Cited by 295Advanced Sensor and Energy Harvesting MaterialsNon-Invasive Vital Sign MonitoringInternet of Things and AI

The DOI matches its Crossref record; 209 of the 209 references it cites were found in a registry or an index; 6 of the 290 sources its claims cite were checked for support.

Artificial intelligence enhanced sensors - enabling technologies to next-generation healthcare and biomedical platform

Open access

Abstract

The fourth industrial revolution has led to the development and application of health monitoring sensors that are characterized by digitalization and intelligence. These sensors have extensive applications in medical care, personal health management, elderly care, sports, and other fields, providing people with more convenient and real-time health services. However, these sensors face limitations such as noise and drift, difficulty in extracting useful information from large amounts of data, and lack of feedback or control signals. The development of artificial intelligence has provided powerful tools and algorithms for data processing and analysis, enabling intelligent health monitoring, and achieving high-precision predictions and decisions. By integrating the Internet of Things, artificial intelligence, and health monitoring sensors, it becomes possible to realize a closed-loop system with the functions of real-time monitoring, data collection, online analysis, diagnosis, and treatment recommendations. This review focuses on the development of healthcare artificial sensors enhanced by intelligent technologies from the aspects of materials, device structure, system integration, and application scenarios. Specifically, this review first introduces the great advances in wearable sensors for monitoring respiration rate, heart rate, pulse, sweat, and tears; implantable sensors for cardiovascular care, nerve signal acquisition, and neurotransmitter monitoring; soft wearable electronics for precise therapy. Then, the recent advances in volatile organic compound detection are highlighted. Next, the current developments of human-machine interfaces, AI-enhanced multimode sensors, and AI-enhanced self-sustainable systems are reviewed. Last, a perspective on future directions for further research development is also provided. In summary, the fusion of artificial intelligence and artificial sensors will provide more intelligent, convenient, and secure services for next-generation healthcare and biomedical applications.

Overview

AI snapshot

Written from the paper’s full text.

TL;DR

This review argues that integrating AI, IoT, and health monitoring sensors can enable closed-loop healthcare systems with real-time monitoring, data analysis, diagnosis, and treatment recommendations. It surveys wearable, implantable, therapeutic, VOC-sensing, human-machine interface, multimodal, and self-sustainable sensor technologies enhanced by machine learning.

Key findings

  • AI is presented as a solution to major HMS limitations: sensor noise and drift, difficulty extracting useful information from large data, and the open-loop nature of traditional sensors lacking feedback or control signals.
  • Wearable and implantable examples include a spider-inspired TUNES sensor for pulse, muscle contraction, and respiration; a PEDOT-coated mask for real-time respiratory rate; and an NiO thermistor that recorded a 27% rise in respiratory rate and a 65% reduction in temperature variation amplitude under low blood oxygen saturation.
  • Self-powered implantable sensors include iTEAS, which monitored functions for 72 hours after chest closure, and SEPS, which achieved 1.195 mV/mmHg sensitivity with linearity R²=0.997 for intracardiac pressure monitoring.
  • AI-enhanced VOC and HMI systems report high performance: a graphene plasmon SEIRA platform detected SO₂, NO₂, N₂O, and NO with a 1-minute response time and 800 zeptomoles per μm²; a MOF-based SERS platform reached a 10 ppb detection limit; a graphene varactor array achieved 98% accuracy for five analytes and 89% with 1-octene added; PCA+SVM reached 100% recognition for methanol, ethanol, and isopropanol; a TENG smart sock achieved 93.54% accuracy for 13 gait patterns; a smart mat achieved 96.0%; and HSVM fusion of radar and pressure sensors reached 92.5% gesture classification accuracy.

Methods

  • Narrative review covering wearable physical and chemical sensors, in vivo self-powered sensors, neural interfaces, flexible electronics for therapy, VOC detection, human-machine interfaces, AI-enhanced multimode sensors, and AI-enhanced self-sustainable systems.
  • Synthesizes cited studies and figures across materials, device structure, system integration, and application scenarios; no primary data collection, systematic search protocol, or meta-analysis is reported.
  • Discusses AI roles including sensor design, data preprocessing, dimensionality reduction, classification, and multimodal data fusion.

