Search

Background: Oral mucosa lesions are the third most prevalent oral pathology, following caries and periodontal diseases. Teledentistry offers an effective way to manage patients with these lesions. The accuracy of remote diagnoses and consultations relies heavily on the quality of the information and photos sent to remote specialists. This study aims to evaluate the usability and reliability of a teledentistry tool for the remote diagnosis of oral lesions. Methods: The cross-sectional study included both usability evaluation and reliability assessment. The teledentistry platform, "OralMedTeledent", facilitated synchronous and asynchronous interactions, allowing for patient consultations, remote follow-ups, and doctor-to-doctor consultations. Usability was evaluated by 5 experts using the Nielsen heuristic checklist. Reliability was assessed from August 2022 to September 2023 with 109 patients, using Cohen's kappa coefficient to measure agreement between examiners and the gold standard in diagnosing oral lesions. Results: The findings revealed 66 usability issues, most of which were related to helping users recognize, diagnose, and recover from errors, as well as issues with help and documentation. Among these, 11 issues were of minor severity. The reliability test, conducted with 109 participants (57.8% female, 42.2% male) showed that the web-based teleconsultation system performed significantly well. The system demonstrated significant substantial performance (0.81 ≤ κ < 1; P > 0.05). Conclusion: Overall, the web-based teleconsultation system has proven to be reliable for the remote diagnosis of oral lesions, making it a valuable alternative during emergencies such as the COVID-19 pandemic. However, several usability issues have been identified and need to be addressed. [ABSTRACT FROM AUTHOR]

Abstract Background Oral mucosa lesions are the third most prevalent oral pathology, following caries and periodontal diseases. Teledentistry offers an effective way to manage patients with these lesions. The accuracy of remote diagnoses and consultations relies heavily on the quality of the information and photos sent to remote specialists. This study aims to evaluate the usability and reliability of a teledentistry tool for the remote diagnosis of oral lesions. Methods The cross-sectional study included both usability evaluation and reliability assessment. The teledentistry platform, "OralMedTeledent", facilitated synchronous and asynchronous interactions, allowing for patient consultations, remote follow-ups, and doctor-to-doctor consultations. Usability was evaluated by 5 experts using the Nielsen heuristic checklist. Reliability was assessed from August 2022 to September 2023 with 109 patients, using Cohen's kappa coefficient to measure agreement between examiners and the gold standard in diagnosing oral lesions. Results The findings revealed 66 usability issues, most of which were related to helping users recognize, diagnose, and recover from errors, as well as issues with help and documentation. Among these, 11 issues were of minor severity. The reliability test, conducted with 109 participants (57.8% female, 42.2% male) showed that the web-based teleconsultation system performed significantly well. The system demonstrated significant substantial performance (0.81 ≤ κ 0.05). Conclusion Overall, the web-based teleconsultation system has proven to be reliable for the remote diagnosis of oral lesions, making it a valuable alternative during emergencies such as the COVID-19 pandemic. However, several usability issues have been identified and need to be addressed.

The coronavirus disease 2019 (COVID-19) pandemic has sparked changes across various domains, encompassing health, commerce, education, and the economy. Given the widespread impact of COVID-19 across numerous nations, it has strained hospital resources, oxygen reserves, and healthcare personnel. Consequently, there exists an urgent necessity to exploit sophisticated technologies such as artificial intelligence and the internet of things (IoT) to monitor patients effectively. This scholarly article proposes a prototype that integrates IoT and artificial intelligence (IA) for the surveillance of COVID-19 patients within healthcare facilities. Wearable IoT devices, equipped with embedded sensors, autonomously collect vital information like oxygen levels and body temperature. Notably, oxygen saturation and heart rate serve as significant markers in COVID-19 cases. These metrics are discerned through the deep learning capabilities of the TensorFlow library. The prototype aims to augment the intelligence of IoT sensors to identify these crucial signs through a trained model. A meticulously labeled dataset comprising oxygen saturation and heart rate data is amassed. Deep neural networks are deployed to prognosticate the disease's progression. The utilization of these technologies harbors the potential for rapid advancements in healthcare, thereby mitigating risks to human life and fostering more proactive responses to health crises. [ABSTRACT FROM AUTHOR]

Many patients with obstructive sleep apnoea (OSA) remain undiagnosed and thus untreated, and in part this relates to delay in diagnosis. Novel diagnostic strategies may improve access to diagnosis. In a multicentre, randomised study, we evaluated time to treatment decision in patients referred for suspected OSA, comparing a mandibular movement (MM) monitor to respiratory polygraphy, the most commonly used OSA detection method in the UK. Adults with high pre-test probability OSA were recruited from both northern Scotland and London. 40 participants (70 % male, mean±SD age 46.8 ± 12.9 years, BMI 36.9 ± 7.5 kg/m², ESS 14.9 ± 4.1) wore a MM monitor and respiratory polygraphy simultaneously overnight and were randomised (1:1) to receive their treatment decision based on results from either device. Compared to respiratory polygraphy, MM monitor reduced time to treatment decision by 6 days (median(IQR): 13.5 (7.0-21.5) vs. 19.5 (13.7-35.5) days, P = 0.017) and saved an estimated 29 min of staff time per patient. [ABSTRACT FROM AUTHOR]

Copyright of Chinese Medical Equipment Journal is the property of Chinese Medical Equipment Journal Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Many patients with obstructive sleep apnoea (OSA) remain undiagnosed and thus untreated, and in part this relates to delay in diagnosis. Novel diagnostic strategies may improve access to diagnosis. In a multicentre, randomised study, we evaluated time to treatment decision in patients referred for suspected OSA, comparing a mandibular movement (MM) monitor to respiratory polygraphy, the most commonly used OSA detection method in the UK. Adults with high pre-test probability OSA were recruited from both northern Scotland and London. 40 participants (70 % male, mean±SD age 46.8 ± 12.9 years, BMI 36.9 ± 7.5 kg/m2, ESS 14.9 ± 4.1) wore a MM monitor and respiratory polygraphy simultaneously overnight and were randomised (1:1) to receive their treatment decision based on results from either device. Compared to respiratory polygraphy, MM monitor reduced time to treatment decision by 6 days (median(IQR): 13.5 (7.0–21.5) vs. 19.5 (13.7–35.5) days, P = 0.017) and saved an estimated 29 min of staff time per patient.

