[A survey on the application of convolutional neural networks in the diagnosis of occupational pneumoconiosis].

Pneumoconiosis ranks first among the newly-emerged occupational diseases reported annually in China, and imaging diagnosis is still one of the main clinical diagnostic methods. However, manual reading of films requires high level of doctors, and it is difficult to discriminate the staged diagnosis of pneumoconiosis imaging, and due to the influence of uneven distribution of medical resources and other factors, it is easy to lead to misdiagnosis and omission of diagnosis in primary healthcare institutions. Computer-aided diagnosis system can realize rapid screening of pneumoconiosis in order to assist clinicians in identification and diagnosis, and improve diagnostic efficacy. As an important branch of deep learning, convolutional neural network (CNN) is good at dealing with various visual tasks such as image segmentation, image classification, target detection and so on because of its characteristics of local association and weight sharing, and has been widely used in the field of computer-aided diagnosis of pneumoconiosis in recent years. This paper was categorized into three parts according to the main applications of CNNs (VGG, U-Net, ResNet, DenseNet, CheXNet, Inception-V3, and ShuffleNet) in the imaging diagnosis of pneumoconiosis, including CNNs in pneumoconiosis screening diagnosis, CNNs in staging diagnosis of pneumoconiosis, and CNNs in segmentation of pneumoconiosis foci to conduct a literature review. It aims to summarize the methods, advantages and disadvantages, and optimization ideas of CNN applied to the images of pneumoconiosis, and to provide a reference for the research direction of further development of computer-aided diagnosis of pneumoconiosis.

Computer-aided autism diagnosis using visual attention models and eye-tracking: replication and improvement proposal.

BACKGROUND: Autism Spectrum Disorder (ASD) diagnosis can be aided by approaches based on eye-tracking signals. Recently, the feasibility of building Visual Attention Models (VAMs) from features extracted from visual stimuli and their use for classifying cases and controls has been demonstrated using Neural Networks and Support Vector Machines. The present work has three aims: 1) to evaluate whether the trained classifier from the previous study was generalist enough to classify new samples with a new stimulus; 2) to replicate the previously approach to train a new classifier with a new dataset; 3) to evaluate the performance of classifiers obtained by a new classification algorithm (Random Forest) using the previous and the current datasets. METHODS: The previously approach was replicated with a new stimulus and new sample, 44 from the Typical Development group and 33 from the ASD group. After the replication, Random Forest classifier was tested to substitute Neural Networks algorithm. RESULTS: The test with the trained classifier reached an AUC of 0.56, suggesting that the trained classifier requires retraining of the VAMs when changing the stimulus. The replication results reached an AUC of 0.71, indicating the potential of generalization of the approach for aiding ASD diagnosis, as long as the stimulus is similar to the originally proposed. The results achieved with Random Forest were superior to those achieved with the original approach, with an average AUC of 0.95 for the previous dataset and 0.74 for the new dataset. CONCLUSION: In summary, the results of the replication experiment were satisfactory, which suggests the robustness of the approach and the VAM-based approaches feasibility to aid in ASD diagnosis. The proposed method change improved the classification performance. Some limitations are discussed and additional studies are encouraged to test other conditions and scenarios.

Benefits and challenges in implementation of artificial intelligence in colonoscopy: World Endoscopy Organization position statement.

The number of artificial intelligence (AI) tools for colonoscopy on the market is increasing with supporting clinical evidence. Nevertheless, their implementation is not going smoothly for a variety of reasons, including lack of data on clinical benefits and cost-effectiveness, lack of trustworthy guidelines, uncertain indications, and cost for implementation. To address this issue and better guide practitioners, the World Endoscopy Organization (WEO) has provided its perspective about the status of AI in colonoscopy as the position statement. WEO Position Statement: Statement 1.1: Computer-aided detection (CADe) for colorectal polyps is likely to improve colonoscopy effectiveness by reducing adenoma miss rates and thus increase adenoma detection; Statement 1.2: In the short term, use of CADe is likely to increase health-care costs by detecting more adenomas; Statement 1.3: In the long term, the increased cost by CADe could be balanced by savings in costs related to cancer treatment (surgery, chemotherapy, palliative care) due to CADe-related cancer prevention; Statement 1.4: Health-care delivery systems and authorities should evaluate the cost-effectiveness of CADe to support its use in clinical practice; Statement 2.1: Computer-aided diagnosis (CADx) for diminutive polyps (≤5 mm), when it has sufficient accuracy, is expected to reduce health-care costs by reducing polypectomies, pathological examinations, or both; Statement 2.2: Health-care delivery systems and authorities should evaluate the cost-effectiveness of CADx to support its use in clinical practice; Statement 3: We recommend that a broad range of high-quality cost-effectiveness research should be undertaken to understand whether AI implementation benefits populations and societies in different health-care systems.

