Feasibility and Acceptability Evaluation of a Digital Therapeutic Program for Improving Cancer Prevention: A Quasi-experimental Pre-post Interventional Pilot Study.

Previous studies have proved that healthy behaviors hinder the onset and progression of tumors. Digital therapeutics (DTx), playing a pivotal role in facilitating behavioral adjustments through educational interventions, lifestyle support, and symptom monitoring, contribute to the goal of tumor prevention. We aim to optimize the evaluation of the feasibility and acceptability of DTx for cancer prevention. This involves assessing AITI's daily activity rates and user feedback, and comparing changes in behavioral habits and differences in SF-36 before and after the intervention. In a 4-week trial with 57 participants engaging actively, we found both the average daily activity rate and 4-week retention rate at 35 (61.4%). The USE Questionnaire scores (validity, ease of use, acquisition, and satisfaction) ranged from 68.06 to 83.10, indicating AITI's user-friendliness and acceptability. Furthermore, positive habit changes were noted among participants in exercise and diet (p < 0.0001), suggesting the effectiveness of the DTx approach in modifying behavioral habits related to physical activity and nutrition. This pilot study underscores the potential of DTx in advancing cancer prevention. However, larger and longer studies are needed to comprehensively assess its impact.

Multi-target meridians classification based on the topological structure of anti-cancer phytochemicals using deep learning.

ETHNOPHARMACOLOGICAL RELEVANCE: Traditional Chinese medicine (TCM) meridian is the key theoretical guidance of prescription against tumor in clinical practice. However, there is no scientific and systematic verification of therapeutic action of herbs under meridians context. Several studies have determined the Chinese herbal medicine (CHM) phytochemicals for intrinsic attribute or meridians classification based on artificial intelligence (AI) tools. However, it is challenging to represent the complex molecular structures with large heterogeneity through the current technologies. In addition, the multiple correspondence between herbs and meridians has not been paid much attention. AIM OF THE STUDY: We aim to develop an AI framework to classify multi-target meridians through the topological structure of phytochemicals. MATERIALS AND METHODS: A total of 354 anti-cancer herbs, their corresponding TCM meridians and 5471 ingredient compounds were collected from public databases of CancerHSP, ETCM, and Hit 2.0. The statistical analysis of herbal and compound datasets, clustering analysis of the associated cancers, and correlational analysis of meridian tropism were preliminary conducted. Then a deep learning (DL) hybrid model named GRMC consisting of graph convolutional network (GCN) and recurrent neural network (RNN) was employed to generate the meridian multi-label sequences based on molecular graph. RESULTS: The curing herbs against tumors have tight relationships to lung, liver, stomach, and spleen meridians. These herbs behave different properties in curing certain cancer. Certain cancer types have co-occurrence such as ovarian, bladder and cervical cancer. Compounds have multitarget meridians with characteristics of higher-order correlations. Compared with the other state-of-the-art algorithms on the datasets and previous methods dealing with conventional fixed fingerprints of herbal compounds, the proposed GRMC has superior overall performance on testing dataset with the one error of 0.183, hamming loss of 0.112, mean averaged accuracy (MAA) of 0.855, mean averaged precision (MAP) of 0.891, mean averaged recall (MAR) of 0.812, and mean averaged F1 score (MAF) of 0.849. CONCLUSIONS: The proposed method can predict multi-targeted meridians through neural graph features in herbal compounds and outperforms several comparison methods. It could provide a basis for understanding the molecular scientific evidence of TCM meridians.

Advances in the Application of Traditional Chinese Medicine Using Artificial Intelligence: A Review.

Traditional Chinese medicine (TCM), as one of the crystallizations of Chinese wisdom, emphasizes the balance of Yin and Yang to keep the body healthy. Under the theoretical guidance of a holistic view, the diagnostic process in TCM has characteristics of subjectivity, fuzziness, and complexity. Therefore, realizing standardization and achieving objective quantitative analysis are the bottlenecks of the development of TCM. The emergence of artificial intelligence (AI) technology has brought unprecedented challenges and opportunities to traditional medicine, which is expected to provide objective measurements and improve the clinical efficacy. However, the combination of TCM and AI is still in its infancy and currently faces many challenges. Therefore, this review provides a comprehensive discussion of the existing advances, problems, and prospects of the applications of AI technologies in TCM with the hope of promoting a better understanding of the TCM modernization and intellectualization.