Limitations

  • Paper-stated: successful implementation of AI-enhanced sensors faces challenges in data privacy and security, regulatory and ethical considerations, and robust validation frameworks including generalizability, robustness to data variation, and interpretability.
  • Paper-stated: implantable neural interfaces still need long-term stable interfaces, improved resolution and specificity, ability to interface with large neuron populations, and safe clinical protocols.
  • Evident from text: as a review, it does not provide a systematic search strategy, inclusion criteria, or quantitative synthesis, and many performance numbers come from cited primary studies rather than new experiments.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1186/s42234-023-00118-1

Cites

209 of 209 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Figures

Fig. 1 Overview of the development of artificial sensors enabled by intelligent technologies. This figure illustrates the road map of sensing technologies (left side) and artificial intelligence technologies (right side) and the development of diversified applications in self-powered, implantable, wearable sensors and smart home, machine learning (ML), VOC sensing, and human-machine interfaces
Fig. 1 Overview of the development of artificial sensors enabled by intelligent technologies. This figure illustrates the road map of sensing technologies (left side) and artificial intelligence technologies (right side) and the development of diversified applications in self-powered, implantable, wearable sensors and smart home, machine learning (ML), VOC sensing, and human-machine interfacesCC BY · PubMed Central
Fig. 2 Wearable technologies for diversified applications. a A tunable, ultrasensitive, nature-inspired, epidermal sensor (TUNES) inspired by a spider’s sensory system with a tenable sensitivity by preset strain, which not only can measure respiration and muscle contraction but also serves as a skin-attachable biomedical sensor (Kim et al. 2023). b An respiratory rate sensor that detects breath patterns in real-time, which is fabricated by depositing PEDOT on a disposable mask (Clevenger et al. 2021). c A sensitive and flexible artificial skin comprising a negative temperature coefficient thermistor that can be attached to facial skin conformably, enabling the recording exhaled breath-induced temperature variations (Shin et al. 2020). d A highly conductive polymer dry electrode (PWS film) with excellent conductivity, stretchability, and self-adhesiveness, enabling high-quality ECG, EMG, and EEG signal acquisition in diverse conditions (Zhang, L. et al. 2020). e A wearable patch that enables continuous monitoring of the composition and rate of thermoregulatory sweat during periods of rest, which incorporates a fast sweat absorption mechanism and minimizes the time required for sweat accumulation, allowing for real-time measurement (Nyein et al. 2021). f A multifunctional contact lens sensor for wireless ocular diagnostics, which detects glucose in tears and intraocular pressure (Kim et al. 2017). g Interconnected wireless body sensor networks, characterized by energy efficiency and enhanced security, utilize radio surface plasmons propagating on metamaterial textiles (Tian, X. et al. 2019b)
Fig. 2 Wearable technologies for diversified applications. a A tunable, ultrasensitive, nature-inspired, epidermal sensor (TUNES) inspired by a spider’s sensory system with a tenable sensitivity by preset strain, which not only can measure respiration and muscle contraction but also serves as a skin-attachable biomedical sensor (Kim et al. 2023). b An respiratory rate sensor that detects breath patterns in real-time, which is fabricated by depositing PEDOT on a disposable mask (Clevenger et al. 2021). c A sensitive and flexible artificial skin comprising a negative temperature coefficient thermistor that can be attached to facial skin conformably, enabling the recording exhaled breath-induced temperature variations (Shin et al. 2020). d A highly conductive polymer dry electrode (PWS film) with excellent conductivity, stretchability, and self-adhesiveness, enabling high-quality ECG, EMG, and