changes in the morphology of the PPG waveform can reflect the effect of arterial elasticity changes on blood pressure (BP). However, machine learning models and non-recurrent neural network models typically ignore the time-dependency of continuous PPG data, leading to the decrease of accuracy or the increased calibration frequency. OBJECTIVE: This paper proposes a BiGRU model with attention to estimate BP trends, which uses a single-channel PPG signal combined with demographic information to estimate continuous BP trends point-by-point and to discuss the impact of calibration cycle. METHODS: This paper selects 15 typical subjects from two groups with/without cardiovascular disease (CVD) and evaluates the model performance. Regarding the calibration frequency problem, we set two modes of non-calibration and calibration to validate the results of blood pressure trends estimation. RESULTS: In the calibration mode, the estimation errors (ME ± STD) of SBP for CVD/non-CVD groups are 0.91 ± 10.58 mmHg/0.17 ± 10.06 mmHg respectively, and DBP are 0.34 ± 5.28 mmHg/-0.19 ± 5.36 mmHg; in the non-calibration mode, the estimation errors of SBP for CVD/non-CVD groups are 0.27 ± 9.87 mmHg/-0.82 ± 9.92 mmHg respectively, and DBP are -0.63 ± 3.28 mmHg/0.80 ± 4.93 mmHg. CONCLUSIONS: The results show that the proposed model has high accuracy in estimating BP levels, which is expected to achieve real-time, long-term continuous BP trends monitoring in wearable devices.

Structure and function of rice hybrid genomes reveal genetic basis and optimal performance of heterosis.

Exploitation of crop heterosis is crucial for increasing global agriculture production. However, the quantitative genomic analysis of heterosis was lacking, and there is currently no effective prediction tool to optimize cross-combinations. Here 2,839 rice hybrid cultivars and 9,839 segregation individuals were resequenced and phenotyped. Our findings demonstrated that indica-indica hybrid-improving breeding was a process that broadened genetic resources, pyramided breeding-favorable alleles through combinatorial selection and collaboratively improved both parents by eliminating the inferior alleles at negative dominant loci. Furthermore, we revealed that widespread genetic complementarity contributed to indica-japonica intersubspecific heterosis in yield traits, with dominance effect loci making a greater contribution to phenotypic variance than overdominance effect loci. On the basis of the comprehensive dataset, a genomic model applicable to diverse rice varieties was developed and optimized to predict the performance of hybrid combinations. Our data offer a valuable resource for advancing the understanding and facilitating the utilization of heterosis in rice.

The WD40 domain-containing protein Ehd5 positively regulates flowering in rice (Oryza sativa).

Heading date (flowering time), which greatly influences regional and seasonal adaptability in rice (Oryza sativa), is regulated by many genes in different photoperiod pathways. Here, we characterized a heading date gene, Early heading date 5 (Ehd5), using a modified bulked segregant analysis method. The ehd5 mutant showed late flowering under both short-day and long-day conditions, as well as reduced yield, compared to the wild type. Ehd5, which encodes a WD40 domain-containing protein, is induced by light and follows a circadian rhythm expression pattern. Transcriptome analysis revealed that Ehd5 acts upstream of the flowering genes Early heading date 1 (Ehd1), RICE FLOWERING LOCUS T 1 (RFT1), and Heading date 3a (Hd3a). Functional analysis showed that Ehd5 directly interacts with Rice outermost cell-specific gene 4 (Roc4) and Grain number, plant height, and heading date 8 (Ghd8), which might affect the formation of Ghd7-Ghd8 complexes, resulting in increased expression of Ehd1, Hd3a, and RFT1. In a nutshell, these results demonstrate that Ehd5 functions as a positive regulator of rice flowering and provide insight into the molecular mechanisms underlying heading date.

BAT6026, a novel anti-OX40 antibody with enhanced antibody dependent cellular cytotoxicity effect for cancer immunotherapy.

