Biological Signals Research Articles

Identification and functional prediction of long non-coding RNA and mRNA related to connective tissue disease-associated interstitial lung diseases.

Recently, the role of long non-coding RNA (lncRNA) in rheumatic immune diseases has attracted widespread attention. However, knowledge of lncRNA in connective tissue disease-associated interstitial lung disease (CTD-ILD) is limited. This study explored the expression profile and possible mechanisms of lncRNA and mRNA in peripheral blood mononuclear cells (PBMCs) of CTD-ILD patients, especially systemic sclerosis (SSc)-ILD and rheumatoid arthritis (RA)-ILD. LncRNA microarray analysis identified 240 diferentially expressed lncRNAs and 218 diferentially expressed mRNA in the CTD-ILD group and the connective tissue disease without associated interstitial lung disease (CTD-NILD) group. The bioinformatics analysis of diferential genes has identified several important biological processes and signal pathways, including nuclear factor kappa B (NF-kappa B) signaling pathway, interleukin 17 (IL-17) signaling pathway, B cell receptor signaling pathway. Relative expression levels of five diferentially expressed lncRNAs and one mRNA in 120 SSc and RA patients with or without ILD were detected by quantitative reverse-transcription (PCR). The ENST00000604692 expression level was significantly higher in the ILD than the without interstitial lung disease (NILD) group; T311354 and arginase-1 were significantly higher in SSc than RA group. These data suggest that the specific profile of lncRNA in PBMCs of CTD-ILD patients and the potential signal pathways related to the pathogenesis of CTD-ILD, which may provide newfound insights for the diagnosis and treatment of CTD-ILD patients.

Data integration and inference of gene regulation using single-cell temporal multimodal data with scTIE.

Single-cell technologies offer unprecedented opportunities to dissect gene regulatory mechanisms in context-specific ways. Although there are computational methods for extracting gene regulatory relationships from scRNA-seq and scATAC-seq data, the data integration problem, essential for accurate cell type identification, has been mostly treated as a standalone challenge. Here we present scTIE, a unified method that integrates temporal multimodal data and infers regulatory relationships predictive of cellular state changes. scTIE uses an autoencoder to embed cells from all time points into a common space by using iterative optimal transport, followed by extracting interpretable information to predict cell trajectories. Using a variety of synthetic and real temporal multimodal data sets, we show scTIE achieves effective data integration while preserving more biological signals than existing methods, particularly in the presence of batch effects and noise. Furthermore, on the exemplar multiome data set we generated from differentiating mouse embryonic stem cells over time, we show scTIE captures regulatory elements highly predictive of cell transition probabilities, providing new potentials to understand the regulatory landscape driving developmental processes.

Functional engineering of human iPSC-derived parasympathetic neurons enhances responsiveness to gastrointestinal hormones.

Food-derived biological signals are transmitted to the brain via peripheral nerves through the paracrine activity of gastrointestinal (GI) hormones. The signal transduction circuit of the brain-gut axis has been analyzed in animals; however, species-related differences and animal welfare concerns necessitate investigation using in vitro human experimental models. Here, we focused on the receptors of five GI hormones (CCK, GLP1, GLP2, PYY, and serotonin (5-HT)), and established human induced pluripotent stem cell (iPSC) lines that functionally expressed each receptor. Compared to the original iPSCs, iPSCs expressing one of the receptors did not show any differences in global mRNA expression, genomic stability, or differentiation capacities of the three germ layers. We induced parasympathetic neurons from these established iPSC lines to assess vagus nerve activity. We generated GI hormone receptor-expressing neurons (CCKAR, GLP1R, and NPY2R-neuron) and tested their responsiveness to each ligand using Ca2+ imaging and microelectrode array recording. GI hormone receptor-expressing neurons (GLP2R and HTR3A) were generated directly by gene induction into iPSC-derived peripheral nerve progenitors. These receptor-expressing neurons promise to contribute to a better understanding of how the body responds to GI hormones via the brain-gut axis, aid in drug development, and offer an alternative to animal studies.