EEG signal acquisition in diverse conditions (Zhang, L. et al. 2020). e A wearable patch that enables continuous monitoring of the composition and rate of thermoregulatory sweat during periods of rest, which incorporates a fast sweat absorption mechanism and minimizes the time required for sweat accumulation, allowing for real-time measurement (Nyein et al. 2021). f A multifunctional contact lens sensor for wireless ocular diagnostics, which detects glucose in tears and intraocular pressure (Kim et al. 2017). g Interconnected wireless body sensor networks, characterized by energy efficiency and enhanced security, utilize radio surface plasmons propagating on metamaterial textiles (Tian, X. et al. 2019b)CC BY · PubMed Central
Fig. 3 Self-powered sensor for in vivo healthcare. a A multifunctional triboelectric active sensor for accurate, continuous, and real-time monitoring of multiple physiological and pathological signs (Ma et al. 2016). b A miniaturized, flexible pressure sensor for intracardiac pressure monitoring, which can be combined with minimally invasive catheters (Liu et al. 2019). c A degradable and absorbable active pressure sensor for blood pressure monitoring and diagnosis of abnormal cardiovascular events (Ouyang et al. 2021). d A self-control system based on shape memory alloy for pressure monitoring and control of voluntary voiding of the neurogenic underactive bladder (Arab Hassani et al. 2018)
Fig. 3 Self-powered sensor for in vivo healthcare. a A multifunctional triboelectric active sensor for accurate, continuous, and real-time monitoring of multiple physiological and pathological signs (Ma et al. 2016). b A miniaturized, flexible pressure sensor for intracardiac pressure monitoring, which can be combined with minimally invasive catheters (Liu et al. 2019). c A degradable and absorbable active pressure sensor for blood pressure monitoring and diagnosis of abnormal cardiovascular events (Ouyang et al. 2021). d A self-control system based on shape memory alloy for pressure monitoring and control of voluntary voiding of the neurogenic underactive bladder (Arab Hassani et al. 2018)CC BY · PubMed Central
Fig. 4 Neural signal sensing based on flexible neural interfaces. a The adaptive, no-invasive general neural ribbon electrode for small peripheral nerve signals recording. i: the neural ribbon electrode (NRE); ii: 3D contact point of nerve electrode; iii: in vivo performance of NRE (Xiang et al. 2016b). b A flexible nerve electrode with a 3D spike structure enables accurate monitoring and decoding of peripheral nerve signals for restoring motion perception (Wang, J. et al. 2018b). c A universal interface based on biphasic dispersed gold nanoparticles that can connect flexible/rigid modules in a plug-and-play way. i - ii: A schematic shows the integration way of flexible and rigid modulus; iii: Applying BIND electrode onto the peroneus longus muscle as an electrode (Jiang et al. 2023). d A soft and stretchable graphene-based biosensing neural interface for the brain and gut. i - ii: NeuroString for chemical sensing in the gut; iii - iv: NeuroString for brain neural signals recording (Li et al. 2022)
Fig. 4 Neural signal sensing based on flexible neural interfaces. a The adaptive, no-invasive general neural ribbon electrode for small peripheral nerve signals recording. i: the neural ribbon electrode (NRE); ii: 3D contact point of nerve electrode; iii: in vivo performance of NRE (Xiang et al. 2016b). b A flexible nerve electrode with a 3D spike structure enables accurate monitoring and decoding of peripheral nerve signals for restoring motion perception (Wang, J. et al. 2018b). c A universal interface based on biphasic dispersed gold nanoparticles that can connect flexible/rigid modules in a plug-and-play way. i - ii: A schematic shows the integration way of flexible and rigid modulus; iii: Applying BIND electrode onto the peroneus longus muscle as an electrode (Jiang et al. 2023). d A soft and stretchable graphene-based biosensing neural interface for the brain and gut. i - ii: NeuroString for chemical sensing in the gut; iii - iv: NeuroString for brain neural signals recording (Li et al. 2022)CC BY · PubMed Central