OX40 (CD134), a member of the TNF receptor superfamily, is a widely studied costimulatory immune checkpoint. Several OX40 agonistic antibodies are in the clinical stage for cancer treatment, among which PF-04518600 is the leader and currently in phase II trial. It has been recognized that one potential mode of action for anti-OX40 antibodies is the deletion of intratumoral Tregs. Thus, a novel human anti-OX40 antibody, BAT6026, was generated with enhanced antibody dependent cellular cytotoxicity (ADCC) via fucose deletion to strengthen its Treg depletion activity. This characteristic of BAT6026 differentiates it from other previously reported anti-OX40 antibodies in the field of tumor therapy. The affinity of BT6026 to OX40 was 0.28nM, approximately 8 times stronger than that of PF-04518600. BAT6026 effectively competed for the binding of ligand OX40L to OX40, whereas PF-04518600 only partially competed. Moreover, compared to PF-04518600, BAT6026 activated T cells more effectively when clustered by FcγRs engagement and stimulated SEB-pretreated PBMCs to secrete IL-2 cytokines in vitro. In addition, BAT6026 demonstrated stronger anti-tumor activity than PF-04518600 in an OX40-humanized mouse MC38 tumor model. BAT6026 also showed a significantly synergistic effect on tumor inhibition when combined treatment with PD-1 antibody. Analysis of tumor-infiltrating T cells revealed that BAT6026 treatment significantly reduced Treg cells and increased CD8+ T cells in tumor. Preclinical safety assessment in non-human primates demonstrated a good safety profile for BAT6026. Together these data warrant further development of BAT6026 into clinical trials for patients with cancer.

Expanded Carbon Nanotube Fiber at the Liquid-Air Interface for High-Performance Fiber-Based Supercapacitors and Electrochemical Sensors.

Carbon nanotube fibers (CNTFs) are widely utilized in flexible and wearable electronics due to their outstanding electrical and mechanical properties. However, the spinning process of CNTFs has limited the CNTs from exposure, leading to an ultralow usage efficiency of individual CNTs. Here, we propose an electrochemical expansion strategy of a single CNTF at the liquid-air interface, forming a macroscopic spindle-shaped CNTF (SS-CNTF) with an enlarged volume of up to 5000-fold upon the spindle. The obtained spindle-shaped structure endows CNTF with a high specific surface area together with excellent conductivity and good mechanical properties. Therefore, the SS-CNTF-based devices exhibit outstanding performances both in energy storage (electrical double-layer supercapacitor, energy density: 11.22 Wh kg-1, power density: 203.9 kW kg-1) and electrochemical sensing (ascorbic acid: 1.26 µA µM-1 cm-2; dopamine: 103.91 µA µM-1 cm-2; uric acid: 11.53 µA µM-1 cm-2). The novel architecture of SS-CNTF prepared by one-step electrochemical expansion at the liquid-air interface enabled its high performance in multiple applications, providing new insight into the development of CNTF-based devices.

Reducing the muscle activity of walking using a portable hip exoskeleton based on human-in-the-loop optimization.

Introduction: Human-in-the-loop optimization has made great progress to improve the performance of wearable robotic devices and become an effective customized assistance strategy. However, a lengthy period (several hours) of continuous walking for iterative optimization for each individual makes it less practical, especially for disabled people, who may not endure this process. Methods: In this paper, we provide a muscle-activity-based human-in-the-loop optimization strategy that can reduce the time spent on collecting biosignals during each iteration from around 120 s to 25 s. Both Bayesian and Covariance Matrix Adaptive Evolution Strategy (CMA-ES) optimization algorithms were adopted on a portable hip exoskeleton to generate optimal assist torque patterns, optimizing rectus femoris muscle activity. Four volunteers were recruited for exoskeleton-assisted walking trials. Results and Discussion: As a result, using human-in-the-loop optimization led to muscle activity reduction of 33.56% and 41.81% at most when compared to walking without and with the hip exoskeleton, respectively. Furthermore, the results of human-in-the-loop optimization indicate that three out of four participants achieved superior outcomes compared to the predefined assistance patterns. Interestingly, during the optimization stage, the order of the two typical optimizers, i.e., Bayesian and CMA-ES, did not affect the optimization results. The results of the experiment have confirmed that the assistance pattern generated by muscle-activity-based human-in-the-loop strategy is superior to predefined assistance patterns, and this strategy can be achieved more rapidly than the one based on metabolic cost.

Which strain of the avian coronavirus vaccine will become the prevalent one in China next?

Infectious bronchitis virus (IBV) is a vital pathogen in poultry farms, which can induce respiratory, nephropathogenic, oviduct, proventriculus, and intestinal diseases. Based on the phylogenetic classification of the full-length S1 gene, IBV isolates have been categorized into nine genotypes comprising 38 lineages. GI (GI-1, GI-2, GI-3, GI-4, GI-5, GI-6, GI-7, GI-13, GI-16, GI-18, GI-19, GI-22, GI-28, and GI-29), GVI-1 and GVII-1 have been reported in China in the past 60 years. In this review, a brief history of IBV in China is described, and the current epidemic strains and licensed IBV vaccine strains, as well as IBV prevention and control strategies, are highlighted. In addition, this article presents unique viewpoints and recommendations for a more effective management of IBV. The recombinant Newcastle Disease virus (NDV) vector vaccine expressed S gene of IBV QX-like and 4/91 strains may be the dominant vaccine strains against NDV and IBV.