Application of Artificial Intelligence to Gastroenterology and Hepatology.

Since 2010, substantial progress has been made in artificial intelligence (AI) and its application to medicine. AI is explored in gastroenterology for endoscopic analysis of lesions, in detection of cancer, and to facilitate the analysis of inflammatory lesions or gastrointestinal bleeding during wireless capsule endoscopy. AI is also tested to assess liver fibrosis and to differentiate patients with pancreatic cancer from those with pancreatitis. AI might also be used to establish prognoses of patients or predict their response to treatments, based on multiple factors. We review the ways in which AI may help physicians make a diagnosis or establish a prognosis and discuss its limitations, knowing that further randomized controlled studies will be required before the approval of AI techniques by the health authorities.

Open access image repositories: high-quality data to enable machine learning research.

Originally motivated by the need for research reproducibility and data reuse, large-scale, open access information repositories have become key resources for training and testing of advanced machine learning applications in biomedical and clinical research. To be of value, such repositories must provide large, high-quality data sets, where quality is defined as minimising variance due to data collection protocols and data misrepresentations. Curation is the key to quality. We have constructed a large public access image repository, The Cancer Imaging Archive, dedicated to the promotion of open science to advance the global effort to diagnose and treat cancer. Drawing on this experience and our experience in applying machine learning techniques to the analysis of radiology and pathology image data, we will review the requirements placed on such information repositories by state-of-the-art machine learning applications and how these requirements can be met.

Tracking cognitive impairment in multiple sclerosis using the Brain on Track test: a validation study.

BACKGROUND: The accurate and regular monitoring cognitive performance in multiple sclerosis (MS) patients is critical to develop new prevention and management strategies for cognitive impairment (CI). The Brain on Track (BoT) test is a self-administered web-based tool developed for cognitive screening and monitoring. The objective of this study was to validate the use of the BoT in MS, by assessing its ability to distinguish between MS patients and matched controls, as well as detect CI among MS patients, by analysing its correlation with standard cognitive tests and its reliability and learning effects in repeatable use. METHODS: The BoT was applied in 30 patients with MS consecutively selected and 30 age- and education-matched controls, first in a hospital clinic, under supervision, and then 1 week later from home. After these first two trials, MS patients repeated the test from home every 4 weeks for 3 months. A standard neuropsychological battery was also applied to MS patients at baseline. RESULTS: The Cronbach's alpha was 0.89. Test scores were significantly different between MS patients and controls (Cohen's d = 0.87; p < 0.01). Among MS patients, scores were significantly lower in those with CI documented in the standard neuropsychological battery than in their cognitively preserved counterparts (Cohen's d = 2.0; p < 0.001). The BoT scores presented a good correlation with standard neuropsychological tests, particularly for information processing speed. Regarding test-retest reliability, 10/11 subtests presented two-way mixed single intraclass consistency correlation coefficients > 0.70. CONCLUSION: The BoT showed good neuropsychological parameters in MS patients, endorsing the use of self-administered computerized tests in this setting.

Artificial intelligence and colonoscopy: Current status and future perspectives.