An intelligent intestinal bleeding diagnosis and treatment capsule system based on color recognition.

To our best knowledge, there are no non-invasive and painless means for the diagnosis and treatment of intestinal bleeding as of now, especially the segment of intestine that cannot be reached by endoscopy. We proposed an intelligent intestinal bleeding diagnosis and treatment capsule (IBDTC) system for the first time to diagnose and treat intestinal bleeding with low power consumption, estimated to be about 2.16mW. A hue-saturation-light (HSL) color space method was applied to diagnose bleeding according to H (hue) values of the film dyed by blood. A MEMS-based micro-igniter works as the critical component of the micro-thruster that houses the propellant (74.6% potassium nitrate, 11.9% sulfur, 13.5% charcoal) and the detonating agent (dinitrodiazophenol), to help release drug. Bleeding detection and ignition tests were performed to justify its feasibility and reliability. Results demonstrated that the bleeding diagnosis module of the IBDTC can effectively detect bleeding and the micro-igniter can successfully ignite the propellant. Owing to its simplicity and intelligence, the IBDTC system will pave a way for future accurate treatment of small intestinal bleeding with no injury, no pain, no complicated supporting equipment, no need for in vitro operation and positioning.

Multi-label classification of fundus images with graph convolutional network and LightGBM.

Early detection and treatment of retinal disorders are critical for avoiding irreversible visual impairment. Given that patients in the clinical setting may have various types of retinal illness, the development of multi-label fundus disease detection models capable of screening for multiple diseases is more in line with clinical needs. This article presented a composite model based on hybrid graph convolution for patient-level multi-label fundus illness identification. The composite model comprised a backbone module, a hybrid graph convolution module, and a classifier module. This article established the relationship between labels via graph convolution and then employed a self-attention mechanism to design a hybrid graph convolution structure. The backbone module extracted features using EfficientNet-B4, whereas the classifier module output multi-label using LightGBM. Additionally, this work investigated the input pattern of binocular images and the influence of label correlation on the model's identification performance. The proposed model MCGL-Net outperformed all other state-of-the-art methods on the publicly available ODIR dataset, with F1 reaching 91.60% on the test set. Ablation experiments were also performed in this paper. Experiments showed that the idea of hybrid graph convolutional structure and composite model designed in this paper promotes the model performance under any backbone CNN. The adoption of hybrid graph convolution can increase the F1 by 2.39% in trials using EfficientNet-B4 as the backbone. The composite model had a higher F1 index by 5.42% than the single EfficientNet-B4 model.

Recognizing lung cancer and stages using a self-developed electronic nose system.

Exhaled breath contains thousands of gaseous volatile organic compounds (VOCs) that could be used as non-invasive biomarkers of lung cancer. Breath-based lung cancer screening has attracted wide attention on account of its convenience, low cost and easy popularization. In this paper, the research of lung cancer detection and staging is conducted by the self-developed electronic nose (e-nose) system. In order to investigate the performance of the device in distinguishing lung cancer patients from healthy controls, two feature extraction methods and two different classification models were adopted. Among all the models, kernel principal component analysis (KPCA) combined with extreme gradient boosting (XGBoost) achieved the best results among 235 breath samples. The accuracy, sensitivity and specificity of e-nose system were 93.59%, 95.60% and 91.09%, respectively. Meanwhile, the device could innovatively classify stages of 90 lung cancer patients (i.e., 44 stage III and 46 stage IV). Experimental results indicated that the recognition accuracy of lung cancer stages was more than 80%. Further experiments of this research also showed that the combination of sensor array and pattern recognition algorithms could identify and distinguish the expiratory characteristics of lung cancer, smoking and other respiratory diseases.

Detection of lung cancer with electronic nose using a novel ensemble learning framework.

