Medical Diagnosis Research Articles

Artificial intelligence assisted diagnosis of early tc markers and its application.

Thyroid cancer (TC) is a common endocrine malignancy with an increasing incidence worldwide. Early diagnosis is particularly important for TC patients, because it allows patients to receive treatment as early as possible. Artificial intelligence (AI) provides great advantages for complex healthcare systems by analyzing big data based on machine learning. Nowadays, AI is widely used in the early diagnosis of cancer such as TC. Ultrasound detection and fine needle aspiration biopsy are the main methods for early diagnosis of TC. AI has been widely used in the detection of malignancy in thyroid nodules by ultrasound images, cytopathology images and molecular markers. It shows great potential in auxiliary medical diagnosis. The latest clinical trial has shown that the performance of AI models matches with the diagnostic efficiency of experienced clinicians, and more efficient AI tools will be developed in the future. Therefore, in this review, we summarized the recent advances in the application of AI algorithms in assessing the risk of malignancy in thyroid nodules. The objective of this review was to provide a data base for the clinical use of AI-assisted diagnosis in TC, as well as to provide new ideas for the next generation of AI-assisted diagnosis in TC.

U-shaped relationship found between fibrinogen-to-albumin ratio and systemic inflammation response index in osteoporotic fracture patients.

The relationship between the Systemic Inflammatory Response Index (SIRI) and the Fibrinogen-to-albumin ratio (FAR) has not been extensively investigated. The objective of this study was to determine the independent relationship between FAR and SIRI in people with osteoporotic fractures (OPF). A cross-sectional study was conducted using retrospective data from 3431 hospitalized OPF patients. The exposure variable in this study was the baseline FAR, while the outcome variable was the SIRI. Covariates, including age, gender, BMI, and other clinical and laboratory factors, were adjusted. Cross-correlation analysis and linear regression models were applied. The generalized additive model (GAM) investigated non-linear relationships. Adjusted analysis revealed an independent negative association between FAR and SIRI in OPF patients (β = -0.114, p = 0.00064, 95% CI -0.180, -0.049). A substantial U-shaped association between FAR and SIRI was shown using GAM analysis (p < 0.001). FAR and SIRI indicated a negative association for FAR below 6.344% and a positive correlation for FAR over 6.344%. The results of our study revealed a U-shaped relationship between SIRI and FAR. The lowest conceivable FAR for a bone-loose inflammatory disease might be 6.344%, suggesting that this has particular significance for the medical diagnosis and therapy of persons with OPF. Consequently, the term "inflammatory trough" is proposed. These results offer fresh perspectives on controlling inflammation in individuals with OPF and preventing inflammatory osteoporosis.

Deep Learning Based Cystoscopy Image Enhancement.

Endoscopy image enhancement technology provides doctors with clearer and more detailed images for observation and diagnosis, allowing doctors to assess lesions more accurately. Unlike most other endoscopy images, cystoscopy images face more complex and diverse image degradation due to their underwater imaging characteristics. Among the various causes of image degradation, the blood haze resulting from bladder mucosal bleeding make the background blurry and unclear, severely affecting diagnostic efficiency, even leading to misjudgment. We propose a deep learning-based approach to mitigate the impact of blood haze on cystoscopy images. The approach consists of two parts: a blood haze removal network and a contrast enhancement algorithm. Firstly, we adopt Feature Fusion Attention Network (FFA-Net) and transfer learning in the field of deep learning to remove blood haze from cystoscopy images, and introduce perceptual loss to constrain the network for better visual results. Secondly, we enhance the image contrast by remapping the gray scale of the blood haze-free image and performing weighted fusion of the processed image and the original image. In the blood haze removal stage, the algorithm proposed in this paper achieves an average peak signal-to-noise ratio of 29.44 decibels, which is 15% higher than state-of-the-art traditional methods. The average structural similarity and perceptual image patch similarity reach 0.9269 and 0.1146, respectively, both superior to state-of-the-art traditional methods. Besides, our method is the best in keeping color balance after removing the blood haze. In the image enhancement stage, our algorithm enhances the contrast of vessels and tissues while preserving the original colors, expanding the dynamic range of the image. The deep learning-based cystoscopy images enhancement method is significantly better than other traditional methods in both qualitative and quantitative evaluation. The application of artificial intelligence will provide clearer, higher contrast cystoscopy images for medical diagnosis.