BACKGROUND AND AIM: Application of artificial intelligence in medicine is now attracting substantial attention. In the field of gastrointestinal endoscopy, computer-aided diagnosis (CAD) for colonoscopy is the most investigated area, although it is still in the preclinical phase. Because colonoscopy is carried out by humans, it is inherently an imperfect procedure. CAD assistance is expected to improve its quality regarding automated polyp detection and characterization (i.e. predicting the polyp's pathology). It could help prevent endoscopists from missing polyps as well as provide a precise optical diagnosis for those detected. Ultimately, these functions that CAD provides could produce a higher adenoma detection rate and reduce the cost of polypectomy for hyperplastic polyps. METHODS AND RESULTS: Currently, research on automated polyp detection has been limited to experimental assessments using an algorithm based on ex vivo videos or static images. Performance for clinical use was reported to have >90% sensitivity with acceptable specificity. In contrast, research on automated polyp characterization seems to surpass that for polyp detection. Prospective studies of in vivo use of artificial intelligence technologies have been reported by several groups, some of which showed a >90% negative predictive value for differentiating diminutive (≤5 mm) rectosigmoid adenomas, which exceeded the threshold for optical biopsy. CONCLUSION: We introduce the potential of using CAD for colonoscopy and describe the most recent conditions for regulatory approval for artificial intelligence-assisted medical devices.

Effect of a clinical evidence technology on patient skin disease outcomes in primary care: a cluster-randomized controlled trial.

OBJECTIVE: Providers' use of clinical evidence technologies (CETs) improves their diagnosis and treatment decisions. Despite these benefits, few studies have evaluated the impact of CETs on patient outcomes. The investigators evaluated the effect of one CET, VisualDx, on skin problem outcomes in primary care. METHODS: A cluster-randomized controlled pragmatic trial was conducted in outpatient clinics at an academic medical center in the northeastern United States. Participants were primary care providers (PCPs) and their adult patients seen for skin problems. The intervention was VisualDx, as used by PCPs. Outcomes were patient-reported time from index clinic visit to problem resolution, and the number of follow-up visits to any provider for the same problem. PCPs who were randomly assigned to the intervention agreed to use VisualDx as their primary evidence source for skin problems. Control group PCPs agreed not to use VisualDx. Investigators collected outcome data from patients by phone at thirty-day intervals. Cox proportional hazards models assessed time to resolution. Wilcoxon-rank sum tests and logistic regression compared the need for return appointments. RESULTS: Thirty-two PCPs and 433 patients participated. In proportional hazards modelling adjusted for provider clusters, the time from index visit to skin problem resolution was similar in both groups (hazard ratio=0.92; 95% confidence interval [CI]=0.70, 1.21; p=0.54). Patient follow-up appointments did not differ significantly between groups (odds ratio=1.26; CI=0.94, 1.70; p=0.29). CONCLUSION: This pragmatic trial tested the effectiveness of VisualDx on patient-reported skin disease outcomes in a generalizable clinical setting. There was no difference in skin problem resolution or number of follow-up visits when PCPs used VisualDx.

Imaging Examination and Quantitative Detection and Analysis of Gastrointestinal Diseases Based on Data Mining Technology.

The medical image storage and transmission system completes the collection, storage, management, diagnosis and information processing of digital medical image information generated from digital medical devices, accumulates a large amount of data resources, and uses these valuable data resources to extract corresponding diseases. Diagnostic rules that help improve the accuracy of clinical disease diagnosis have always been the subject of medical research and management. Gastrointestinal diseases are common high-risk digestive diseases. This paper studies the imaging detection and quantitative detection and analysis of gastrointestinal diseases based on data mining, aiming to improve the accuracy of doctors' clinical diagnosis, reduce the misdiagnosis and misdiagnosis of patients' diseases, and reduce the burden on patients. With the high computing speed and computational accuracy of the computer, combined with the flexible analysis and judgment ability of the human body, the doctor can help the semi-structured and unstructured diagnosis problems. Experiments demonstrate the effectiveness and robustness of the proposed method.

Computerized Cognitive Testing in Primary Care: A Qualitative Study.