Breath analysis based on electronic nose (e-nose) is a promising new technology for the detection of lung cancer that is non-invasive, simple to operate and cost-effective. Lung cancer screening by e-nose relies on predictive models established using machine learning methods. However, using only a single machine learning method to detect lung cancer has some disadvantages, including low detection accuracy and high false negative rate. To address these problems, groups of individual learning models with excellent performance were selected from classic models, including support vector machine, decision tree, random forest, logistic regression andK-nearest neighbor regression, to build an ensemble learning framework (PCA-SVE). The output result of the PCA-SVE framework was obtained by voting. To test this approach, we analyzed 214 breath samples measured by e-nose with 11 gas sensors of four types using the proposed PCA-SVE framework. Experimental results indicated that the accuracy, sensitivity, and specificity of the proposed framework were 95.75%, 94.78%, and 96.96%, respectively. This framework overcomes the disadvantages of a single model, thereby providing an improved, practical alternative for exhaled breath analysis by e-nose.

Hybrid Network with Attention Mechanism for Detection and Location of Myocardial Infarction Based on 12-Lead Electrocardiogram Signals.

The electrocardiogram (ECG) is a non-invasive, inexpensive, and effective tool for myocardial infarction (MI) diagnosis. Conventional detection algorithms require solid domain expertise and rely heavily on handcrafted features. Although previous works have studied deep learning methods for extracting features, these methods still neglect the relationships between different leads and the temporal characteristics of ECG signals. To handle the issues, a novel multi-lead attention (MLA) mechanism integrated with convolutional neural network (CNN) and bidirectional gated recurrent unit (BiGRU) framework (MLA-CNN-BiGRU) is therefore proposed to detect and locate MI via 12-lead ECG records. Specifically, the MLA mechanism automatically measures and assigns the weights to different leads according to their contribution. The two-dimensional CNN module exploits the interrelated characteristics between leads and extracts discriminative spatial features. Moreover, the BiGRU module extracts essential temporal features inside each lead. The spatial and temporal features from these two modules are fused together as global features for classification. In experiments, MI location and detection were performed under both intra-patient scheme and inter-patient scheme to test the robustness of the proposed framework. Experimental results indicate that our intelligent framework achieved satisfactory performance and demonstrated vital clinical significance.

Design of a Real-time Self-adjusting Calibration Algorithm to Improve the Accuracy of Continuous Blood Glucose Monitoring.

The aim of this study is to establish a real-time self-adjusting calibration algorithm to compensate for signal drift and sensitivity attenuation of subcutaneous implantable glucose sensors. A real-time self-adjusting in vivo calibration method was designed based on the one-point calibration model. The current signal was compensated in real-time and the sensitivity was calibrated regularly. The least squares method was used to fit the initial parameters of the model, and then, the in vivo monitored current data was calibrated. Comparing with the mean absolute relative difference (MARD) of the blood glucose concentration by the traditional one-point calibration model (22.85 ± 5.76%), the MARD of the blood glucose concentration calibrated by the real-time self-adjusting in vivo calibration method was 6.28 ± 2.31%. The accuracy of the dynamic blood glucose monitoring was effectively improved. This calibration algorithm could compensate the signal drift in real time and correct sensitivity regularly to improve the accuracy of dynamic glucose monitoring, thus significantly enhancing diabetic self-management.

Electret filter collects more exhaled albumin than glass condenser: A method comparison based on human study.

In recent years, noninvasive diagnosis based on biomarkers in exhaled breath has been extensively studied. The procedure of biomarker collection is a key step. However, the traditional condenser method has low efficacy in collecting nonvolatile compounds especially the protein biomarkers in breath. To solve this deficiency, here we propose an electret filter method.Exhaled breath of 6 volunteers was collected with a glass condenser and an electret filter. The amount of albumin was analyzed. Furthermore, the difference of exhaled albumin between smokers and nonsmokers was evaluated.The electret filter method collected more albumin than the glass condenser method at the same breath volume level (P < .01). Smokers exhaling more albumin than nonsmokers were also observed (P < .01).The electret filter is capable of collecting proteins more effectively than the condenser method. In addition, smokers tend to exhale more albumin than nonsmokers.

[Development of Portable Anesthesia Video Laryngoscope Based on ARM].