The unexpectedly high number of deaths caused by inadequate medical care is, to date, considered as a serious problem. Moreover, the ratio of elderly people who require continuous care is rising. Therefore, a patient monitoring system (PMS) also known as remote patient monitoring (RPM) using the latest Internet of Things (IoT) technology becomes a viable solution that can provide efficient healthcare from a remote distance. PMS monitors timely physiological signals of a patient’s health and can reduce the healthcare costs of treatment significantly. In PMS, different health and vital signs issues such as body temperature, heart rate, sleep monitoring, fall detection, and blood pressure can be checked effectively in real-time. To this end, this paper provides a clear vision of electronic healthcare assistance based on PMS and explores the applications of IoT that allow efficient medical services in healthcare systems. In particular, the objective of this paper is to provide a review of PMS, current research, and the challenges associated with this area. Besides, the essential services that can be offered by PMS for monitoring human activities are also discussed. Furthermore, the communication networks and protocols that are required to endure efficient healthcare systems are explained. Finally, this paper discusses several research challenges and open issues that can be investigated for further work. Overall, this paper offers valuable insights for both industry professionals and academic researchers, exploring potential avenues for new research directions.

This study aims explore the feasibility of using neural network (NNs) and deep learning to diagnose three common respiratory diseases with few symptom words. These three diseases are nasopharyngitis, upper respiratory infection, and bronchitis/bronchiolitis. Through natural language processing, the symptom word vectors are encoded by GPT-2 and classified by the last linear layer of the NN. The experimental results are promising, showing that this model achieves a high performance in predicting all three diseases. They revealed 90% accuracy, which suggests the implications of the developed model, highlighting its potential use in assisting patients' understanding of their conditions via a remote diagnosis. Unlike previous studies that have focused on extracting various categories of information from medical records, this study directly extracts sequential features from unstructured text data, reducing the effort required for data pre-processing. [ABSTRACT FROM AUTHOR]

The coronavirus disease 2019 (COVID‐19) pandemic had widespread impact on health care systems globally—particularly services arranged around elective admission and attendance such as epilepsy monitoring units and home video‐EEG telemetry (HVET). Here, we review the ongoing impacts of the pandemic on HVET services among several different providers who used different initial models of HVET. We discuss the features of HVET that led to success in providing continued diagnostic services to patients with epilepsy and related disorders and through retrospective audit of our services demonstrate the high diagnostic yield of HVET. We reflect on this unforeseen future and its implications for other diagnostic techniques and approaches. [ABSTRACT FROM AUTHOR]

Numerous classification systems have been developed over the years, systems which not only provide assistance to dermatologists, but also enable individuals, especially those living in areas with low medical access, to get a diagnosis. In this paper, a Machine Learning model, which performs a binary classification, and, which for the remainder of this paper will be abbreviated as ML model, is trained and tested, so as to evaluate its effectiveness in giving the right diagnosis, as well as to point out the limitations of the given method, which include, but are not limited to, the quality of smartphone images, and the lack of FAIR image datasets for model training. The results indicate that there are many measures to be taken and improvements to be made, if such a system were to become a reliable tool in real-life circumstances. [ABSTRACT FROM AUTHOR]

Background: Remote diagnosis using collaborative tools have led to multilingual joint working sessions in various domains, including comprehensive health care, and resulting in more inclusive health care services. One of the main challenges is providing a real-time solution for shared documents and presentations on display to improve the efficacy of noninvasive, safe, and far-reaching collaborative models. Classic optical character recognition (OCR) solutions fail when there is a mixture of languages or dialects or in case of the participation of different technical levels and skills. Due to the risk of misunderstandings caused by mistranslations or lack of domain knowledge of the interpreters involved, the technological pipeline also needs artificial intelligence (AI)-supported improvements on the OCR side. This study examines the feasibility of machine learning-supported OCR in a multilingual environment. The novelty of our method is that it provides a solution not only for different speaking languages but also for a mixture of technological languages, using artificially created vocabulary and a custom training data generation approach. Methods: A novel hybrid language vocabulary creation method is utilized in the OCR training process in combination with convolutional recurrent neural networks (CRNNs) and a single visual model for scene text recognition within the patch-wise image tokenization framework (SVTR). Data: In the research, we used a dedicated Python-based data generator built on dedicated collaborative tool-based templates to cover and simulated the real-life variances of remote diagnosis and co-working collaborative sessions with high accuracy. The generated training datasets ranged from 66 k to 8.5 M in size. Twenty-one research results were analyzed. Instruments: Training was conducted by using tuned PaddleOCR with CRNN and SVTR modeling and a domain-specific, customized vocabulary. The Weight & Biases (WANDB) machine learning (ML) platform is used for experiment tracking, dataset versioning, and model evaluation. Based on the evaluations, the training dataset was adjusted by using a different language corpus or/and modifications applied to templates. Results: The machine learning models recognized the multilanguage/hybrid texts with high accuracy. The highest precision scores achieved are 90.25%, 91.35%, and 93.89%. Conclusions: machine learning models for special multilanguages, including languages with artificially made vocabulary, perform consistently with high accuracy. [ABSTRACT FROM AUTHOR]

This study aims explore the feasibility of using neural network (NNs) and deep learning to diagnose three common respiratory diseases with few symptom words. These three diseases are nasopharyngitis, upper respiratory infection, and bronchitis/bronchiolitis. Through natural language processing, the symptom word vectors are encoded by GPT-2 and classified by the last linear layer of the NN. The experimental results are promising, showing that this model achieves a high performance in predicting all three diseases. They revealed 90% accuracy, which suggests the implications of the developed model, highlighting its potential use in assisting patients’ understanding of their conditions via a remote diagnosis. Unlike previous studies that have focused on extracting various categories of information from medical records, this study directly extracts sequential features from unstructured text data, reducing the effort required for data pre-processing.