Computerized cognitive assessment tools may facilitate early identification of dementia in the primary care setting. We investigated primary care physicians' (PCPs') views on advantages and disadvantages of computerized testing based on their experience with the Computer Assessment of Mild Cognitive Impairment (CAMCI). Over a 2-month period, 259 patients, 65 years and older, from the family practice of 13 PCPs completed the CAMCI. Twelve PCPs participated in an individual interview. Generally, PCPs felt that the relationship between them and their patients helped facilitate cognitive testing; however, they thought available paper tests were time consuming and not sufficiently informative. Despite concerns regarding elderly patients' computer literacy, PCPs noticed high completion rates and that their patients had generally positive experiences completing the CAMCI. PCPs appreciated the time-saving advantage of the CAMCI and the immediately generated report, but thought the report should be shortened to 1 page and that PCPs should receive training in its interpretation. Our results suggest that computerized cognitive tools such as the CAMCI can address PCPs' concerns with cognitive testing in their offices. Recommendations to improve the practicality of computerized testing in primary care were suggested.

[Computer based neurocognitive testing in audiology]. / Computerbasierte Testung neurokognitiver Aspekte im Rahmen der audiologischen Diagnostik.

INTRODUCTION: Due to the demographic changes neurocognition has become an important issue also in the field of hearing rehabilitation. BACKGROUND: The present study aimed to evaluate the feasibility of a neurocognitive test using computer based tasks with regard to the elderly with and without hearing loss and its practicability for the daily clinical ENT setting. PATIENTS: 171 patients of both genders with normal hearing or a profound hearing loss were enrolled in the study: 90 middleaged persons were between 50 and 64 years (57.0 ± 4.5 years) and 81 elderly persons 65 years and older (72.5 ± 5.4). METHOD: A set of computer-based neurocognitive tasks with only visual instructions covering attention, processing speed, short- and longterm memory as well as executive functions was applied. A presession under the supervision of a trained assistant was included. RESULTS: All patients were capable to complete the assessment by themselves regardless of age and hearing status, however the hearing impaired required 15 minutes more to finish the pretest and reported about a higher level of effort than normal hearing subjects (71 % versus 63 %). Interestingly 90 % of the older individuals claimed the test to fit with all ages, whereas 30 % of the middleaged participants remained skeptical (p = 0.02). CONCLUSION: The presented neurocognitive assessment might be a useful instrument which can be easily included into the daily clinical ENT. It may give important hints to the otolaryngologist in order to develop the most effective hearing rehabilitation strategy.

Two to one CRTD pacing: When the T wave and the P wave interact.

We presented a unique phenomenon of 2:1 cardiac resynchronization therapy pacing due to T wave oversensing. Ultimately, by utilizing a unique feature of integrated bipolar sensing, we succeeded to eliminate the T wave oversensing signals, and restore 1:1 CRTD pacing. Importantly, this feature enabled us to overcome the T wave oversensing issue, without the need to decrease the ventricular sensitivity, which could potentially interfere with ventricular arrhythmia detection and appropriate shock delivery when required.

Bone scan index: A new biomarker of bone metastasis in patients with prostate cancer.

Bone scintigraphy is one of the first-line imaging modalities for the screening and follow up of bone metastasis in patients with prostate cancer. The amount (%) of bone metastasis can be calculated using a bone scan index thanks to recent advances in quantitative bone scintigraphy. Since an artificial neural network was applied for hot-spot characterization and quantitation, the bone scan index has become a simple, reproducible and practical means of quantifying bone metastasis. The bone scan index is presently considered as an imaging biomarker of bone metastasis. The present article summarizes the principles and application of bone scan index using dedicated software (EXINI bone in Europe and North America; BONENAVI in Japan), and the advantages and cautions of using the bone scan index. The bone scan index could serve as a practical marker with which to monitor disease progression and treatment effects in multicenter studies, and to manage prostate and other types of cancer in the clinical setting.

A Digital Assessment of the Maxillary Deformity Correction in Infants With Bilateral Cleft Lip and Palate Using Computer-Aided Nasoalveolar Molding.