NClSilico: A Closed-Loop neuromodulation platform in silico

The closed-loop electrophysiology is gradually applied to targeted stimulation of nervous system. According to desired neural biomarkers acquired by biological signal measurement, the stimulus pattern can be automatically adjusted with the suitable closed-loop control algorithms. Moreover, the neural computing uses the numerical computing models to simulate the structures, functions and relations of the neurons and the neural networks, as the substitute of biological brain. As the prevalence of the hardware-in-loop (HIL), the HIL closed-loop electrophysiology not only bypasses the problem of biological experiments but also makes up for the insufficient efficiency and real-time performance of software digital simulation. This paper proposes a hardware experiment platform mainly made up of TMS320F28377D digital signal processor (DSP) and AMD Ryzen 5 5600X 6-Core Processor (CPU) for closed-loop electrophysiological research. The hardware platform is programable, portable, real-time and supports the repeated experiments. Closed-loop electrophysiological experiments with different kinds of control algorithms, stimulation waveforms, feedback variables or neuron models can be implemented on the platform, it may promote the development of researches in the field of closed-loop neuroscience and biomedical engineering.

Ga‐Based Liquid Metals: Versatile and Biocompatible Solutions for Next‐Generation Bioelectronics

AbstractThe utilization of gallium (Ga)‐based liquid metals (LMs) as functional materials in bioelectronics has been extensively explored over the past decade as a key to stimulation of biological systems and recording of biological signals. The motivation behind this class of electronics is driven by the opportunities to exploit mechanical properties similar to biological tissues. These bioelectronic devices are required to maintain functionality under deformation and, especially for implantable applications, should interface with biological tissues in a minimally invasive manner. LMs are attractive for such applications due to their ability to deform while retaining their electrical conductivity. Furthermore, unlike most liquids that form droplets to minimize surface energy, the ultrathin solid‐state oxide layer on the outer surface of LMs enables them to be shaped to specific 3D patterns. Unlike mercury, Ga‐based LMs are considered biocompatible due to their low toxicity and vapor pressure, highlighting their potential as advantageous materials for bioelectronics. This review comprehensively presents the fundamental aspects of these materials, with a focus on their effectiveness in stimulating and recording specific biological tissues, as well as their diverse applications as soft and stretchable electrodes in bioelectronics. Additionally, this review investigates additional strategies aimed at driving future advancements in this field.

Serpentinization-associated travertines as spatio-temporal archives for lipid biomarkers key for the search for life on Mars

Serpentinization is a well-known aqueous alteration process that may have played important roles in the origins and early evolution of life on Earth, and perhaps Mars, but there are still aspects related to biomarker distribution, partitioning, and preservation that merit further study. To assess the role that precipitation of carbonate phases in serpentinization settings may have on biomarker preservation, we search for life signs in one of the world's largest outcrops of subcontinental peridotites (Ronda, South Spain). We investigate the organic record of groundwater and associated carbonate deposits (travertines) in seven hyperalkaline springs, and reconstruct the biological activity and metabolic interactions of the serpentinization-hosted ecosystem. We identified lipid biomarkers and isotopic evidences of life, whose concentration and variety were much lower in groundwater than travertine deposits (ppb/ppt versus ppm level). Groundwater carried organics of abiotic (n-alkanes with values of CPI ∼ 1) and/or biotic origin, of fresher (e.g. acids or alcohols) or more diagenetized (mature hopanes and n-alkanes) nature. In contrast, associated travertines held a more prolific record of biomarkers incorporating (molecular and isotopic) fingerprints of surface (mostly phototrophs) and subsurface (chemolithotrophs, methanogens and/or methanotrophs) life. Serpentinization-associated travertines seem to act as biomolecule archives over time fed by autochthonous and allochthonous sources, hence amplifying the dim biological signal of groundwater. These results illustrate the relevance of serpentinization-associated surface mineral deposits in searching for traces of life on analogous environments on Mars. We highlight the diversity of lipids produced in serpentinizing land environments and emphasize the potential of these geostable biomolecules to preserve fingerprints of life.

Automated differential diagnostics of respiratory diseases using an electronic stethoscope