Background: This article describes how a simple slide scanner with remote viewing software enabled a remote “nomadic” pathologist to continue his role as specialist lead for a regional gastrointestinal multidisciplinary team meeting (MDTM) after relocating to another site in the 5 hospital Southwest UK Peninsula cancer network just prior to the COVID-19 pandemic. Materials and methods: The author used digital pathology (DP) to supplement a conventional workflow as a way of minimising delay in reporting and reviewing slides for a regional specialist Oesophagogastric MDTM (the OGSMDT). The specialist centre at University Hospital Plymouth (UHP) is 58 miles from the author’s new workplace at Royal Cornwall Hospital (RCHT). Slides from the 44 cases (10% of this specialist annual workload) in this validation study were reported or reviewed digitally using the slide scanner. All were listed for the OGSMDT due to being clinically suspicious for upper gastrointestinal malignancy, having been processed at UHP, or one of the other hospitals in the cancer network. Results: The scanner allowed the author who was only on site at UHP 1 day per week to prevent delays in reporting/ reviewing glass slides, using remote DP. Confidence in digital diagnosis was assessed using the Royal College of Pathologists recommendations. The author was the primary pathologist signing out 31, and second opinion for the remaining 13 cases. These comprised a mixture of biopsies as well as endoscopic and surgical excision specimens. The DP system enabled the author to report the cases digitally with an equivalent degree of confidence to glass slides and no significant discrepancies were identified between the author’s digital and final glass slide diagnosis. Conclusions: The scanner was found to be safe and effective for remote reporting and review for OGSMDT cases. It was recognised that DP was advantageous to enable this role to continue remotely but that a fully integrated digital reporting system capable of high-capacity scanning would be preferable to the simple system used. [ABSTRACT FROM AUTHOR]

Context: Telepathology is a promising tool for remote communities to receive pathology services where professional diagnosis services are inadequate. Aims: We aimed to clarify how effective telepathology was when compared with conventional pathology service among rural communities of Bangladesh. Methods and Materials: We conducted a cross-sectional study in suburban and rural areas of Bangladesh between June and August 2020. We enrolled 117 participants who received both telepathology services from Thakurgaon Eye Hospital and conventional pathology service experience. The participant's satisfaction with the accessibility and perceptions were statistically compared. In addition, we summarized descriptive statistics using the frequencies and percentages of participants' responses. Statistical Analysis Used: Wilcoxon's Signed-rank test using SPSS statistic software version 25.00. Results: Among the study participants, service cost, travel cost, travel time, waiting time, and travel distance were significantly higher for conventional pathology than telepathology (P < 0.001). The majority of participants (94%) were satisfied with the telepathology experience; however, one out of 117 participants was dissatisfied with this service when their travel distance was far away (≥50 km). Among the participants, 91.5% thought that telepathology service was effective for their treatment, and 98.3% wanted to continue this service in their community. On an average, participants saved 58% (95% CI, 53.4–61.5) of cost using telepathology rather than conventional pathology service. Conclusions: Remote under-resourced communities received professional pathology services with less time-consuming and significantly lower costs using the telepathology approach. Where pathology services are absent/insufficient, telepathology is efficacious for primary diagnosis, screening, and referral through professional pathologists for the satisfactory treatment of unreached communities.

Background: This article describes how a simple slide scanner with remote viewing software enabled a remote “nomadic” pathologist to continue his role as specialist lead for a regional gastrointestinal multidisciplinary team meeting (MDTM) after relocating to another site in the 5 hospital Southwest UK Peninsula cancer network just prior to the COVID-19 pandemic.Materials and methods: The author used digital pathology (DP) to supplement a conventional workflow as a way of minimising delay in reporting and reviewing slides for a regional specialist Oesophagogastric MDTM (the OGSMDT). The specialist centre at University Hospital Plymouth (UHP) is 58 miles from the author’s new workplace at Royal Cornwall Hospital (RCHT). Slides from the 44 cases (10% of this specialist annual workload) in this validation study were reported or reviewed digitally using the slide scanner. All were listed for the OGSMDT due to being clinically suspicious for upper gastrointestinal malignancy, having been processed at UHP, or one of the other hospitals in the cancer network.Results: The scanner allowed the author who was only on site at UHP 1 day per week to prevent delays in reporting/reviewing glass slides, using remote DP. Confidence in digital diagnosis was assessed using the Royal College of Pathologists recommendations. The author was the primary pathologist signing out 31, and second opinion for the remaining 13 cases. These comprised a mixture of biopsies as well as endoscopic and surgical excision specimens. The DP system enabled the author to report the cases digitally with an equivalent degree of confidence to glass slides and no significant discrepancies were identified between the author’s digital and final glass slide diagnosis.Conclusions: The scanner was found to be safe and effective for remote reporting and review for OGSMDT cases. It was recognised that DP was advantageous to enable this role to continue remotely but that a fully integrated digital reporting system capable of high-capacity scanning would be preferable to the simple system used.

Background and purpose: The National Institutes of Health Stroke Scale (NIHSS) is the most recommended tool for objectively quantifying the impairment caused by a suspected stroke. Nevertheless, it is mainly used by trained neurologists in the emergency department (ED). To bring forward the NIHSS to the pre-hospital setting, a smartphone-based Telestroke system was developed. It captures the full NIHSS by video, transmits it off-line, and enables assessment by a distant stroke physician. We aimed to compare the reliability of an NIHSS score determined by a neurologist from afar, using the platform with a standard NIHSS assessment performed in the emergency departments. Methods: Amulti-center prospective study was conducted in two centers (Vall d'Hebron, Barcelona, and Rambam, Israel). Patients admitted to the ED with suspected stroke had a neurological exam based on the NIHSS, while being recorded by the system. A skilled neurologist rated the NIHSS according to the videos oine. The results were compared with the NIHSS score given by a neurologist at the bedside. Results: A total of 95 patients with suspected stroke were included. The overall intraclass correlation coefficient was 0.936 (0.99 in VdH and 0.84 in Rambam), indicating excellent and good reliability, respectively. Conclusion: Remote stroke assessment based on the NIHSS, using videos segments collected by a dedicated platform, installed on a standard smartphone, is a reliable measurement as compared with the bedside evaluation. [ABSTRACT FROM AUTHOR]