In the process of tracheal intubation, the anesthesia video laryngoscope is used to lift up the patient's epiglottis to expose the glottis, and thus guiding the medical staff to perform anesthesia intubation accurately. This paper describes the method and significance of video laryngoscope in the process of guiding anesthesia intubation, introduces the overall structure and function of portable anesthesia video laryngoscope, the design is mainly focused on image acquisition module, core board circuit, video decoding circuit, lithium battery charging circuit and external storage circuit, at last briefly introduces work process of the video laryngoscope.

[Computer-aided Diagnosis and New Electronic Stethoscope].

Auscultation is an important method in early-diagnosis of cardiovascular disease and respiratory system disease. This paper presents a computer-aided diagnosis of new electronic auscultation system. It has developed an electronic stethoscope based on condenser microphone and the relevant intelligent analysis software. It has implemented many functions that combined with Bluetooth, OLED, SD card storage technologies, such as real-time heart and lung sounds auscultation in three modes, recording and playback, auscultation volume control, wireless transmission. The intelligent analysis software based on PC computer utilizes C# programming language and adopts SQL Server as the background database. It has realized play and waveform display of the auscultation sound. By calculating the heart rate, extracting the characteristic parameters of T1, T2, T12, T11, it can analyze whether the heart sound is normal, and then generate diagnosis report. Finally the auscultation sound and diagnosis report can be sent to mailbox of other doctors, which can carry out remote diagnosis. The whole system has features of fully function, high portability, good user experience, and it is beneficial to promote the use of electronic stethoscope in the hospital, at the same time, the system can also be applied to auscultate teaching and other occasions.

[Research on Exact Location Algorithm of Pupil Center Based on Ellipse Fitting].

In order to realize the requirement of precise eye tracking in clinical, a pupil center location algorithm based on the least square method is proposed. First, the eye image was captured by the camera under the infrared light, and then the two-valued image was obtained after preprocessing. Use the number of pixels that form the outline which was Extracting from the two-valued image to carry out the rough filtration of the pupil. The ellipse curve was fitting by the randomly select 6 pixels on the filtered contours, and then calculated the variance of distance between the center and the edge of the ellipse. The ellipse center is ellipse center, where the variance of the distance is Minimum. The algorithm has advantage of accurate identification the pupil center when there is white spot interference and squint. Experiments show that the pupil center can be located quickly and real-timely by this algorithm.

[Structure design of a new video laryngoscope image sensor].

In order to overcome the influence of stray light and impurity on the image of video laryngoscope, we designed an optical structure by using Trace Pro, a simulation software, to imitate optical path status. Images are captured by CMOS sensor which has the size of 4.5 mm×18 mm and the pixel size is 1.75 µm×1.75 µm. The sensor is placed in the elbow of the laryngoscope, and the elbow has the size of 9 mm×10 mm. As a result, the video laryngoscope could meet the requirements, including wide viewing angle(80°), short focal length(2.8 mm), long working distance(10 cm), and least impurity. In the test, the image was clear and there was no facula or impurity in the condition of required illumination,and thus stray light and image impurity were eliminated and the image quality was improved.

[Design of portable blood pressure depressor based on slow breathing training].

Clinical studies had demonstrated that slow breathing could lower blood pressure significantly. Based on this knowledge, a portable blood pressure depressor was designed in this study. The device used a miniature variable distance capacitive sensor to collect respiratory signal, an STM32 as the main control chip, a WT588D voice chip to generate voice and music and guide slow breathing, and a 3.5-inch color screen to display breathing state and provide guidance. For patients with difficulty in adapting themselves to the slow breathing training, an intelligent guiding breathing algorithm based on feedback regulation mechanism was proposed to train patients to breathe slowly. Ten volunteers with hypertension were recruited and then trained to breathe slowly, accumulating up to 100 times using this device. The results showed that breath rate of the volunteers decreased from 15.16±0.92 times per minute to 9.40±0.29 times per minute, and meanwhile, time length of breath rate less than 8 times per minute in the proportion of total treatment time increased from 0.079±0.017 to 0.392±0.019 as the training times increased. In a conclusion, the proposed blood pressure depressor worked effectively in guiding slow breathing training.

[Design and implementation of real-time continuous glucose monitoring instrument].