Abstract Introduction: The outbreak of the coronavirus infection, which has escalated into a pandemic, has worsened the already unfavourable situation with respiratory system diseases in Ukraine. The burden on doctors has significantly increased, necessitating the exploration of simplified and expedited methods for conducting routine respiratory examinations. The research aims to describe a model for creating an automated differential diagnosis of respiratory noise using an electronic stethoscope, combining medical and clinical information about the types of respiratory noise characterizing the normal or pathological state of the respiratory system with a means of its information and technical processing. Material and methods: The research methods were analysis of theoretical information about the types of respiratory noise, analysis of technical information for choosing an information technology tool for processing biological signals; synthesis of the results; modelling. Results: The research resulted in a model of automated differential diagnosis based on the principle of auscultation, which includes the process of extracting the sound of air movement inside and outside the lungs and the classification of the extracted sounds. Automation of this process concerned only the classification of the extracted sounds since the principle of extraction itself was the same for both mechanical and automatic implementations. Conclusions: The automatic classification process was intended to reduce the time of the procedure and reduce the influence of the human factor, eliminating the possibility of medical error. To implement the process, a deep machine learning method was used, the array of information for which was to be a created phonotheque of acoustic signals of the respiratory system, which would include all types of respiratory noise concerning normal or pathological processes in the body.

An engineered lymph node comprising porous collagen scaffold with hybridized biological signals embedded in B cell membrane coatings

Complications can arise from damaging or removing lymph nodes after surgeries for malignant tumours. Our team has developed an innovative solution to recreate lymph nodes via an engineering approach. Using a Type II collagen scaffold coated with B cell membranes for the sake of attracting T cells in different regions, we could mimic the thymus-dependent and thymus-independent areas in vitro. This engineering strategy based on biophysical mimicry has a great potential for clinical applications. By further conjugating biological signals, anti-CD3/28, onto the scaffold coated with the B cell membrane, we achieved an 11.6-fold expansion of T cells within 14 days of in vitro culture while ensuring their activity, phenotype homeostasis, and differentiation capacity kept intact. Artificial lymph nodes had excellent biocompatibility and caused no pathological or physiological adverse effects after implantation into C57BL6 mice. In vivo assays also demonstrated that this artificial lymph node system positively adhered to omental tissues, creating an environment that fostered T cell growth and prevented cellular failure and death. Additionally, it induced vascular and lymphatic vessel invasion, which was beneficial to the migration and circulation of T cells between this system and peripheral blood. Due to the porous collagen fibre structure, it also facilitated the infiltration of host immune cells. This work opens new avenues to immune organ regeneration via a tissue engineering approach.

Advanced Diffusion-Weighted MRI for Cancer Microstructure Assessment in Body Imaging, and Its Relationship With Histology.

Diffusion-weighted magnetic resonance imaging (DW-MRI) aims to disentangle multiple biological signal sources in each imaging voxel, enabling the computation of innovative maps of tissue microstructure. DW-MRI model development has been dominated by brain applications. More recently, advanced methods with high fidelity to histology are gaining momentum in other contexts, for example, in oncological applications of body imaging, where new biomarkers are urgently needed. The objective of this article is to review the state-of-the-art of DW-MRI in body imaging (ie, not including the nervous system) in oncology, and to analyze its value as compared to reference colocalized histology measurements, given that demonstrating the histological validity of any new DW-MRI method is essential. In this article, we review the current landscape of DW-MRI techniques that extend standard apparent diffusion coefficient (ADC), describing their acquisition protocols, signal models, fitting settings, microstructural parameters, and relationship with histology. Preclinical, clinical, and in/ex vivo studies were included. The most used techniques were intravoxel incoherent motion (IVIM; 36.3% of used techniques), diffusion kurtosis imaging (DKI; 16.7%), vascular, extracellular, and restricted diffusion for cytometry in tumors (VERDICT; 13.3%), and imaging microstructural parameters using limited spectrally edited diffusion (IMPULSED; 11.7%). Another notable category of techniques relates to innovative b-tensor diffusion encoding or joint diffusion-relaxometry. The reviewed approaches provide histologically meaningful indices of cancer microstructure (eg, vascularization/cellularity) which, while not necessarily accurate numerically, may still provide useful sensitivity to microscopic pathological processes. Future work of the community should focus on improving the inter-/intra-scanner robustness, and on assessing histological validity in broader contexts. LEVEL OF EVIDENCE: NA TECHNICAL EFFICACY: Stage 2.