An Innovative Approach on Yao’s Three-Way Decision Model Using Intuitionistic Fuzzy Sets for Medical Diagnosis

In the realm of medical diagnosis, intuitionistic fuzzy data serves as a valuable tool for representing information that is uncertain and imprecise. Nevertheless, decision-making based on this kind of knowledge can be quite challenging due to the inherent vagueness of the data. To address this issue, we employ power aggregation operators, which prove effective in combining several sources of data, such as expert thoughts and patient information. This allows for a more correct diagnosis; a particularly crucial aspect of medical practice where precise and timely diagnoses can significantly impact medication policy and patient results. In our research, we introduce a novel methodology to the three-way decision idea. Initially, we revamp the three-way decision model using rough set theory and incorporate interval-valued classes to handle intuitionistic fuzzy data. Secondly, we explore the use of intuitionistic fuzzy power weighted and intuitionistic fuzzy power weighted geometric aggregation operators to consolidate attribute values within the data system. Furthermore, we present a case study in the medical field to exhibit the validity and efficiency of our offered technique. This innovative method enables us to classify participants into three distinct zones based on their symptoms. The manuscript concludes with a summary of key points provided by the authors.

Intelligent medical detection and diagnosis assisted by deep learning

Intelligent medical detection and diagnosis assisted by deep learning

The 4AT scale for rapid detection of delirium in emergency department triage

The 4AT scale for rapid detection of delirium in emergency department triage

Feedback Loop Failure Modes in Medical Diagnosis: How Biases Can Emerge and Be Reinforced.

Medical diagnosis in practice connects to research through continuous feedback loops: Studies of diagnosed cases shape our understanding of disease, which shapes future diagnostic practice. Without accounting for an imperfect and complex diagnostic process in which some cases are more likely to be diagnosed correctly (or diagnosed at all), the feedback loop can inadvertently exacerbate future diagnostic errors and biases. A feedback loop failure occurs if misleading evidence about disease etiology encourages systematic errors that self-perpetuate, compromising future diagnoses and patient care. This article defines scenarios for feedback loop failure in medical diagnosis. Through simulated cases, we characterize how disease incidence, presentation, and risk factors can be misunderstood when observational data are summarized naive to biases arising from diagnostic error. A fourth simulation extends to a progressive disease. When severe cases of a disease are diagnosed more readily, less severe cases go undiagnosed, increasingly leading to underestimation of the prevalence and heterogeneity of the disease presentation. Observed differences in incidence and symptoms between demographic groups may be driven by differences in risk, presentation, the diagnostic process itself, or a combination of these. We suggested how perceptions about risk factors and representativeness may drive the likelihood of diagnosis. Differing diagnosis rates between patient groups can feed back to increasingly greater diagnostic errors and disparities in the timing of diagnosis and treatment. A feedback loop between past data and future medical practice may seem obviously beneficial. However, under plausible scenarios, poorly implemented feedback loops can degrade care. Direct summaries from observational data based on diagnosed individuals may be misleading, especially concerning those symptoms and risk factors that influence the diagnostic process itself. Current evidence about a disease can (and should) influence the diagnostic process. A feedback loop failure may occur if biased "evidence" encourages diagnostic errors, leading to future errors in the evidence base.When diagnostic accuracy varies for mild versus severe cases or between demographic groups, incorrect conclusions about disease prevalence and presentation will result without specifically accounting for such variability.Use of demographic characteristics in the diagnostic process should be done with careful justification, in particular avoiding potential cognitive biases and overcorrection.