High ratio of C-reactive protein to albumin is associated with hemorrhagic transformation and poor functional outcomes in acute ischemic stroke patients after thrombolysis.

Background: In patients with acute ischemic stroke, hemorrhagic transformation (HT) is a common complication after intravenous thrombolysis (IVT). In this study, we evaluated the relationship between the ratio of C-reactive protein to albumin (CAR) before thrombolysis, HT, and functional outcomes in patients with acute ischemic stroke. Methods: We retrospectively analyzed data from 354 patients who received thrombolytic therapy at the Second Affiliated Hospital of the Wenzhou Medical University in China between July 2014 and May 2022. CAR was measured on admission, and HT was identified by cranial computed tomography (CT) within 24-36 h after treatment. Poor outcome was defined as a score on the modified Rankin Scale (mRS) > 2 at discharge. The multivariate logistic regression model was used to investigate the association between CAR, HT, and poor outcome after thrombolysis, respectively. Results: A total of 354 patients were analyzed, and their median CAR was 0.61 (interquartile range, 0.24-1.28). CAR was significantly higher in the 56 patients (15.8%) who experienced HT than in those who did not (0.94 vs. 0.56, p < 0.001), and the 131 patients (37.0%) who experienced poor outcome than in those who did not (0.87 vs. 0.43, p < 0.001). Multivariate logistic regression indicated that CAR was an independent risk factor for both HT and poor outcome. The risk of HT was significantly higher among patients whose CAR fell in the fourth quartile than among those with CAR in the first quartile (OR 6.64, 95% CI 1.83 to 24.17, p = 0.004). Patients with CAR in the third quartile were more likely to experience poor outcome (OR 3.35, 95% CI 1.32 to 8.51, p = 0.01), as were those in the fourth quartile (OR 7.33, 95% CI 2.62 to 20.50, p < 0.001), compared to patients with CAR in the first quartile. Conclusion: High ratio of C-reactive protein to albumin in individuals with ischemic stroke is associated with an increased risk of HT and poor functional outcomes after thrombolysis.

Armadillo repeat only protein GS10 negatively regulates brassinosteroid signaling to control rice grain size.

Grain yield and grain quality are major determinants in modern breeding controlled by many quantitative traits loci (QTLs) in rice (Oryza sativa). However, the mechanisms underlying grain shape and quality are poorly understood. Here, we characterize a QTL for grain size and grain quality via map-based cloning from wild rice (W1943), GS10 (Grain Size on Chromosome 10), which encodes a protein with 6 tandem armadillo repeats. The null mutant gs10 shows slender and narrow grains with altered cell size, which has a pleiotropic effect on other agronomical traits. Functional analysis reveals that GS10 interacts with TUD1 (Taihu Dwarf1) and is epistatic to OsGSK2 (glycogen synthase kinase 2) through regulating grain shape and lamina joint inclination, indicating it is negatively involved in brassinosteroid (BR) signaling. Pyramiding gs10 and the grain size gene GW5 into cultivar GLA4 substantially improved grain shape and appearance quality. Natural variation analysis revealed that gs10 from the wild rice Oryza rufipogon W1943 is a rare allele across the rice population. Collectively, these findings advance our understanding of the underlying mechanism of grain shape and provide the beneficial allele of gs10 for future rice breeding and genetic improvement.

Protective Effects of Sophorae tonkinensis Gagnep. (Fabaceae) Radix et Rhizoma Water Extract on Carbon Tetrachloride-Induced Acute Liver Injury.

Sophorae tonkinensis Radix et Rhizoma (STR) is a traditional Chinese herbal medicine. STR can reduce aminotransferase activity; however, the specific mechanism remains unclear. Here, we explored the potential therapeutic effects and hepatoprotective mechanism of STR on liver damage in mice. The chemical characteristics of the extract were characterized using ultra-high-performance liquid chromatography-tandem mass spectrometry fingerprinting, and its antioxidant capacity was verified using free radical scavenging tests. Forty-eight Kunming mice were randomly assigned into six groups. The model was made after the corresponding drug was given. The results showed that the STR water extract pretreatment significantly reduced serum aminotransferase and related liver function indicators compared with that in the model group. Furthermore, the STR water extract pretreatment significantly inhibited the apoptosis of liver cells, the level of liver high-mobility group box 1 (HMGB1), and inflammatory factors in hepatic tissue compared with that in the model group, and significantly downregulated the levels of toll-like receptor 4 (TLR4), Myeloid differentiation factor 88 (MyD88), and nuclear factor kappa B (NF-κB) compared with those in the model group. Overall, the STR water extract exerted a significant protective effect on CCL4-induced acute liver injury in this study, and the accurate active ingredients of the STR water extract will be explored in the near future.