Mechanisms of carbon dioxide detection in the earthworm Dendrobaena veneta

IntroductionCarbon dioxide (CO2) is a critical biological signal that is noxious to many animals at high concentrations. The earthworm Dendrobaena veneta lives in subterranean burrows containing high levels of CO2 and respires through its skin. Despite the ecological and agricultural importance of earthworms, relatively little is known about how they make decisions in their environment, including their response to elevated levels of CO2.MethodsTo examine CO2 detection in this species, we designed the exudate assay, in which we placed an earthworm in a sealed container, exposed it to varying concentrations of CO2 for one minute, and recorded the amount of exudate secreted. Because earthworms excrete exudate in response to noxious stimuli, we hypothesized that the amount of exudate produced was proportional to the amount of irritation. We repeated these experiments after treatment with several blockers for molecules with potential involvement in CO2 detection, including carbonic anhydrases, guanylate cyclase, TRPA1, ASICs, and OTOP channels. We also confirmed the presence of homologous transcripts for each of these gene families in an epithelial transcriptome for D. veneta. Additionally, since organisms often detect CO2 levels indirectly by monitoring the conversion to carbonic acid (a weak acid), we used the exudate assay to evaluate aversion to additional weak acids (formic acid, acetic acid, and propionic acid).ResultsEarthworms excreted significantly more exudate in response to CO2 in a dosage-dependent manner, and this response was muted by the general carbonic anhydrase inhibitor acetazolamide, the carbonic anhydrase IX/XII inhibitor indisulam, the calcium channel blocker ruthenium red, the sodium channel blocker amiloride, and the acid-sensing ion channel blocker diminazene aceturate.DiscussionThese data provide evidence of the role of carbonic anhydrase and epithelial sodium channels in earthworm CO2 detection, establish that, similar to other subterranean-dwelling animals, earthworms are extremely tolerant of CO2, and contribute to our understanding of the mechanisms used by earthworms to detect and react to weak acids in their environment.

A flexible electrode with tetra-chiral structure connected in serpentine shape

Flexible electrodes are usually well-matched to the substrate as the core component of flexible electronics technology. However, when large deformation occurs, the conductive layer of flexible electrodes can mechanically fracture due to insufficient mechanical properties, leading to the failure of flexible electronic devices. Improving the mechanical properties of flexible electrodes is essential for the development of flexible electronics. Herein, a flexible electrode with a serpentine shape tetra-chiral structure is designed and fabricated via screen-printed process based on existing tetra-chiral structure. The research demonstrates that the serpentine tetra-chiral structure can improve the mechanical properties of the flexible electrode and the maximum tensile stress is reduced by 87.19 % relative to existing tetra-chiral structure. The flexible electrode is still conductive when the strain of that is 70 %, and the resistance is only 5 Ω and 4.4 Ω, respectively, at a bending angle of 180° and following 1000 times fold cycles. In addition, the flexible electrodes fabricated in this paper are utilized to realize the collection of ECG signals and pulse signals, showing greater potential in biological signal monitoring. The strategy proposed here is expected to maintain electrodes’ original functions under repeated use and complex deformation.

Semisupervised Deep Features of Time-Frequency Maps for Multimodal Emotion Recognition

Traditional approaches for emotion recognition utilize unimodal physiological signals. The effectiveness of such systems is affected by some limitations. To overcome them, this paper proposes a new method based on time-frequency maps that extract the features from multimodal biological signals. At first, the fusion of electroencephalogram (EEG) and peripheral physiological signal (PPS) is performed, and then, the two-dimensional discrete orthonormal Stockwell transform (2D-DOST) of the multimodal signal matrix is calculated to obtain time-frequency maps. A convolutional neural network (CNN) is then utilized to extract the local deep features from the absolute output of the 2D-DOST. Since there are uninformative deep features, the semisupervised dimension reduction scheme reduces them by balancing the generalization and discrimination. Finally, the classifier recognizes the emotion. The Bayesian optimizer finds the proper SSDR and classifier parameter values to maximize the recognition accuracy. The performance of the proposed method is evaluated on the DEAP dataset considering the two- and four-class scenarios through extensive simulations. This dataset consists of electroencephalograph (EEG) signals in 32 channels and peripheral physiological signals (PPSs) in eight channels from 32 subjects. The proposed method reaches the accuracy of 0.953 and 0.928 for two- and four-class scenarios, respectively. The results indicate the efficiency of the multimodal signals for detecting emotions compared to that of unimodal signals. Also, the results indicate that the proposed method outperforms the recently introduced ones.