Point-of-care testing: a critical analysis of the market and future trends

Point-of-care testing (POCT) involves conducting diagnostic tests outside the laboratory. These tests are utilized for their quick and reliable results in detecting chronic diseases and acute infections. We examined the historical market value trends of the POCT industry and projected its future growth. POCT devices offer several advantages, such as portability, no specific storage requirements, and simplicity of use. However, issues such as inaccurate results can reduce demand for POCT compared to traditional laboratory testing alternatives. While the benefits of POCT are clear, it’s important to acknowledge the challenges. The accuracy of POCT devices can be compromised due to factors such as user error, environmental conditions, and limitations in technology. Furthermore, the cost-effectiveness of these devices is often a concern, particularly in resource-limited settings. The regulatory landscape for POCT is also complex and varies by region, which can pose challenges for manufacturers and end-users. Improvements in POCT devices’ sensitivity, specificity, cost, and turnaround time for test results could enhance their utility. Enhancements to a POCT device should be considered if they are economically viable and lead to a significant increase in demand. Our financial analysis of the POCT market revealed a positive growth trend. We identified potential areas for growth that could help the industry progress and expand in line with its projected growth in the coming years. The industry could focus on integrating intelligent technologies into POCT devices and collaborating with the innovative technology sector to increase revenue. It could also develop more sensitive and accurate POCT devices for non-communicable diseases. Another potential area of growth is in diseases that require continuous patient monitoring but where conventional clinical testing is time-consuming. Enhancing the POCT devices used in these areas could revolutionize medical diagnosis and potentially save many lives, provided they meet clinical standards.

Complex Pythagorean Normal Interval-Valued Fuzzy Aggregation Operators for Solving Medical Diagnosis Problem

This paper presents a new methodology for solving multiple-attribute decision-making problems (MADMs) using a complex Pythagorean normal interval-valued fuzzy set (CPNIVFS), which is an extended concept of a complex Pythagorean fuzzy set. Four types of different aggregating operations (AOs), including CPNIVF weighted averaging (CPNIVFWA), CPNIVF weighted geometric (CPNIVFWG), generalized CPNIVFWA (CGPNIVFWA), and generalized CPNIVFWG (CGPNIVFWG), are discussed. The scoring function, accuracy function, and operational laws of the CPNIVFS are defined. Algebraic structures, such as associative, distributive, idempotent, bounded, commutativity, and monotonicity properties, are also shown to be satisfied by complex Pythagorean normal interval-valued fuzzy numbers. Furthermore, an algorithm is proposed to solve the MADM problems based on the defined AOs. The proposed approach is then used for a medical diagnosis problem about brain tumors because computer science and machine tool technology are among the most important components of brain tumor research. The five types of brain tumors diagnosed in these patients are gliomas, meningiomas, metastases, embryonal tumors, and ependymomas. Several types of treatments are available, which are often combined as part of an overall treatment plan. Brain tumors can be treated in various ways, including surgery, radiation therapy, chemotherapy, immunotherapy, and clinical trials. Based on the comparisons and options gathered, the most suitable treatment can be chosen. In this regard, it is evident that the value of the integer ⅁\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\Game $$\\end{document} plays a significant role in determining the model. The candidate models under consideration can be validated by comparing them with the previously proposed ones. The proposed technique is compared with the existing method to demonstrate its superiority and validity, and the results conclude that the former is more reliable and effective than the latter. Finally, the criteria are evaluated by expert assessments to determine the most appropriate options.

EHyPRETo: Enhanced Hybrid Pre-Trained and Transfer Learning-based Contextual Relation Classification Model

eHyPRETo: Enhanced Hybrid Pre-Trained and Transfer Learning-based Contextual Relation Classification Model

Improve robustness of machine learning via efficient optimization and conformal prediction

AbstractThe advance of machine learning (ML) systems in real‐world scenarios usually expects safe deployment in high‐stake applications (e.g., medical diagnosis) for critical decision‐making process. To this end, provable robustness of ML is usually required to measure and understand how reliable the deployed ML system is and how trustworthy their predictions can be. Many studies have been done to enhance the robustness in recent years from different angles, such as variance‐regularized robust objective functions and conformal prediction (CP) for uncertainty quantification on testing data. Although these tools provably improve the robustness of ML model, there is still an inevitable gap to integrate them into an end‐to‐end deployment. For example, robust objectives usually require carefully designed optimization algorithms, while CP treats ML models as black boxes. This paper is a brief introduction to our recent research focusing on filling this gap. Specifically, for learning robust objectives, we designed sample‐efficient stochastic optimization algorithms that achieves the optimal (or faster compared to existing algorithms) convergence rates. Moreover, for CP‐based uncertainty quantification, we established a framework to analyze the expected prediction set size (smaller size means more efficiency) of CP methods in both standard and adversarial settings. This paper elaborates the key challenges and our exploration towards efficient algorithms with details of background methods, notions for robustness measure, concepts of algorithmic efficiency, our proposed algorithms and results. All of them further motivate our future research on risk‐aware ML that can be critical for AI–human collaborative systems. The future work mainly targets designing conformal robust objectives and their efficient optimization algorithms.