Fig. 5 Wearable electronics for wound healing, drug delivery, and rehabilitation. a A wearable and programmable bandage that is able to transport essential pharmaceutical compounds and growth factors to the deeper regions of the wound site (Derakhshandeh et al. 2020). b A microneedle patch incorporating PS and O2 propellant, enabling more efficient transdermal delivery of PS and enhancing the effectiveness of photodynamic therapy. (Liu, P. et al. 2022b). c Engineering bacteria-activated thermos-responsive hydrogel to facilitate the healing of diabetic wound (Lu et al. 2021). d A self-sustaining transcutaneous electrical stimulation system utilizing microneedles to enhance the pharmacodynamics of epidermal growth factor (Yang, Yuan et al. 2022d). e A novel sonosensitizer, Au@BTO, incorporating Au nanoparticles into piezoelectric nanocomposite (BTO) with a modified Schottky junction for highly efficient sonodynamic therapy (Wu et al. 2021). f An electrical bandage to facilitate skin wound healing through electrical stimulation (Long et al. 2018). g An assistive and rehabilitative exosuit utilizing soft robotics for individuals recovering from stroke-related walking impairments. (Awad et al. 2020). h A lightweight and soft exosuit with optimized hip flexion assistance to reduce the energy expenditure of walking (Kim et al. 2022)
Fig. 5 Wearable electronics for wound healing, drug delivery, and rehabilitation. a A wearable and programmable bandage that is able to transport essential pharmaceutical compounds and growth factors to the deeper regions of the wound site (Derakhshandeh et al. 2020). b A microneedle patch incorporating PS and O2 propellant, enabling more efficient transdermal delivery of PS and enhancing the effectiveness of photodynamic therapy. (Liu, P. et al. 2022b). c Engineering bacteria-activated thermos-responsive hydrogel to facilitate the healing of diabetic wound (Lu et al. 2021). d A self-sustaining transcutaneous electrical stimulation system utilizing microneedles to enhance the pharmacodynamics of epidermal growth factor (Yang, Yuan et al. 2022d). e A novel sonosensitizer, Au@BTO, incorporating Au nanoparticles into piezoelectric nanocomposite (BTO) with a modified Schottky junction for highly efficient sonodynamic therapy (Wu et al. 2021). f An electrical bandage to facilitate skin wound healing through electrical stimulation (Long et al. 2018). g An assistive and rehabilitative exosuit utilizing soft robotics for individuals recovering from stroke-related walking impairments. (Awad et al. 2020). h A lightweight and soft exosuit with optimized hip flexion assistance to reduce the energy expenditure of walking (Kim et al. 2022)CC BY · PubMed Central
Fig. 6 Optical volatile organic compound (VOC) gas identification for healthcare diagnoses. a VOC components in breath for disease diagnosis (Wilson 2018). b VOC gas identification using sensors based on the surface-enhanced infrared absorption (SEIRA) effect (Hu et al. 2019). i: Schematic representation. ii-iv: Identification of different nitrogen oxides. c VOC gas detection using sensors based on surface-enhanced Raman spectroscopy (SERS). i: Concept of the SERS platform. ii: SEM image of the SERS platform. iii: Demonstration of the detection of 5 VOC gases. iv: Selectivity of the SERS platform. v: PCA of a set of simulated healthy and lung cancer breath samples (Qiao et al. 2018)
Fig. 6 Optical volatile organic compound (VOC) gas identification for healthcare diagnoses. a VOC components in breath for disease diagnosis (Wilson 2018). b VOC gas identification using sensors based on the surface-enhanced infrared absorption (SEIRA) effect (Hu et al. 2019). i: Schematic representation. ii-iv: Identification of different nitrogen oxides. c VOC gas detection using sensors based on surface-enhanced Raman spectroscopy (SERS). i: Concept of the SERS platform. ii: SEM image of the SERS platform. iii: Demonstration of the detection of 5 VOC gases. iv: Selectivity of the SERS platform. v: PCA of a set of simulated healthy and lung cancer breath samples (Qiao et al. 2018)CC BY · PubMed Central