The Internet of Medical Things (IoMT) is transforming modern healthcare systems by merging technological, economical, and social opportunities and has recently gained traction in the healthcare domain. The severely contagious respiratory syndrome coronavirus called COVID-19 has emerged as a severe threat to public health. COVID-19 is a highly infectious virus that is spread by person-to-person contact. Therefore, minimizing physical interactions between patients and medical healthcare workers is necessary. The significance of technology and its associated potential were fully explored and proven during the outbreak of COVID-19 in all domains of human life. Healthcare systems employ all modes of technology to facilitate the increasing number of COVID-19 patients. The need for remote healthcare was reemphasized, and many remote healthcare solutions were adopted. Various IoMT-based systems were proposed and implemented to support traditional healthcare systems with reaching the maximum number of people remotely. The objective of this research is twofold. First, a systematic literature review (SLR) is conducted to critically evaluate 76 articles on IoMT systems for different medical applications, especially for COVID-19 and other health sectors. Secondly, we briefly review IoMT frameworks and the role of IoMT-based technologies in COVID-19 and propose a framework, named 'cov-AID', that remotely monitors and diagnoses the disease. The proposed framework encompasses the benefits of IoMT sensors and extensive data analysis and prediction. Moreover, cov-AID also helps to identify COVID-19 outbreak regions and alerts people not to visit those locations to prevent the spread of infection. The cov-AID is a promising framework for dynamic patient monitoring, patient tracking, quick disease diagnosis, remote treatment, and prevention from spreading the virus to others. We also discuss potential challenges faced in adopting and applying big data technologies to combat COVID-19. [ABSTRACT FROM AUTHOR]

Background and purposeThe National Institutes of Health Stroke Scale (NIHSS) is the most recommended tool for objectively quantifying the impairment caused by a suspected stroke. Nevertheless, it is mainly used by trained neurologists in the emergency department (ED). To bring forward the NIHSS to the pre-hospital setting, a smartphone-based Telestroke system was developed. It captures the full NIHSS by video, transmits it off-line, and enables assessment by a distant stroke physician. We aimed to compare the reliability of an NIHSS score determined by a neurologist from afar, using the platform with a standard NIHSS assessment performed in the emergency departments.MethodsA multi-center prospective study was conducted in two centers (Vall d'Hebron, Barcelona, and Rambam, Israel). Patients admitted to the ED with suspected stroke had a neurological exam based on the NIHSS, while being recorded by the system. A skilled neurologist rated the NIHSS according to the videos offline. The results were compared with the NIHSS score given by a neurologist at the bedside.ResultsA total of 95 patients with suspected stroke were included. The overall intraclass correlation coefficient was 0.936 (0.99 in VdH and 0.84 in Rambam), indicating excellent and good reliability, respectively.ConclusionRemote stroke assessment based on the NIHSS, using videos segments collected by a dedicated platform, installed on a standard smartphone, is a reliable measurement as compared with the bedside evaluation.

Objective: We determined the diagnostic accuracies of the mydriatic, monoscopic, iPhone 6s+ optic nerve photographs with a 20D lens and the Melbourne Rapid Fields (MRF) visual fields iPad application. Methods: This was a prospective, cross-sectional, single-center study involving 47 non-glaucomatous and 49 glaucomatous eyes. Each eye underwent 2 visual field tests: MRF iPad application and the Humphrey Field Analyzer (HRF). Mydriatic photographs of the fundus were taken with two devices: an iPhone 6s+ combined with a 20 D lens and the Visucam 500 fundus camera. All printouts were evaluated by 2 independent, masked glaucoma specialists. Diagnostic accuracies between the modalities were computed. Agreements between different parameters of both devices were analyzed using Cohen's kappa test. Results: Smartphone-based (iPhone 6s+) fundus photos had an overall sensitivity of 100%, specificity of 89.36%, positive predictive value (PPV) of 89.36% and negative predictive value (NPV) of 100%, with all kappa values between graders of each parameter above 0.61. Tablet-based Melbourne Rapid Fields test had a sensitivity of 81.82%, specificity of 86.54%, PPV of 83.72% and NPV of 84.91%, showing good agreement with the HRF with a kappa value of 0.68 ± 0.07. Conclusion: Smartphone-based fundus photography and tablet-based visual field tests are comparable to the standard fundus photos and visual field tests in evaluating the optic nerve and visual field. These portable devices are reliable and appropriate tools for diagnosing glaucoma and can be used for documentation and testing in remote areas and in a wider range of settings. [ABSTRACT FROM AUTHOR]

Abnormal movement of the head and neck is a typical symptom of Cervical Dystonia (CD). Accurate scoring on the severity scale is of great significance for treatment planning. The traditional scoring method is to use a protractor or contact sensors to calculate the angle of the movement, but this method is time-consuming, and it will interfere with the movement of the patient. In the recent outbreak of the coronavirus disease, the need for remote diagnosis and treatment of CD has become extremely urgent for clinical practice. To solve these problems, we propose a multi-view vision based CD severity scale scoring method, which detects the keypoint positions of the patient from the frontal and lateral images, and finally scores the severity scale by calculating head and neck motion angles. We compared the Toronto Western Spasmodic Torticollis Rating Scale (TWSTRS) subscale scores calculated by our vision based method with the scores calculated by a neurologist trained in dyskinesia. An analysis of the correlation coefficient was then conducted. Intra-class correlation (ICC)(3,1) was used to measure absolute accuracy. Our multi-view vision based CD severity scale scoring method demonstrated sufficient validity and reliability. This low-cost and contactless method provides a new potential tool for remote diagnosis and treatment of CD. [ABSTRACT FROM AUTHOR]