Fuzzy Soft Set Theory Applications in Medical Diagnosis: A Comprehensive Review and the Roadmap for Future Studies

This paper provides a literature review addressing the use of soft sets in medical diagnosis. Distinguishing itself from the existing literature, the study offers a comprehensive analysis of how fuzzy soft sets can be integrated into diagnostic processes, highlighting a novel fusion of fuzzy and soft sets in medical applications. Any soft set on a countably infinite universe can be regarded as a fuzzy set, recognizing the limitations of traditional diagnostic tools in dealing with vague and incomplete information, our research aims to utilize the flexibility and comprehensiveness of fuzzy soft sets to enhance decision-making accuracy in medical scenarios. The primary objective of this research is to present a thorough and critical analysis of fuzzy soft set theory in medical diagnosis, aiming to establish it as a fundamental approach in the field. By combining all of these results, we can generate a comprehensive picture of the connections between the many theories that account for fuzziness and imprecision, which helps to fill in the blanks left by recent surveys. The review will focus on identifying the main research trends in this field: the primary research topics that soft set theory addresses in medical applications, the community is currently facing and the major theoretical concepts used to study these topics. The primary objective of this review is to assist in the identifying of emerging research directions. Some of these trends are promising and will help shape a new role for soft set theory in the area of medical applications. The fusion of fuzzy and soft sets in medical applications represents a crucial and necessary stage in the research and diagnosis procedures. Key results include the study on development of algorithms and models that outperform traditional methods in accuracy and reliability.

Multi-class identification of tonal contrasts in Chokri using supervised machine learning algorithms

This study examines and explores the effectiveness of various Machine Learning Algorithms (MLAs) in identifying intricate tonal contrasts in Chokri (ISO 639-3), an under-documented and endangered Tibeto-Burman language of the Sino-Tibetan language family spoken in Nagaland, India. Seven different supervised MLAs, viz., [Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Naive Bayes (NB)], and one neural network (NN)-based algorithms [Artificial Neural Network (ANN)] are implemented to explore five-way tonal contrasts in Chokri. Acoustic correlates of tonal contrasts, encompassing fundamental frequency fluctuations, viz., f0 height and f0 direction, are examined. Contrary to the prevailing notion of NN supremacy, this study underscores the impressive accuracy achieved by the RF. Additionally, it reveals that combining f0 height and directionality enhances tonal contrast recognition for female speakers, while f0 directionality alone suffices for male speakers. The findings demonstrate MLAs’ potential to attain accuracy rates of 84–87% for females and 95–97% for males, showcasing their applicability in deciphering the intricate tonal systems of Chokri. The proposed methodology can be extended to predict multi-class problems in diverse fields such as image processing, speech classification, medical diagnosis, computer vision, and social network analysis.

Classification performance assessment for imbalanced multiclass data

The evaluation of diagnostic systems is pivotal for ensuring the deployment of high-quality solutions, especially given the pronounced context-sensitivity of certain systems, particularly in fields such as biomedicine. Of notable importance are predictive models where the target variable can encompass multiple values (multiclass), especially when these classes exhibit substantial frequency disparities (imbalance). In this study, we introduce the Imbalanced Multiclass Classification Performance (IMCP) curve, specifically designed for multiclass datasets (unlike the ROC curve), and characterized by its resilience to class distribution variations (in contrast to accuracy or Fβ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$_\\beta$$\\end{document}-score). Moreover, the IMCP curve facilitates individual performance assessment for each class within the diagnostic system, shedding light on the confidence associated with each prediction—an aspect of particular significance in medical diagnosis. Empirical experiments conducted with real-world data in a multiclass context (involving 35 types of tumors) featuring a high level of imbalance demonstrate that both the IMCP curve and the area under the IMCP curve serve as excellent indicators of classification quality.