OBJECTIVES: To evaluate the maxillary alveolar repositioning of the infants with bilateral cleft lip and palate (BCLP) undergoing computer-aided nasoalveolar molding (CAD-NAM). METHODS: A total of 19 BCLP infants undergoing CAD-NAM were recruited as the treatment group, and 21 nonpresurgically treated BCLP patients served as controls. The upper alveolar morphology was measured and evaluated. Changes in all variables between pre- and post-CAD-NAM were compared. RESULTS: By the end of CAD-NAM, significant difference was found in the P-A, P'-A', and L-ideal midline (P < 0.01); in the sagittal dimensions, significant difference was found in the P-TT', P'-TT', I-TT', A-X, and A'-X' (P < 0.01), while in the vertical dimensions, significant difference was found in the alveolus height in the bilateral canine regions (P < 0.01). CONCLUSION: Computer-aided nasoalveolar molding can effectively reduce the cleft gap, correct the alveolar midline deviation, and retract the projection and outward rotation of the premaxilla segment, and normalize the contour of the alveolus.

[Secondary closed rhinoplasty in the patient presenting with post-injurious deformation of the external nose]. / Vtorichnaia zakrytaia rinoplastika u patsienta s posttravmaticheskoi deformatsiei naruzhnogo nosa.

The authors describe the process of the surgical treatment of a patient presenting with the displaced fracture of the nasal bones involving the left orbital wall. The correction was performed by means of secondary closed rhinoseptoplastic surgery. The special emphasis is laid on the importance of computer-assisted modeling for the planning and achievement of the favourable surgical outcome.

Deconstructing Chronic Low Back Pain in the Older Adult-Step by Step Evidence and Expert-Based Recommendations for Evaluation and Treatment: Part IX: Anxiety.

OBJECTIVE: As a part of a series of articles designed to deconstruct chronic low back pain (CLBP) in older adults, this article focuses on anxiety-a significant contributor of reduced health-related quality of life, increased use of medical services, and heightened disability in older adults with CLBP. METHODS: A modified Delphi technique was used to develop an algorithm for the screening and clinical care of older adults with CLBP and anxiety. A 4-member content expert panel and a nine-member primary care panel were involved in this iterative development process. Evidence underlying the recommendations is not strictly based on VA populations; therefore, the algorithm can be applied in both VHA and civilian settings. The illustrative clinical case was taken from one of the contributor's clinical practice. RESULTS: We present a treatment algorithm and supporting tables to be used by providers treating older adults who have anxiety and CLBP. A case of an older adult with anxiety and CLBP is provided to illustrate the approach to management. CONCLUSIONS: To promote early engagement in evidence-based treatments, providers should routinely evaluate anxiety in older adults with CLBP using a screening and treatment algorithm.

Assessing the Effects of Repetitive Transcranial Magnetic Stimulation on Cognition in Major Depressive Disorder Using Computerized Cognitive Testing.

OBJECTIVES: A range of different treatment approaches are available for depression; however, there is an ongoing concern about the cognitive impairment associated with many treatments. This study investigated the effect of treatment with repetitive transcranial magnetic stimulation (rTMS) on cognition in patients with major depressive disorder. Cognition before and after treatment was assessed using a computerized cognitive testing battery, which provided comprehensive assessment across a range of cognitive domains. This was a naturalistic study involving patients attending an outpatient clinical rTMS service. METHODS: A total of 63 patients with treatment-resistant depression completed the IntegNeuro cognitive test battery, a well-validated comprehensive computerized assessment tool before and after receiving 18 or 20 treatments of sequential bilateral rTMS. Change in the various cognitive domains was assessed, and analyses were undertaken to determine whether any change in cognition was associated with a change in rating of depression severity. RESULTS: There was a significant decrease in Hamilton Depression Rating Scale scores from baseline to posttreatment. There was no decline in performance on any of the cognitive tests. There were significant improvements in maze completion time and the number of errors in the maze task. However, these were accounted for by improvement in mood when change in depressive symptoms was included as a covariate. CONCLUSIONS: This open-label study provides further support for the efficacy and safety of rTMS as a treatment option for people with major depressive disorder in a naturalistic clinical setting. Using a comprehensive, robust computerized battery of cognitive tests, the current study indicated that there was no significant cognitive impairment associated with rTMS and that any improvements in cognitive functioning were associated with a reduction in depressive symptoms.