Context: Telepathology is a promising tool for remote communities to receive pathology services where professional diagnosis services are inadequate. Aims: We aimed to clarify how effective telepathology was when compared with conventional pathology service among rural communities of Bangladesh. Methods and Materials: We conducted a cross-sectional study in suburban and rural areas of Bangladesh between June and August 2020. We enrolled 117 participants who received both telepathology services from Thakurgaon Eye Hospital and conventional pathology service experience. The participant's satisfaction with the accessibility and perceptions were statistically compared. In addition, we summarized descriptive statistics using the frequencies and percentages of participants' responses. Statistical Analysis Used: Wilcoxon's Signed-rank test using SPSS statistic software version 25.00. Results: Among the study participants, service cost, travel cost, travel time, waiting time, and travel distance were significantly higher for conventional pathology than telepathology (P < 0.001). The majority of participants (94%) were satisfied with the telepathology experience; however, one out of 117 participants was dissatisfied with this service when their travel distance was far away (≥50 km). Among the participants, 91.5% thought that telepathology service was effective for their treatment, and 98.3% wanted to continue this service in their community. On an average, participants saved 58% (95% CI, 53.4–61.5) of cost using telepathology rather than conventional pathology service. Conclusions: Remote under-resourced communities received professional pathology services with less time-consuming and significantly lower costs using the telepathology approach. Where pathology services are absent/insufficient, telepathology is efficacious for primary diagnosis, screening, and referral through professional pathologists for the satisfactory treatment of unreached communities. [ABSTRACT FROM AUTHOR]

People are exploring new ideas based on artificial intelligent infrastructures for immediate processing, in which the main obstacles of widely-deploying deep methods are the huge volume of neural network and the lack of training data. To meet the high computing and low latency requirements in modeling remote smart tongue diagnosis with edge computing, an efficient and compact deep neural network design is necessary, while overcoming the vast challenge on modeling its intrinsic diagnosis patterns with the lack of clinical data. To address this challenge, a deep transfer learning model is proposed for the effective tongue diagnosis, based on the proposed similar-sparse domain adaptation (SSDA) scheme. Concretely, a transfer strategy of similar data is introduced to efficiently transfer necessary knowledge, overcoming the insufficiency of clinical tongue images. Then, to generate simplified structure, the network is pruned with transferability remained in domain adaptation. Finally, a compact model combined with two sparse networks is designed to match limited edge device. Extensive experiments are conducted on the real clinical dataset. The proposed model can use fewer training data samples and parameters to produce competitive results with less power and memory consumptions, making it possible to widely run smart tongue diagnosis on low-performance infrastructures.

Background: Remote diagnosis using collaborative tools have led to multilingual joint working sessions in various domains, including comprehensive health care, and resulting in more inclusive health care services. One of the main challenges is providing a real-time solution for shared documents and presentations on display to improve the efficacy of noninvasive, safe, and far-reaching collaborative models. Classic optical character recognition (OCR) solutions fail when there is a mixture of languages or dialects or in case of the participation of different technical levels and skills. Due to the risk of misunderstandings caused by mistranslations or lack of domain knowledge of the interpreters involved, the technological pipeline also needs artificial intelligence (AI)-supported improvements on the OCR side. This study examines the feasibility of machine learning-supported OCR in a multilingual environment. The novelty of our method is that it provides a solution not only for different speaking languages but also for a mixture of technological languages, using artificially created vocabulary and a custom training data generation approach. Methods: A novel hybrid language vocabulary creation method is utilized in the OCR training process in combination with convolutional recurrent neural networks (CRNNs) and a single visual model for scene text recognition within the patch-wise image tokenization framework (SVTR). Data: In the research, we used a dedicated Python-based data generator built on dedicated collaborative tool-based templates to cover and simulated the real-life variances of remote diagnosis and co-working collaborative sessions with high accuracy. The generated training datasets ranged from 66 k to 8.5 M in size. Twenty-one research results were analyzed. Instruments: Training was conducted by using tuned PaddleOCR with CRNN and SVTR modeling and a domain-specific, customized vocabulary. The Weight & Biases (WANDB) machine learning (ML) platform is used for experiment tracking, dataset versioning, and model evaluation. Based on the evaluations, the training dataset was adjusted by using a different language corpus or/and modifications applied to templates. Results: The machine learning models recognized the multilanguage/hybrid texts with high accuracy. The highest precision scores achieved are 90.25%, 91.35%, and 93.89%. Conclusions: machine learning models for special multilanguages, including languages with artificially made vocabulary, perform consistently with high accuracy.

Abstract Background Intraoral scans (IOS) provide three-dimensional images with approximate true colors representing a possible tool in teledentistry for remote examination. The aim of the present cross-sectional validation study was, therefore, to evaluate the levels of agreement between remote diagnoses derived from IOS and diagnoses based on clinical examinations for assessing dental and periodontal conditions. Methods The test sample comprised 10 patients representing different clinical conditions. Following the acquisition of IOS (Trios, 3Shape), a full-mouth dental and periodontal examination was done and periapical radiographs were taken. Ten dentists were asked to perform dental and periodontal scorings for each of the ten patients on a tablet computer presenting the IOS. Scores included diagnosis of gingivitis/periodontitis, and evaluated presence as well as amount of plaque and calculus, and presence of teeth exhibiting gingival recession, furcation involvement, erosion, tooth wear, stain, and non-carious cervical lesion, as well as presence of decayed, filled, and crowned teeth and implants. In a second round of assessments, the periapical radiographs were provided and the dentists were able to change the scores. The time for the remote assessment was recorded. The agreement between remote and clinical scorings (reference) was then analyzed descriptively. Results The mean time for the tele assessment was 3.17 min and the additional consultation of the radiographs accounted for another 1.48 min. The sensitivity and specificity values were 0.61 and 0.39 for gingivitis and 0.67 and 0.33 for periodontitis, with no relevant changes when radiographs were provided for the diagnosis of periodontitis (0.72 and 0.28). The agreement for dichotomized dental and periodontal indices ranged between 78 and 95%. With the provision of radiographs, the remote examiners were able to detect existing filled teeth, crowned teeth, and implants, whereas the detection of decayed teeth (70%) was not improved. Conclusions The remote examination using IOS was effective in detecting dental findings, whereas periodontal conditions could not be assessed with the same accuracy. Still, remote assessment of IOS would allow a time-efficient screening and triage of patients. Improvement of the image quality of IOS may further allow to increase the accuracy of remote assessments in dentistry. According to the Swiss Regulation this investigation is not a clinical trial and therefore no registration in a WHO-registry is needed.