Fig. 7 Electric methodology for VOC gas detection. a VOC gas detection using acoustic resonators based on the gravimetric mechanism (Lu et al. 2015). i: Schematic of the FBAR sensor array functionalized with four supramolecular monolayers. ii: Schematic of the device section. iii: SEM image of the device. iv: Schematic diagram of VOCs adsorption. v: Real-time responses of the FBAR sensor with exposure to chloroform gas. vi: Adsorption isotherms of chloroform. b VOC gas detection using semiconducting metal oxide (Li et al. 2017). i: A Reaction mechanism of the sensor for HCHO detection. ii: SEM images of as-synthesized SnO2 microspheres. iii: Dynamic response-recovery curve of the SnO2 microspheres gas sensor. c Machine learning-enabled graphene electronic nose for VOC gas detection (Capman et al. 2022). i: Schematic of the ML-enabled sensor system. ii: PCA score plots showing the projection of the measured responses onto principal components 1 and 2. iii: Confusion matrix
Fig. 7 Electric methodology for VOC gas detection. a VOC gas detection using acoustic resonators based on the gravimetric mechanism (Lu et al. 2015). i: Schematic of the FBAR sensor array functionalized with four supramolecular monolayers. ii: Schematic of the device section. iii: SEM image of the device. iv: Schematic diagram of VOCs adsorption. v: Real-time responses of the FBAR sensor with exposure to chloroform gas. vi: Adsorption isotherms of chloroform. b VOC gas detection using semiconducting metal oxide (Li et al. 2017). i: A Reaction mechanism of the sensor for HCHO detection. ii: SEM images of as-synthesized SnO2 microspheres. iii: Dynamic response-recovery curve of the SnO2 microspheres gas sensor. c Machine learning-enabled graphene electronic nose for VOC gas detection (Capman et al. 2022). i: Schematic of the ML-enabled sensor system. ii: PCA score plots showing the projection of the measured responses onto principal components 1 and 2. iii: Confusion matrixCC BY · PubMed Central
Fig. 8 Artificial intelligence-enhanced sensor design and VOC detection. a Machine learning-enabled forward design of sensors (Li, D. et al. 2021b). i: 3D view of the sensor. ii: Design process. b Inverse design of sensors using a semi-supervised deep learning algorithm (Ma et al. 2019). i: A schematic of inverse design. ii: The desired spectra (upper panel), the results of inverse design (lower panel). Insets are the design pattern through algorithms. iii: Visualization of the latent space. c Machine learning-enabled VOC detection (Ren et al. 2022). i: A diagram illustrating the VOC sensor. ii: The measured spectra of analytes, show spectral overlapping, which is difficult to distinguish clearly with the classic data processing methods. iii: The measured raw spectral data. iv: Data preprocessing using PCA. v: The weight of scores of each spectrum in 3D space. vi: The confusion map for analyte classification results
Fig. 8 Artificial intelligence-enhanced sensor design and VOC detection. a Machine learning-enabled forward design of sensors (Li, D. et al. 2021b). i: 3D view of the sensor. ii: Design process. b Inverse design of sensors using a semi-supervised deep learning algorithm (Ma et al. 2019). i: A schematic of inverse design. ii: The desired spectra (upper panel), the results of inverse design (lower panel). Insets are the design pattern through algorithms. iii: Visualization of the latent space. c Machine learning-enabled VOC detection (Ren et al. 2022). i: A diagram illustrating the VOC sensor. ii: The measured spectra of analytes, show spectral overlapping, which is difficult to distinguish clearly with the classic data processing methods. iii: The measured raw spectral data. iv: Data preprocessing using PCA. v: The weight of scores of each spectrum in 3D space. vi: The confusion map for analyte classification resultsCC BY · PubMed Central
Fig. 9 Advanced AI-enhanced wearable glove sensors. a A scalable tactile glove (STAG) consists of a sensing sleeve with 584 piezoresistive sensors (Sundaram et al. 2019). b A flexible quadruple tactile sensor for a robot hand to perceive grasped objects (Li et al, 2020). c A TENG strain sensor based on a unique yarn structure for the smart glove application (Zhou, Z. et al. 2020b). d A low-cost, self-powered, and intuitive glove-based HMI combining superhydrophobic triboelectric textile sensors (Wen, F. et al. 2020a, 2020b, 2020c). e A sign language recognition and communication system based on TENG gloves (Wen, F. et al. 2021)