Light-Adaptive Human Body Key Point Detection Algorithm Based on Multi-Source Information Fusion

The identification of key points in the human body is vital for sports rehabilitation, medical diagnosis, human–computer interaction, and related fields. Currently, depth cameras provide more precise depth information on these crucial points. However, human motion can lead to variations in the positions of these key points. While the Mediapipe algorithm demonstrates effective anti-shake capabilities for these points, its accuracy can be easily affected by changes in lighting conditions. To address these challenges, this study proposes an illumination-adaptive algorithm for detecting human key points through the fusion of multi-source information. By integrating key point data from the depth camera and Mediapipe, an illumination change model is established to simulate environmental lighting variations. Subsequently, the fitting function of the relationship between lighting conditions and adaptive weights is solved to achieve lighting adaptation for human key point detection. Experimental verification and similarity analysis with benchmark data yielded R2 results of 0.96 and 0.93, and cosine similarity results of 0.92 and 0.90. With a threshold range of 8, the joint accuracy rates for the two rehabilitation actions were found to be 89% and 88%. The experimental results demonstrate the stability of the proposed method in detecting key points in the human body under changing illumination conditions, its anti-shake ability for human movement, and its high detection accuracy. This method shows promise for applications in human–computer interaction, sports rehabilitation, and virtual reality.

Implementasi Sistem Antrian Pasien Berbasis Website Pada Klinik Sehat Tamba Kelurahan Cilangkap

Clinics are health facilities that provide basic medical services, diagnosis, treatment, and care to patients with minor or non-emergency medical conditions. The development of information technology has triggered the need for information systems in the medical field to improve health services. One important factor in increasing patient satisfaction is minimizing waiting time. Long queues can reduce clinic efficiency and affect patient satisfaction. This study aims to implement a website-based patient queue system at the Tamba Sehat Clinic, with the hope of increasing service efficiency and patient satisfaction. In implementing the website queuing system, researchers used qualitative methods to understand the effectiveness of health services and patient experiences. Data was collected through interviews, observations, and literature studies. The implementation of the Website-Based Patient Queuing System at the Tamba Sehat Clinic has had a significant impact. People can now easily get a queue number online via mobile phone or computer, eliminating the need to queue directly at the clinic location. Tamba Sehat Clinic, which was established in January 2023, has seen increased efficiency with this system. Patients can quickly and efficiently get a queue number, ensuring that their time is spent productively. Additionally, adopting this technology helps clinics improve the quality of service to prospective patients, creating a more comfortable and efficient experience for those in need of healthcare services. Thus, the implementation of a website-based patient queue system has brought real benefits to the community and clinics.

Ga2O3 Photon‐Controlled Diode for Sensitive DUV/X‐Ray Detection and High‐Resolution Array Imaging Application

AbstractSensitive high‐energy photon detection from UV to X‐ray and high‐resolution array imaging are critical for medical diagnosis, space exploration, and scientific research. The key challenges for high‐performance photodetector and imaging arrays are the effective material and device design strategies for the miniaturization and integration of the device. Here, photon‐controlled diodes (i.e., the detector has rectifying characteristics only under light irradiation) are proposed for high‐resolution and anti‐crosstalk array imaging applications without integrating the switching element. Based on ultra‐wide bandgap semiconductor Ga2O3, the sensitive DUV/X‐ray photon‐controlled diodes are realized by the design of high‐resistance Ga2O3 film and high‐barrier contact. The device exhibits remarkable detection performance, including high photo‐responsivity (168 A W−1) and specific detectivity (1.45 × 1015 Jones) under DUV illumination, as well as a high sensitivity (1.23 × 105 µC Gyair−1 cm−2) under X‐ray light. Moreover, the low dark current and excellent rectification characteristics are obtained. Furthermore, its potential for high‐density and anti‐crosstalk array imaging applications is verified. These results not only bring forth new insights in the implementation of high‐performance DUV/X‐ray photodetector, but also pave a feasible way to realize high pixel density detector array through the simplified fabrication process for high‐resolution imaging applications.

Boundary sample-based class-weighted semi-supervised learning for malignant tumor classification of medical imaging.