In the electric power industry of Russia and abroad, special attention is paid to the problem of an increase in the number of accidents caused by damage to high-voltage insulators in high-voltage equipment. An analysis of emergencies at substations and open switchgears [1- 2, 4] was carried out, which showed that in most cases the causes of damage to high-voltage insulators are natural aging in an applied electric field, overvoltage, and the presence of initial defects in the manufacture of high-voltage insulators. Based on this fact, we developed various methods of non-contact diagnostics of high-voltage insulators in order to identify defects at an early stage of their development. Particular attention was paid to the method of partial discharges because the characteristics of partial discharges provide information on the parameters of defects. The article describes a set of non-contact methods for remote diagnostics of high-voltage insulators; a two-channel method for remote diagnostics of the operating state of high-voltage insulators, based on the registration of partial discharges by electromagnetic and acoustic sensors; a device that allows visual inspection and the search for faulty high-voltage equipment; remote non-contact method for recording electric fields of high tension of industrial frequency, as well as their spatial orientation based on the electro-optical effect. We developed a mock-up of a portable diagnostic device for implementing research methods for high-voltage dielectric elements to diagnose their technical condition using the described complex of non-contact methods. The measuring device as part of a portable diagnostic device consists of a set of sensors for collecting diagnostic information detected by electromagnetic, acoustic and electro-optical sensors and a voltage phase signal applied to the studied highvoltage insulator. The simultaneous use of several sensors at once made it possible to increase the accuracy of localization of partial discharges in high-voltage insulators. Visualization of diagnostic results is possible at the control room in the form of amplitude-phase, frequencyphase and amplitude-frequency diagrams of the distribution of characteristics of partial discharges and on a portable device in the form of radiation intensity from the selected sensor. A portable diagnostic device made it possible in laboratory conditions to study electrophysical processes in various dielectric materials and products under the influence of strong alternating electric fields. A study was made of the features of defects on the rod and the terminal-terminal contact, a diagram of the electrophysical processes accompanying the emission of partial discharges was constructed, and the causes of their occurrence were established.

Telecardiology, the remote diagnosis and treatment of cardiac conditions, is experiencing a significant increase in developing nations. This article explores the driving forces behind this trend and its implications. Limited access to healthcare facilities, especially in rural, isolated, and underdeveloped regions, has propelled the adoption of telecardiology as a cost-effective solution to bridge the gap in cardiac care provision. Technological advancements, such as portable diagnostic devices and improvements in telecommunication infrastructure, have facilitated the expansion of telecardiology services. Moreover, the COVID-19 pandemic has accelerated the acceptance and deployment of telehealth solutions worldwide. Nevertheless, challenges persist, including regulatory hurdles, data privacy concerns, and disparities in digital literacy. Despite these obstacles, the rise of telecardiology in developing countries presents a promising opportunity to enhance access to cardiac care and improve health outcomes among underserved populations., Competing Interests: Declaration of competing interest The authors state that they have no known financial conflicts of interest or personal relationships that could have influenced the work reported in this paper., (Copyright © 2024. Published by Elsevier Inc.)

Abnormal movement of the head and neck is a typical symptom of Cervical Dystonia (CD). Accurate scoring on the severity scale is of great significance for treatment planning. The traditional scoring method is to use a protractor or contact sensors to calculate the angle of the movement, but this method is time-consuming, and it will interfere with the movement of the patient. In the recent outbreak of the coronavirus disease, the need for remote diagnosis and treatment of CD has become extremely urgent for clinical practice. To solve these problems, we propose a multi-view vision based CD severity scale scoring method, which detects the keypoint positions of the patient from the frontal and lateral images, and finally scores the severity scale by calculating head and neck motion angles. We compared the Toronto Western Spasmodic Torticollis Rating Scale (TWSTRS) subscale scores calculated by our vision based method with the scores calculated by a neurologist trained in dyskinesia. An analysis of the correlation coefficient was then conducted. Intra-class correlation (ICC)(3,1) was used to measure absolute accuracy. Our multi-view vision based CD severity scale scoring method demonstrated sufficient validity and reliability. This low-cost and contactless method provides a new potential tool for remote diagnosis and treatment of CD.

The deep tendon reflex exam is an important part of neurological assessment of patients consisting of two components, reflex elicitation and reflex grading. While this exam has traditionally been performed in person, with trained clinicians both eliciting and grading the reflex, this work seeks to enable the exam by novices. The COVID-19 pandemic has motivated greater utilization of telemedicine and other remote healthcare delivery tools. A smart tendon hammer capable of streaming acceleration measurements wirelessly allows differentiation of correct and incorrect tapping locations with 91.5% accuracy to provide feedback to users about the appropriateness of stimulation, enabling reflex elicitation by laypeople, while survey results demonstrate that novices are reasonably able to grade reflex responses. Novice reflex grading demonstrates adequate performance with a mean error of 0.2 points on a five point scale. This work shows that by assisting in the reflex elicitation component of the reflex exam via a smart hammer and feedback application, novices should be able to complete the reflex exam remotely, filling a critical gap in neurological care during the COVID-19 pandemic.