Underlying mechanisms of acupuncture therapy on polycystic ovary syndrome: Evidences from animal and clinical studies.

Polycystic ovary syndrome (PCOS) is a common endocrine and metabolic disorder among women of reproductive age. Current standard treatment includes lifestyle change, oral pharmacological agents, and surgical modalities. However, the efficacy of current therapies is less than satisfactory. Clinical evidence has shown that acupuncture is effective for regulating hormone levels, promoting ovulation, and attenuating insulin resistance in patients with PCOS. Acupuncture may affect the production of ß-endorphin, which may lead to gonadotropin-releasing hormone secretion and then affect ovulation, menstrual cycle, and fertility. The mechanism of acupuncture for patients with PCOS has not been comprehensively reviewed so far. Better understanding of the mechanisms of acupuncture would help popularize the use of acupuncture therapy for patients with PCOS. In this narrative review, we aimed to overview the potential mechanisms and evidence-based data of acupuncture on PCOS, and analyze the most frequently used acupoints based on animal and clinical studies. The results of this study will contribute to a better understanding of the current situation in this field.

Blood pressure monitoring techniques in the natural state of multi-scenes: A review.

Blood pressure is one of the basic physiological parameters of human physiology. Frequent and repeated measurement of blood pressure along with recording of environmental or other physiological parameters when measuring blood pressure may reveal important cardiovascular risk factors that can predict occurrence of cardiovascular events. Currently, wearable non-invasive blood pressure measurement technology has attracted much research attention. Several different technical routes have been proposed to solve the challenge between portability or continuity of measurement methods and medical level accuracy of measurement results. The accuracy of blood pressure measurement technology based on auscultation and oscillography has been clinically verified, while majority of other technical routes are being explored at laboratory or multi-center clinical demonstration stage. Normally, Blood pressure measurement based on oscillographic method outside the hospital can only be measured at intervals. There is a need to develop techniques for frequent and high-precision blood pressure measurement under natural conditions outside the hospital. In this paper, we discussed the current status of blood pressure measurement technology and development trends of blood pressure measurement technology in different scenarios. We focuses on the key technical challenges and the latest advances in the study of miniaturization devices based on oscillographic method at wrist and PTT related method at finger positions as well as technology processes. This study is of great significance to the application of high frequency blood pressure measurement technology.

Research and Development of Ankle-Foot Orthoses: A Review.

The ankle joint is one of the important joints of the human body to maintain the ability to walk. Diseases such as stroke and ankle osteoarthritis could weaken the body's ability to control joints, causing people's gait to be out of balance. Ankle-foot orthoses can assist users with neuro/muscular or ankle injuries to restore their natural gait. Currently, passive ankle-foot orthoses are mostly designed to fix the ankle joint and provide support for walking. With the development of materials, sensing, and control science, semi-active orthoses that release mechanical energy to assist walking when needed and can store the energy generated by body movement in elastic units, as well as active ankle-foot orthoses that use external energy to transmit enhanced torque to the ankle, have received increasing attention. This article reviews the development process of ankle-foot orthoses and proposes that the integration of new ankle-foot orthoses with rehabilitation technologies such as monitoring or myoelectric stimulation will play an important role in reducing the walking energy consumption of patients in the study of human-in-the-loop models and promoting neuro/muscular rehabilitation.

A Refined Blood Pressure Estimation Model Based on Single Channel Photoplethysmography.

This study proposed a refined BP prediction strategy that using single-channel photoplethysmography (PPG) signals to stratify populations by cardiovascular status before BP estimation. Combining demographic characteristics (age, gender) and pulse wave morphological features, the random forest was applied to screen two kinds of typical cardiovascular diseases (CVDs), with an accuracy of 92.2%. A deep learning model (BiLSTM-At) was proposed to estimate the long-term BP trend for different CVD groups. Transfer learning technique was used for personalized modeling to reduce computational complexity while improving performance. The method was validated on 255 patients with different CVDs. The mean absolute errors (MAEs) of systolic blood pressure (SBP) and diastolic blood pressure (DBP) estimation were 2.815 mmHg and 1.876 mmHg for normal subjects, 3.024 mmHg and 1.334 mmHg for AF subjects, and 4.444 mmHg and 2.549 mmHg for CA subjects. The results met the American Association for the Advancement of Medical Instrumentations (AAMI) and British Hypertension Society (BHS) Class A criteria. This indicated that our strategy has good performance and can realize long-term monitoring of BP through a small batch samples, with the potential to implement real-time monitoring in healthy devices.