[Internet-based interventions in the treatment of mental disorders : Overview, quality criteria, perspectives]. / Internetbasierte Interventionen in der Behandlung psychischer Störungen : Überblick, Qualitätskriterien, Perspektiven.

BACKGROUND: Mental disorders are frequently not or only insufficiently treated. Internet-based interventions offer the potential of closing the existing gaps in the treatment of mental disorders; however, it is very difficult for patients and providers to choose from the numerous interventions available. OBJECTIVE: The aim of this study was to develop a set of quality criteria that can help patients and care providers to identify recommendable internet-based interventions. METHODS: A selective literature search was carried out and the existing evidence on internet-based interventions in the treatment of mental disorders was collated. A panel of experts then developed quality criteria based on existing models for the systematic assessment of telemedicine applications. RESULTS: Internet-based interventions are effective in the treatment of a broad range of mental disorders. The best evidence is available for depression and anxiety disorders. A set of criteria is proposed for the evaluation of available internet-based interventions using a checklist. These criteria have to be developed further with input from other stakeholders. DISCUSSION: When taking these quality criteria into account, evidence-based interventions available on the internet can make an important contribution to improvement of the care of patients with mental disorders.

THE INTERACTIVE AUTOMATIC SYNDROME DIAGNOSTIC PROGRAM OF DIGESTIVE SYSTEM DISEASES "ELECTRONIC POLICLINIC".

The aim of the study was to estimate clinical efficiency of the interactive automatic program of digestive system diseases diagnostics "Electronic policlinic". Material was presented by 22 patients with different gastroenterological diseases (duodenal ulcer, chronical gastritis, chronical pancreatitis) and the comparative group consisted of 20 healthy people. The plan of the research included the interactive questionnaire using diagnostic module digestive system diseases of the digestive system of the automated program "Electronic policlinic" (Certificate No. 2012614202 from 12.05.12) posted on the Internet (http://klinikcity.ru). For the purpose of verification of diagnosis patients underwent fibrogastroduodenoscopy, ultrasound examination of abdominal cavity organs, CT scan, sigmoidoscopy, colonoscopy, barium enema. As the result of the study there were showed that interactive automated system was able to reveal 85,7% of patients with chronical gastritis, duodenal ulcer and chronical pancreatitis and 75% of patients with colonopathy. The specify of diagnostic procedure was 80% in the first case and 100% in the second. Prevalence of digestive system diseases basic symptoms was studied too. The conclusion of the study demonstrated interactive questionnaire good ability in preliminary digestive problem patient examination procedure for individual diagnostic plan making.

Understanding and Confronting Our Mistakes: The Epidemiology of Error in Radiology and Strategies for Error Reduction.

Arriving at a medical diagnosis is a highly complex process that is extremely error prone. Missed or delayed diagnoses often lead to patient harm and missed opportunities for treatment. Since medical imaging is a major contributor to the overall diagnostic process, it is also a major potential source of diagnostic error. Although some diagnoses may be missed because of the technical or physical limitations of the imaging modality, including image resolution, intrinsic or extrinsic contrast, and signal-to-noise ratio, most missed radiologic diagnoses are attributable to image interpretation errors by radiologists. Radiologic interpretation cannot be mechanized or automated; it is a human enterprise based on complex psychophysiologic and cognitive processes and is itself subject to a wide variety of error types, including perceptual errors (those in which an important abnormality is simply not seen on the images) and cognitive errors (those in which the abnormality is visually detected but the meaning or importance of the finding is not correctly understood or appreciated). The overall prevalence of radiologists' errors in practice does not appear to have changed since it was first estimated in the 1960s. The authors review the epidemiology of errors in diagnostic radiology, including a recently proposed taxonomy of radiologists' errors, as well as research findings, in an attempt to elucidate possible underlying causes of these errors. The authors also propose strategies for error reduction in radiology. On the basis of current understanding, specific suggestions are offered as to how radiologists can improve their performance in practice.