With the rapid development of microelectronics, handheld ultrasound devices emerged and have a widespread use in the field of medicine and healthcare. The handheld ultrasound is a modality of medical ultrasonic device that is portable (i.e., carried by hand), easy to operate and in some cases even combine the scanner with the host system. It normally has the characteristics of light weight, small size and low power consumption. With the wireless imaging transmission technique, remote and intelligent diagnosis is possible for the doctors using handheld ultrasound devices. As soon as the low-cost, highperformance handheld ultrasound device was launched, it attracted clinical attention and received a warm welcome from primary doctors and clinicians, thereby accelerating the development of ultrasonic clinical visualization. In this paper, we will illustrate the status and roles of handheld ultrasound for its clinical settings and applications in the past, current, and future.

A novel DNC（distributed numerical control） system,which is used to remotely monitor CNC machine tools of FANUC NC system as well as inspection equipment or devices,has been developed based on Socket communication and multithread technology by using SQL Server database and.NET platform.This DNC system can collect the real time information of CNC machines and inspection equipment or devices,and has the functions like the machine state monitoring,data integration and management,performance analysis,fault remote diagnosis,workshop production management,and product quality management and control.In this way,the data integrity and integration has been realized.The architecture of the system is presented and the approaches to the realization of the function modules are elaborated.The data flow,data interpretation and alarm monitoring mechanism are also discussed.This system has been applied in manufacturing plants and performs well.

Abstract Background Routine field diagnosis of malaria is a considerable challenge in rural and low resources endemic areas mainly due to lack of personnel, training and sample processing capacity. In addition, differential diagnosis of Plasmodium species has a high level of misdiagnosis. Real time remote microscopical diagnosis through on-line crowdsourcing platforms could be converted into an agile network to support diagnosis-based treatment and malaria control in low resources areas. This study explores whether accurate Plasmodium species identification—a critical step during the diagnosis protocol in order to choose the appropriate medication—is possible through the information provided by non-trained on-line volunteers. Methods 88 volunteers have performed a series of questionnaires over 110 images to differentiate species (Plasmodium falciparum, Plasmodium ovale, Plasmodium vivax, Plasmodium malariae, Plasmodium knowlesi) and parasite staging from thin blood smear images digitalized with a smartphone camera adapted to the ocular of a conventional light microscope. Visual cues evaluated in the surveys include texture and colour, parasite shape and red blood size. Results On-line volunteers are able to discriminate Plasmodium species (P. falciparum, P. malariae, P. vivax, P. ovale, P. knowlesi) and stages in thin-blood smears according to visual cues observed on digitalized images of parasitized red blood cells. Friendly textual descriptions of the visual cues and specialized malaria terminology is key for volunteers learning and efficiency. Conclusions On-line volunteers with short-training are able to differentiate malaria parasite species and parasite stages from digitalized thin smears based on simple visual cues (shape, size, texture and colour). While the accuracy of a single on-line expert is far from perfect, a single parasite classification obtained by combining the opinions of multiple on-line volunteers over the same smear, could improve accuracy and reliability of Plasmodium species identification in remote malaria diagnosis.

Fifth Generation (5G) mobile communications technology became available in Japan as of the end of March 2020. The Ministry of Internal Affairs and Communications (MIC) is proceeding with a plan to use 5G for a doctor-to-doctor remote diagnosis system. This remote diagnosis offers patients the benefit of receiving advanced medical care without having to travel long distances. The provision of a remote diagnosis will provide elderly patients in rural areas with an earlier diagnosis without burdening patients in Japan where the aging population and the uneven distribution of doctors are increasing. However, the system will increase the burden on specialists by expanding the doctor's catchment area. As a solution to that problem, deep learning-based artificial intelligence (AI) is expected to reduce the burden on doctors. In order to realize 5G- and AI-based real-time diagnostic support, diagnostic imaging using AI and an AI model that provides instructions are required. This is because ultrasonography and endoscopy, which can be used for remote diagnosis, do not acquire data on fixed areas like a CT or MRI scan. The AI model needs to instruct the doctor at the patient's home in order to collect appropriate information in accordance with the patient's symptoms and status. In order to build an interactive AI model, the interactions between doctors who are making a remote diagnosis should be recorded as training data and a 5G-based remote diagnosis system should be created. A remote diagnostic support system incorporating 5G and interactive diagnostic imaging incorporating AI will result in a system that places less of a burden on patients and doctors. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) is a newly emerging term for the new generation of the Internet which allows understanding between interconnected devices. IoT acts as an assistant in healthcare and plays an extremely important role in wide scopes of medicinal services observing applications. Through determining the pattern of parameters that are observed, the character of the disease can be expected. Health specialists and technicians have developed a great system with low-cost healthcare monitoring for people suffering from many diseases using common techniques such as wearable devices, wireless channels, and other remote devices. Network-related sensors, either worn on the body or in living environments, collect rich information to assess the physical and mental state of the patient. This work focuses on scanning the existing e-health (electronic healthcare) monitoring system using integrated systems. The main goal of the e-health monitoring system is to offer the patient a prescription automatically according to his or her condition. The doctor can check patient health continuously without physical interaction. The study aims to explore the uses of IoT applications in the medical sector, and its role in raising the level of medical care services in health institutions. Also, the study will address the applications of IoT in the medical field and the extent of its use to enrich traditional methods in various health fields and to determine the extent of the ability of IoT to improve the quality of health services provided. The study relies on a descriptive research approach through an analysis of the literature published in this field. The results of the study refer to the application of IoT in the health institutions, it will help to obtain accurate diagnoses for patients, which will reflect on the quality of service provided to the patient. It will also reduce periodic patient reviews to the hospital by relying on IoT applications for remote diagnosis. Also, an application in health institutions will contribute to providing data correct for the diseases that patients suffer from, and hence employing them in preparing scientific research to obtain more accurate results. This paper introduces the review of the Internet-based healthcare monitoring system (HCMS) and the general outlines on opportunities and challenges of the patient's Internet-based patient health monitoring system. [ABSTRACT FROM AUTHOR]