Protein-based bandpass filters for controlling cellular signaling with chemical inputs

Biological signal processing is vital for cellular function. Similar to electronic circuits, cells process signals via integrated mechanisms. In electronics, bandpass filters transmit frequencies with defined ranges, but protein-based counterparts for controlled responses are lacking in engineered biological systems. Here, we rationally design protein-based, chemically responsive bandpass filters (CBPs) showing OFF-ON-OFF patterns that respond to chemical concentrations within a specific range and reject concentrations outside that range. Employing structure-based strategies, we designed a heterodimeric construct that dimerizes in response to low concentrations of a small molecule (ON), and dissociates at high concentrations of the same molecule (OFF). The CBPs have a multidomain architecture in which we used known drug receptors, a computationally designed protein binder and small-molecule inhibitors. This modular system allows fine-tuning for optimal performance in terms of bandwidth, response, cutoff and fold changes. The CBPs were used to regulate cell surface receptor signaling pathways to control cellular activities in engineered cells.

Multitask Learning for Automated Sleep Staging and Wearable Technology Integration

Scoring sleep stages is an essential procedure for the diagnosis of sleeping disorders. Conventional sleep staging is a laborious and costly procedure requiring multimodal biological signals and an expert for the assessment. There has always been a demand for approaches which can exempt the need to going through diagnostic procedures under specialized facilities and enable automated sleep staging. Herein, a high‐performance multitask learning model enabling high‐accuracy sleep staging using heart rate data is reported. The proposed algorithm exhibits superior performance with reduced computational resource in comparison with the competing machine and deep learning algorithms when trained and evaluated using electrocardiography and photoplethysmogram (PPG) data. The reported model consumes ≈7.5 times less training parameters and ≈75% less amount of input data than the previously reported models and yields better or comparable performance (mean per night accuracy of 77.5% and Cohen's kappa of 0.643). To demonstrate its potential for wearable electronics, the reported algorithm is implemented in a fully integrated watch. The reported integrated watch is a stand‐alone fully functional platform, which automatedly captures PPG data from the subject's wrist, predicts sleep stages, and displays the result on a screen as well as an associated smartphone application.

The liver-derived exosomes stimulate insulin gene expression in pancreatic beta cells under condition of insulin resistance.

An insufficient functional beta cell mass is a core pathological hallmark of type 2 diabetes (T2D). Despite the availability of several effective pharmaceuticals for diabetes management, there is an urgent need for novel medications to protect pancreatic beta cells under diabetic conditions. Integrative organ cross-communication controls the energy balance and glucose homeostasis. The liver and pancreatic islets have dynamic cross-communications where the liver can trigger a compensatory beta cell mass expansion and enhanced hormonal secretion in insulin-resistant conditions. However, the indispensable element(s) that foster beta cell proliferation and insulin secretion have yet to be completely identified. Exosomes are important extracellular vehicles (EVs) released by most cell types that transfer biological signal(s), including metabolic messengers such as miRNA and peptides, between cells and organs. We investigated whether beta cells can take up liver-derived exosomes and examined their impact on beta cell functional genes and insulin expression. Exosomes isolated from human liver HepG2 cells were characterized using various methods, including Transmission Electron Microscopy (TEM), dynamic light scattering (DLS), and Western blot analysis of exosomal markers. Exosome labeling and cell uptake were assessed using CM-Dil dye. The effect of liver cell-derived exosomes on Min6 beta cells was determined through gene expression analyses of beta cell markers and insulin using qPCR, as well as Akt signaling using Western blotting. Treatment of Min6 beta cells with exosomes isolated from human liver HepG2 cells treated with insulin receptor antagonist S961 significantly increased the expression of beta cell markers Pdx1, NeuroD1, and Ins1 compared to the exosomes isolated from untreated cells. In line with this, the activity of AKT kinase, an integral component of the insulin receptor pathway, is elevated in pancreatic beta cells, as represented by an increase in AKT's downstream substrate, FoxO1 phosphorylation. This study suggests that liver-derived exosomes may carry a specific molecular cargo that can affect insulin expression in pancreatic beta cells, ultimately affecting glucose homeostasis.