Fig. 9 Advanced AI-enhanced wearable glove sensors. a A scalable tactile glove (STAG) consists of a sensing sleeve with 584 piezoresistive sensors (Sundaram et al. 2019). b A flexible quadruple tactile sensor for a robot hand to perceive grasped objects (Li et al, 2020). c A TENG strain sensor based on a unique yarn structure for the smart glove application (Zhou, Z. et al. 2020b). d A low-cost, self-powered, and intuitive glove-based HMI combining superhydrophobic triboelectric textile sensors (Wen, F. et al. 2020a, 2020b, 2020c). e A sign language recognition and communication system based on TENG gloves (Wen, F. et al. 2021)CC BY · PubMed Central
Fig. 10 Multimodal sensors and ML-base data fusion. a Bioinspired data fusion architecture by integrating visual data with somatosensory data from skin-like stretchable strain sensors (Wang, M. et al. 2020a, 2020b, 2020c). b HSVM algorithm for radar and pressure sensors (Liang et al. 2019). c A mole-inspired olfactory-tactile-associated ML architecture (Liu, M. et al. 2022c). d A multimodal noncontact HMI by combining a MEMS humidity sensor and a triboelectric sensor (Le et al. 2022). e A soft robotic perception system that integrates an ultrasonic sensor with flexible triboelectric sensors (Shi et al. 2023)
Fig. 10 Multimodal sensors and ML-base data fusion. a Bioinspired data fusion architecture by integrating visual data with somatosensory data from skin-like stretchable strain sensors (Wang, M. et al. 2020a, 2020b, 2020c). b HSVM algorithm for radar and pressure sensors (Liang et al. 2019). c A mole-inspired olfactory-tactile-associated ML architecture (Liu, M. et al. 2022c). d A multimodal noncontact HMI by combining a MEMS humidity sensor and a triboelectric sensor (Le et al. 2022). e A soft robotic perception system that integrates an ultrasonic sensor with flexible triboelectric sensors (Shi et al. 2023)CC BY · PubMed Central
Fig. 11 AI-enhanced self-sustainable system for Artificial Intelligence of Things (AIoT) applications. a A low-cost triboelectric sock equipped with the function of energy harvesting and gait sensing (Zhang, Z. et al., 2020b). b A deep learning-enabled smart mat capable of position/activity sensing and individual recognition (Shi, Q. et al. 2020b). c A self-powered piezoelectric AIoT node for smart mining, factory automation, transportation, and smart city applications (Huang et al. 2023). d A multifunctional walking stick for the care of the elderly (Guo, X. et al. 2021b)
Fig. 11 AI-enhanced self-sustainable system for Artificial Intelligence of Things (AIoT) applications. a A low-cost triboelectric sock equipped with the function of energy harvesting and gait sensing (Zhang, Z. et al., 2020b). b A deep learning-enabled smart mat capable of position/activity sensing and individual recognition (Shi, Q. et al. 2020b). c A self-powered piezoelectric AIoT node for smart mining, factory automation, transportation, and smart city applications (Huang et al. 2023). d A multifunctional walking stick for the care of the elderly (Guo, X. et al. 2021b)CC BY · PubMed Central
Fig. 12 An overview of technology evolution from discrete passive sensors to comprehensive and capable AIoT-assisted self-sustainable systems for diversified healthcare and biomedicine applications (Clevenger et al. 2021; Guo, X. et al. 2021b; He et al. 2019; Shi, Qiongfeng et al. 2020b; Shin et al. 2020; Wen, Feng et al. 2020b; Wen, Feng et al. 2020c; Wen, Feng et al. 2021; Zhang, Z. et al. 2020; Zhu et al. 2022)
Fig. 12 An overview of technology evolution from discrete passive sensors to comprehensive and capable AIoT-assisted self-sustainable systems for diversified healthcare and biomedicine applications (Clevenger et al. 2021; Guo, X. et al. 2021b; He et al. 2019; Shi, Qiongfeng et al. 2020b; Shin et al. 2020; Wen, Feng et al. 2020b; Wen, Feng et al. 2020c; Wen, Feng et al. 2021; Zhang, Z. et al. 2020; Zhu et al. 2022)CC BY · PubMed Central