• IoT supportive technologies in IoT-based OSA diagnosis are summarized. • The researches of AI usage in IoT-based OSA diagnosis are discussed. • A new terminology "Internet of intelligent Things" is introduced. Obstructive Sleep Apnea (OSA) syndrome is one of the most widespread diseases that difficult to be detected and remedied. In particular, the examination of OSA by using the traditional Polysomnography (PSG) is one of formidable complexity as it requires full observation in a laboratory overnight. Meanwhile, the number of available laboratories and beds is minimal comparing to the number of OSA patients. What's more, the unusual environment and restricted mobility of patients may result in deficient diagnosis results. The Internet of Things (IoT) is the most appropriate solution for the previous diagnosis obstacles by allowing doctors to synchronize patient status. Besides, several studies have been introduced to consolidate the performance of IoT interoperability via the fusion with Artificial Intelligence (AI) resulting in the Internet of Intelligent Things (IoIT). This paper presents a literature survey about the intensification of IoT technologies for smart monitoring of sleep quality and OSA diagnosis. Mainly, the most recent enabling IoT and support technologies such as (smart devices, fog computing, cloud, big data, and machine learning) are covered via the discussion of more recent works of literature published from 2016 to 2019. Also, the roles of AI in optimizing the efficiency of OSA smart diagnosis are presented. Besides, a new comprehensive IoIT optimization framework is presented which employing AI for optimizing the performance of intelligent diagnosis of OSA. Finally, the open issues and challenges in this field are argued. This paper is, therefore, a major contributor to the compilation of all IoT innovative and efficient AI methods that improving the quality of OSA diagnosis. [ABSTRACT FROM AUTHOR]

Copyright of Petroleum Refinery Engineering is the property of Petroleum Refinery Engineering Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Abstract Background Remote assistance for burns by medical experts can support nurses and general physicians in emergency care with diagnostic and management advice. Previous studies indicate a high diagnostic accuracy based on images viewed on a computer screen, but whether image-based analysis by experts using handheld devices is accurate remains to be determined. Method A review of patient data from eight emergency centres in the Western Cape, South Africa, revealed 10 typical cases of burns commonly seen in children and adults. A web-based questionnaire was created with 51 images of burns representing those cases. Burns specialists from two countries (South Africa and Sweden (n = 8 and 7 respectively)) and emergency medicine specialists from South Africa (n = 11) were contacted by email and asked to assess each burn’s total body surface area (TBSA) and depth using a smartphone or tablet. The accuracy and inter-rater reliability of the assessments were measured using intraclass correlation coefficients (ICC), both for all cases aggregated and for paediatric and adult burn cases separately. Eight participants repeated the questionnaire on a computer and intra-rater reliability was calculated. Results The assessments of TBSA are of high accuracy all specialists aggregated (ICC = 0.82 overall and 0.81 for both child and adult cases separately) and remain high for all three participant groups separately. The burn depth assessments have low accuracy all specialists aggregated, with ICCs of 0.53 overall, 0.61 for child and 0.46 for adult cases. The most accurate assessments of depth are among South African burns specialists (reaching acceptable for child cases); the other two groups’ ICCs are low in all instances. Computer-based assessments were similar to those made on handheld devices. Conclusion As was the case for computer-based studies, burns images viewed on handheld devices may be a suitable means of seeking expert advice even with limited additional information when it comes to burn size but less so in the case of burn depth. Familiarity with the type of cases presented could facilitate image-based diagnosis of depth.

In view of the actual problems existing in life-cycle health monitoring and diagnosis of large complex equipment, the machine-learning algorithm is applied to data mining of the equipment operation big data, the expert knowledge base is established, the diagnosis rules related to the fault are obtained, the intelligent online monitoring and remote diagnosis of the equipment health condition are realised. The system uses uncertain fault prediction method and hybrid intelligent algorithm to discover the hierarchical association between operation feature big data and operation faults, the feature extraction of operation faults, and the intelligent diagnosis of operation faults. It effectively improved the sensitivity, robustness, and accuracy of monitoring and diagnosis. In the cloud service platform based on the Internet of things, the system realises the intelligent fault prediction and diagnosis, establishes a proactive maintenance system, improves the production efficiency, and ensures the production safety. [ABSTRACT FROM AUTHOR]

Several pathologies can alter the way people walk, i.e., their gait. Gait analysis can be used to detect such alterations and, therefore, help diagnose certain pathologies or assess people’s health and recovery. Simple vision-based systems have a considerable potential in this area, as they allow the capture of gait in unconstrained environments, such as at home or in a clinic, while the required computations can be done remotely. State-of-the-art vision-based systems for gait analysis use deep learning strategies, thus requiring a large amount of data for training. However, to the best of our knowledge, the largest publicly available pathological gait dataset contains only 10 subjects, simulating five types of gait. This paper presents a new dataset, GAIT-IT, captured from 21 subjects simulating five types of gait, at two severity levels. The dataset is recorded in a professional studio, making the sequences free of background camouflage, variations in illumination and other visual artifacts. The dataset is used to train a novel automatic gait analysis system. Compared to the state-of-the-art, the proposed system achieves a drastic reduction in the number of trainable parameters, memory requirements and execution times, while the classification accuracy is on par with the state-of-the-art. Recognizing the importance of remote healthcare, the proposed automatic gait analysis system is integrated with a prototype web application. This prototype is presently hosted in a private network, and after further tests and development it will allow people to upload a video of them walking and execute a web service that classifies their gait. The web application has a user-friendly interface usable by healthcare professionals or by laypersons. The application also makes an association between the identified type of gait and potential gait pathologies that exhibit the identified characteristics.

The article describes a complex of non-contact methods for remote diagnosis of high-voltage insulators as well as the two-channel method for remote diagnostics of the operating state of high-voltage insulators, based on the registration of partial discharges by electromagnetic and acoustic sensors. The presented device allows visual inspection and searches for faulty high-voltage equipment and a remote non-contact method of recording high-intensity electric fields of industrial frequency and their spatial distribution based on the electro-optical effect. The scheme of using the system for monitoring and diagnosing the technical condition of high-voltage support insulators of open switchgear is described. The results of experimental studies confirm the possibility of industrial applicability of the proposed method for non-contact remote diagnostics of the state of high-voltage insulators under operating voltage.