Hexagonal image segmentation on spatially resolved transcriptomics

Spatial transcriptomics is a rapidly evolving field that enables researchers to capture comprehensive molecular profiles while preserving information about the physical locations. One major challenge in this research area involves the identification of spatial domains, which are distinct regions characterized by unique gene expression patterns. However, current unsupervised methods have struggled to perform well in this regard due to the presence of high levels of noise and dropout events in spatial transcriptomic profiles. In this paper, we propose a novel hexagonal Convolutional Neural Network (hexCNN) for hexagonal image segmentation on spatially resolved transcriptomics. To address the problem of noise and dropout occurrences within spatial transcriptomics data, we first extend an unsupervised algorithm to a supervised learning method that can identify useful features and reduce noise hindrance. Then, inspired by the classical convolution in convolutional neural networks (CNNs), we designed a regular hexagonal convolution to compensate for the missing gene expression patterns from adjacent spots. We evaluated the performance of hexCNN by applying it to the DLPFC dataset. The results show that hexCNN achieves a classification accuracy of 86.8% and an average Rand index (ARI) of 77.1% (1.4% and 2.5% higher than those of GNNs). The results also demonstrate that hexCNN is capable of removing the noise caused by batch effect while preserving the biological signal differences.

Design of 4-bit absolute value detector with low energy

The article highlights the latest developments in the design of low-power 4-bit Absolute Value Detector (AVD) circuits that are utilized in digital signal processing (DSP) applications. DSP applications like audio and video processing, biological signal processing, and digital communication systems rely heavily on the AVD circuit, which determines the absolute value of an input signal. The article introduces a low-energy 4-bit AVD circuit based on pass transistors that incorporates advanced optimization techniques like adiabatic logic, approximation techniques, and layout optimization. This optimized AVD circuit achieves remarkable results in terms of power consumption and energy efficiency. With a power consumption of just 0.6 nW and an energy efficiency of 0.6 pJ per cycle, the circuit maintains precision and rapid response time. These advancements in AVD circuit design can be highly beneficial for portable and battery-powered devices such as earplugs, implants, and cell phones, as well as electronic components like Static Random Access Memory (SRAM) and motherboards. Overall, the proposed low-energy 4-bit AVD circuit is a significant development in the DSP field, enabling more efficient and effective processing of digital signals.

A guide to Whittle maximum likelihood estimator in MATLAB.

The assessment of physiological complexity via the estimation of monofractal exponents or multifractal spectra of biological signals is a recent field of research that allows detection of relevant and original information for health, learning, or autonomy preservation. This tutorial aims at introducing Whittle's maximum likelihood estimator (MLE) that estimates the monofractal exponent of time series. After introducing Whittle's maximum likelihood estimator and presenting each of the steps leading to the construction of the algorithm, this tutorial discusses the performance of this estimator by comparing it to the widely used detrended fluctuation analysis (DFA). The objective of this tutorial is to propose to the reader an alternative monofractal estimation method, which has the advantage of being simple to implement, and whose high accuracy allows the analysis of shorter time series than those classically used with other monofractal analysis methods.

The Expression and Function of Piezo Channels in Bladder.

The ability for bladder to perceive and analyze mechanical stimuli, such as stretch and filling, is crucial for its functions, such as urinary storage and voiding. The Piezo channel family, including Piezo1 and Piezo2, represents one of the most essential mechanosensitive ion channels in mammals and is involved in a wide array of physiological and pathological processes. It has been demonstrated in numerous investigations that Piezo channels play a key role in mechanical transduction in various types of cells in bladder by converting mechanical stimuli into biological signals. Notably, mounting evidence suggests that Piezo channels are functionally significant for bladder and are related to several bladder disorders. This review systematically summarizes the importance/role and features of Piezo channels in bladder, including their biophysical properties, location, and functions, with attention specifically paid to their association with the physiology and pathophysiology of bladder. This review aims to provide a novel perspective for the future clinical treatment of bladder dysfunction.

Recent advancements in machine learning enabled portable and wearable biosensors

Recent advances in noninvasive portable and wearable biosensors have attracted significant attention due to their capability to offer continual physiological information for continuous healthcare monitoring through the collection of biological signals. To make the collected biological data understandable and improve the efficacy of these biosensors, scientists have integrated machine learning (ML) with biosensors to analyze large sensing data through various ML algorithms. In this article, we have highlighted the recent developments in ML-enabled noninvasive biosensors. Initially, we introduced and discussed the basic features of ML algorithms used in data processing to build an intelligent biosensor system and the capability to make clinical decisions. Next, the principles of portable and wearable biosensors, the application of different ML models in diverse biosensors for healthcare applications, and their impact on the performance of biosensors are discussed. The last section highlights the challenges (such as data privacy, consistency, stability, accuracy, scalable production, and adaptive learning capacity), future prospects, and necessary steps required to address these issues, spotlighting their revolutionizing impact on the healthcare industry for the development of next-generation ML-enabled efficient biosensors.