Medical image classification plays a pivotal role within the field of medicine. Existing models predominantly rely on supervised learning methods, which necessitate large volumes of labeled data for effective training. However, acquiring and annotating medical image data is both an expensive and time-consuming endeavor. In contrast, semi-supervised learning methods offer a promising approach by harnessing limited labeled data alongside abundant unlabeled data to enhance the performance of medical image classification. Nonetheless, current methods often encounter confirmation bias due to noise inherent in self-generated pseudo-labels and the presence of boundary samples from different classes. To overcome these challenges, this study introduces a novel framework known as boundary sample-based class-weighted semi-supervised learning (BSCSSL) for medical image classification. Our method aims to alleviate the impact of intra- and inter-class boundary samples derived from unlabeled data. Specifically, we address reliable confidential data and inter-class boundary samples separately through the utilization of an inter-class boundary sample mining module. Additionally, we implement an intra-class boundary sample weighting mechanism to extract class-aware features specific to intra-class boundary samples. Rather than discarding such intra-class boundary samples outright, our approach acknowledges their intrinsic value despite the difficulty associated with accurate classification, as they contribute significantly to model prediction. Experimental results on widely recognized medical image datasets demonstrate the superiority of our proposed BSCSSL method over existing semi-supervised learning approaches. By enhancing the accuracy and robustness of medical image classification, our BSCSSL approach yields considerable implications for advancing medical diagnosis and future research endeavors.

MedKnee: A New Deep Learning-Based Software for Automated Prediction of Radiographic Knee Osteoarthritis

In computer-aided medical diagnosis, deep learning techniques have shown that it is possible to offer performance similar to that of experienced medical specialists in the diagnosis of knee osteoarthritis. In this study, a new deep learning (DL) software, called “MedKnee” is developed to assist physicians in the diagnosis process of knee osteoarthritis according to the Kellgren and Lawrence (KL) score. To accomplish this task, 5000 knee X-ray images obtained from the Osteoarthritis Initiative public dataset (OAI) were divided into train, valid, and test datasets in a ratio of 7:1:2 with a balanced distribution across each KL grade. The pre-trained Xception model is used for transfer learning and then deployed in a Graphical User Interface (GUI) developed with Tkinter and Python. The suggested software was validated on an external public database, Medical Expert, and compared with a rheumatologist’s diagnosis on a local database, with the involvement of a radiologist for arbitration. The MedKnee achieved an accuracy of 95.36% when tested on Medical Expert-I and 94.94% on Medical Expert-II. In the local dataset, the developed tool and the rheumatologist agreed on 23 images out of 30 images (74%). The MedKnee’s satisfactory performance makes it an effective assistant for doctors in the assessment of knee osteoarthritis.

Ternary nano-composite wireless ammonia sensor based on Polyaniline/CuTsPc/AgNPs for food intelligent packaging

The integration of gas sensing unit and low-cost wireless communication equipment enables real-time detection of various environmental gases, which is of great significance for food safety, medical diagnosis and environmental monitoring. In this study, copper phthalocyanine powder (CuTsPc) was prepared by high temperature solid phase melting technology. Ternary ammonia sensors with exceptional sensitivity to ammonia and conductivity were successfully fabricated by growing polyaniline/copper phthalocyanine/silver nanoparticles (PANI/CuTsPc/AgNPs) composites on polyethylene terephthalate films by in-situ polymerization. The morphology and composition of the films were characterized by FTIR, XRD and SEM, respectively. The ammonia sensing performance of the films at room temperature was systematically investigated. It is found that the flexible PANI/CuTsPc/AgNPs gas sensor exhibited rapid response time (61 s), fast recovery time (19 s), low theoretical detection limit (0.234 ppm), high response value (3.6 towards 500 ppm NH3), and excellent stability at room temperature. These remarkable response characteristics can be attributed to the synergistic effect between protonic acid-doped PANI, CuTsPc derivatives with an electron-withdrawing group, and AgNPs possessing both chemical sensitisation and electron sensitisation. Finally, the sensor material was transformed into a label antenna pattern as well as sensor transducer through series and parallel antenna loop access methods to create a wireless sensor system based on near-field communication (NFC). This system can offer real-time sensing and monitoring of changes in food packaging environment by non-contact recognition way, making it highly promising for future applications in intelligent packaging.