Real-time continuous glucose monitoring can help diabetics to control blood sugar levels within the normal range. However, in the process of practical monitoring, the output of real-time continuous glucose monitoring system is susceptible to glucose sensor and environment noise, which will influence the measurement accuracy of the system. Aiming at this problem, a dual-calibration algorithm for the moving-window double-layer filtering algorithm combined with real-time self-compensation calibration algorithm is proposed in this paper, which can realize the signal drift compensation for current data. And a real-time continuous glucose monitoring instrument based on this study was designed. This real-time continuous glucose monitoring instrument consisted of an adjustable excitation voltage module, a current-voltage converter module, a microprocessor and a wireless transceiver module. For portability, the size of the device was only 40 mm × 30 mm × 5 mm and its weight was only 30 g. In addition, a communication command code algorithm was designed to ensure the security and integrity of data transmission in this study. Results of experiments in vitro showed that current detection of the device worked effectively. A 5-hour monitoring of blood glucose level in vivo showed that the device could continuously monitor blood glucose in real time. The relative error of monitoring results of the designed device ranged from 2.22% to 7.17% when comparing to a portable blood meter.

A Smart Capsule System for Automated Detection of Intestinal Bleeding Using HSL Color Recognition.

There are no ideal means for the diagnosis of intestinal bleeding diseases as of now, particularly in the small intestine. This study investigated an intelligent intestinal bleeding detection capsule system based on color recognition. After the capsule is swallowed, the bleeding detection module (containing a color-sensitive adsorptive film that changes color when absorbing intestinal juice,) is used to identify intestinal bleeding features. A hue-saturation-light color space method can be applied to detect bleeding according to the range of H and S values of the film color. Once bleeding features are recognized, a wireless transmission module is activated immediately to send an alarm signal to the outside; an in vitro module receives the signal and sends an alarm. The average power consumption of the entire capsule system is estimated to be about 2.1mW. Owing to its simplicity, reliability, and effectiveness, this system represents a new approach to the clinical diagnosis of intestinal bleeding diseases.

Collecting Protein Biomarkers in Breath Using Electret Filters: A Preliminary Method on New Technical Model and Human Study.

Biomarkers in exhaled breath are useful for respiratory disease diagnosis in human volunteers. Conventional methods that collect non-volatile biomarkers, however, necessitate an extensive dilution and sanitation processes that lowers collection efficiencies and convenience of use. Electret filter emerged in recent decade to collect virus biomarkers in exhaled breath given its simplicity and effectiveness. To investigate the capability of electret filters to collect protein biomarkers, a model that consists of an atomizer that produces protein aerosol and an electret filter that collects albumin and carcinoembryonic antigen-a typical biomarker in lung cancer development- from the atomizer is developed. A device using electret filter as the collecting medium is designed to collect human albumin from exhaled breath of 6 volunteers. Comparison of the collecting ability between the electret filter method and other 2 reported methods is finally performed based on the amounts of albumin collected from human exhaled breath. In conclusion, a decreasing collection efficiency ranging from 17.6% to 2.3% for atomized albumin aerosol and 42% to 12.5% for atomized carcinoembryonic antigen particles is found; moreover, an optimum volume of sampling human exhaled breath ranging from 100 L to 200 L is also observed; finally, the self-designed collecting device shows a significantly better performance in collecting albumin from human exhaled breath than the exhaled breath condensate method (p<0.05) but is not significantly more effective than reported 3-stage impactor method (p>0.05). In summary, electret filters are potential in collecting non-volatile biomarkers in human exhaled breath not only because it was simpler, cheaper and easier to use than traditional methods but also for its better collecting performance.

[Research and development of portable hypertension therapeutic apparatus based on biofeedback mechanism].

Non-drug treatment of hypertension has become a research hotspot, which might overcome the heavy economic burden and side effects of drug treatment for the patients. Because of the good treatment effect and convenient operation, a new treatment based on slow breathing training is increasingly becoming a kind of physical therapy for hypertension. This paper explains the principle of hypertension treatment based on slow breathing training method, and introduces the overall structure of the portable blood pressure controlling instrument, including breathing detection circuit, the core control module, audio module, memory module and man-machine interaction module. We give a brief introduction to the instrument and the software in this paper. The prototype testing results showed that the treatment had a significant effect on controlling the blood pressure.