Verification

Claims the paper makes

209 Not checked yet · 16 Own interpretation · 4 Supported · 2 No basis given · 1 Partly supported · 1 Couldn’t confirm · 1 Sources not found · accuracy not yet measured

Verify all 283 references — free account

Show all 141 claims

  • It may state two separate claims as one. 75
  • The quote only partly states this claim. 3
  • Probably not a substantial claim. 20
93 of 93
  • The paper relies on this without support.

    Encryption, identity authentication, and other technologies ensure the security of health data and the privacy of patients.

    “Furthermore, by adopting encryption, identity authentication, and other technologies, the security of health data and the privacy of patients also get ensured.”
  • The paper relies on this without support.

    Implantable sensors function inside the body and perform more directly healthy states than wearable sensors.

    “implantable sensors function inside body perform more directly healthy states.”
  • The paper relies on this without support.

    Tears and saliva offer advantages over sweat for noninvasive health monitoring, including short accumulation time and sufficient volume without additional extraction methods.

    “Tears and saliva offer several advantages over sweat when it comes to noninvasive health monitoring. These bodily fluids have a short accumulation time and provide sufficient volume, eliminating the need for additional extraction methods.”
  • The paper relies on this without support.

    Contact lenses are a viable substrate for tear sensors due to their biocompatibility and compliance.

    “Contact lenses have garnered significant attention as a viable substrate for tear sensors due to their biocompatibility and compliance.”
  • The paper relies on this without support.

    Wireless connectivity between contact lens-based tear sensors and measuring equipment is essential to address the potential risk of inflammation caused by wires in contact with the eyeballs.

    “However, to address the potential risk of inflammation caused by wires in contact with the eyeballs, it is essential to establish wireless connectivity between contact lens-based tear sensors and the measuring equipment.”
  • The paper relies on this without support.

    Wireless interconnection approaches are crucial to create a network of discrete wearable devices, enabling seamless communication and functionality while preserving usability and user comfort.

    “Therefore, wireless interconnection approaches are crucial to create a network of discrete wearable devices, enabling seamless communication and functionality while preserving usability and user comfort.”
  • The paper relies on this without support.

    TENG-based SIBE stands out in vivo energy harvesting, cardiovascular monitoring, cardiac pacing, muscle/nerve electrical stimulation, tissue regeneration, and drug delivery.

    “After that with the advantages of lightweight, low cost, and high output energy density, TENG-based SIBE stands out in vivo energy harvesting, cardiovascular monitoring, cardiac pacing, muscle/nerve electrical stimulation, tissue regeneration, and drug delivery.”
  • The paper relies on this without support.

    The mismatch between hard and hydrophobic neural interfaces and soft and wet nervous tissue is the most important cause of immune rejection and nerve electrode failure.

    “The mismatch between hard and hydrophobic NIs and the soft and wet nervous tissue is the most important cause of immune rejection and nerve electrode failure.”
  • The paper relies on this without support.

    Internal signals of nerve fiber bundles contain more conduction and response related to the recovery of limb movement and sensory function than surface potential signals.

    “Compared to the surface potential signals, the internal signals of nerve fiber bundles contain more conduction and response related to the recovery of limb movement and sensory function.”
  • The paper relies on this without support.

    The detection performance of infrared spectroscopy for VOCs is limited due to the low molecular absorption cross-section (10-20 cm2 per molecule in the mid-infrared).

    “However, the detection performance of this method is limited due to the low molecular absorption cross-section (10-20 cm2 per molecule in the mid-infrared).”
  • The paper relies on this without support.

    Monitoring human health status necessitates the coordinated operation of multiple functional devices, imposing new requirements for system integration and information processing.

    “Considering the human body as a complex system, the monitoring of its health status necessitates the coordinated operation of multiple functional devices, imposing new requirements for system integration and information processing.”
  • The paper relies on this without support.

    Currently available COVID-19 diagnostic methods, such as RT-PCR, serological tests, or chest computed tomography scans, have limitations such as low sensitivity and time-consuming procedures.

    “The currently available COVID-19 diagnostic methods, such as RT-PCR, serological tests, or chest computed tomography scans, have their limitations, such as low sensitivity and time-consuming procedures.”
  • The paper relies on this without support.

    Current noncontact human-machine interfaces grapple with challenges including excessive power consumption, complicated signal processing circuits, and an absence of support for multidimensional interaction.

    “Current noncontact HMIs grapple with challenges including excessive power consumption, complicated signal processing circuits, and an absence of support for multidimensional interaction.”
  • The paper relies on this without support.

    As technological advancements in sensors and the number of gases continue to increase, data volume will inevitably rise.

    “As technological advancements in sensors and the number of gases continue to increase, it is foreseeable that data volume will inevitably rise.”
  • The paper relies on this without support.

    Each person's walking gait patterns are unique.

    “Since each person's walking gait patterns are unique, distinctive output voltage patterns are produced when a person walks on the triboelectric DLES-mat array.”
  • The paper relies on this without support.

    The global elderly population and those with mobility impairments has already surpassed one billion and continues to rise.

    “In response to the needs of the global elderly population and those with mobility impairments - a demographic that has already surpassed one billion and continues to rise - a multifunctional walking stick is proposed, as depicted in Fig. 11d (Guo, X. et al. 2021b).”
16 of 16

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 209 references

Research works printed but not linked: 6

  1. Chao S, Ouyang H, Jiang D, Fan Y, Li Z. Triboelectric nanogenerator based on degradable materials. EcoMat. 2020;3: e12072.
  2. Mahmood L, Ghommem M, Bahroun Z. Smart Gas Sensors: Materials, Technologies, Practical Applications, and Use of Machine Learning-A Review. J Appl Comput Mechan. 2023;9:775–803.
  3. Ren Z, Dong B, Qiao Q, Liu X, Liu J, Zhou G, Lee C. Subwavelength on-chip light focusing with bigradient all-dielectric metamaterials for dense photonic integration. InfoMat. 2021;4: e12264.
  4. Wen F, Sun Z, He T, Shi Q, Zhu M, Zhang Z, Li L, Zhang T, Lee C. Machine learning glove using self-powered conductive superhydrophobic triboelectric textile for gesture recognition in VR/AR applications. Adv Sci. 2020;7:2000261. · DOI
  5. Zhou F, Chai Y. Near-sensor and in-sensor computing Nat Electron. 2020;3:664–71.
  6. Zhou H, Li D, Hui X, Mu X. Infrared metamaterial for surface-enhanced infrared absorption spectroscopy: pushing the frontier of ultrasensitive on-chip sensing. I J Optomechan. 2021;15:97–119.

Cited by

Sorted by citations

See all 295

Metadata

Authors
Wang, C., He, T., Zhou, H., Zhang, Z., & Lee, C.
Affiliations
National University of Singapore (SG)
Corresponding author
Lee, Chengkuo
Venue
Bioelectronic Medicine
Published
2023-08-02
Volume
9
Issue
1
Pages
17-17
ISSN
2332-8886 (ISSN-L)
OpenAlex
W4385448491
Cited by
295
References
209
Citations by year
2026: 74 · 2025: 142 · 2024: 69 · 2023: 10
FWCI
6.62
Type
journal article
Language
en
Open access
Locations
  • Bioelectronic Medicine (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • Reimagine Research Scheme (A-0009037-02-00, A0009037-03-00, A-0009454-01-00)
  • Ministry of Education of Singapore (A-0009520-01-00)
  • Advanced Research and Technology Innovation Centre, College of Design and Engineering, National University of Singapore (A-0005947-20-00)
Topics
  • Physical Sciences › Engineering › Biomedical Engineering › Advanced Sensor and Energy Harvesting Materials
  • Physical Sciences › Engineering › Biomedical Engineering › Non-Invasive Vital Sign Monitoring
  • Physical Sciences › Computer Science › Information Systems › Internet of Things and AI
Keywords
artificial intelligence, health monitoring sensors, wearable sensors, implantable sensors, volatile organic compound detection, human-machine interaction, Internet of Things, respiration rate monitoring, heart rate monitoring, neurotransmitter monitoring, closed-loop drug delivery

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

A language model drew the claims from the paper on 2026-10-09, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-09 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (gpt-6-sol).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review