bims-arihec Biomed News
on Artificial intelligence in healthcare
Issue of 2020–03–29
fiveteen papers selected by
Céline Bélanger, Cogniges Inc.



  1. Prog Cardiovasc Dis. 2020 Mar 19. pii: S0033-0620(20)30060-8. [Epub ahead of print]
      There has been a tidal wave of recent interest in artificial intelligence (AI), machine learning and deep learning approaches in cardiovascular (CV) medicine. In the era of modern medicine, AI and electronic health records hold the promise to improve the understanding of disease conditions and bring a personalized approach to CV care. The field of CV imaging (CVI), incorporating echocardiography, cardiac computed tomography, cardiac magnetic resonance imaging and nuclear imaging, with sophisticated imaging techniques and high volumes of imaging data, is primed to be at the forefront of the revolution in precision cardiology. This review provides a contemporary overview of the CVI imaging applications of AI, including a critique of the strengths and potential limitations of deep learning approaches.
    Keywords:  Artificial intelligence; Cardiac computed tomography; Cardiac magnetic resonance; Deep learning; Echocardiography; Machine learning; Nuclear cardiac imaging
    DOI:  https://doi.org/10.1016/j.pcad.2020.03.003
  2. Acta Inform Med. 2019 Dec;27(5): 327-332
       Introduction: Diabetic retinopathy (DR) is the most common diabetic eye disease worldwide and a leading cause of blindness. The number of diabetic patients will increase to 552 million by 2034, as per the International Diabetes Federation (IDF).
    Aim: With advances in computer science techniques, such as artificial intelligence (AI) and deep learning (DL), opportunities for the detection of DR at the early stages have increased. This increase means that the chances of recovery will increase and the possibility of vision loss in patients will be reduced in the future.
    Methods: In this paper, deep transfer learning models for medical DR detection were investigated. The DL models were trained and tested over the Asia Pacific Tele-Ophthalmology Society (APTOS) 2019 dataset. According to literature surveys, this research is considered one the first studies to use of the APTOS 2019 dataset, as it was freshly published in the second quarter of 2019. The selected deep transfer models in this research were AlexNet, Res-Net18, SqueezeNet, GoogleNet, VGG16, and VGG19. These models were selected, as they consist of a small number of layers when compared to larger models, such as DenseNet and InceptionResNet. Data augmentation techniques were used to render the models more robust and to overcome the overfitting problem.
    Results: The testing accuracy and performance metrics, such as the precision, recall, and F1 score, were calculated to prove the robustness of the selected models. The AlexNet model achieved the highest testing accuracy at 97.9%. In addition, the achieved performance metrics strengthened our achieved results. Moreover, AlexNet has a minimum number of layers, which decreases the training time and the computational complexity.
    Keywords:  Convolutional Neural Network; Deep Transfer Learning; Diabetic Retinopathy; Machine Learning
    DOI:  https://doi.org/10.5455/aim.2019.27.327-332
  3. JAMA Ophthalmol. 2020 Mar 26.
       Importance: Evaluating corneal morphologic characteristics with corneal tomographic scans before refractive surgery is necessary to exclude patients with at-risk corneas and keratoconus. In previous studies, researchers performed screening with machine learning methods based on specific corneal parameters. To date, a deep learning algorithm has not been used in combination with corneal tomographic scans.
    Objective: To examine the use of a deep learning model in the screening of candidates for refractive surgery.
    Design, Setting, and Participants: A diagnostic, cross-sectional study was conducted at the Zhongshan Ophthalmic Center, Guangzhou, China, with examination dates extending from July 18, 2016, to March 29, 2019. The investigation was performed from July 2, 2018, to June 28, 2019. Participants included 1385 patients; 6465 corneal tomographic images were used to generate the artificial intelligence (AI) model. The Pentacam HR system was used for data collection.
    Interventions: The deidentified images were analyzed by ophthalmologists and the AI model.
    Main Outcomes and Measures: The performance of the AI classification system.
    Results: A classification system centered on the AI model Pentacam InceptionResNetV2 Screening System (PIRSS) was developed for screening potential candidates for refractive surgery. The model achieved an overall detection accuracy of 94.7% (95% CI, 93.3%-95.8%) on the validation data set. Moreover, on the independent test data set, the PIRSS model achieved an overall detection accuracy of 95% (95% CI, 88.8%-97.8%), which was comparable with that of senior ophthalmologists who are refractive surgeons (92.8%; 95% CI, 91.2%-94.4%) (P = .72). In distinguishing corneas with contraindications for refractive surgery, the PIRSS model performed better than the classifiers (95% vs 81%; P < .001) in the Pentacam HR system on an Asian patient database.
    Conclusions and Relevance: PIRSS appears to be useful in classifying images to provide corneal information and preliminarily identify at-risk corneas. PIRSS may provide guidance to refractive surgeons in screening candidates for refractive surgery as well as for generalized clinical application for Asian patients, but its use needs to be confirmed in other populations.
    DOI:  https://doi.org/10.1001/jamaophthalmol.2020.0507
  4. BMJ. 2020 Mar 25. 368 m689
       OBJECTIVE: To systematically examine the design, reporting standards, risk of bias, and claims of studies comparing the performance of diagnostic deep learning algorithms for medical imaging with that of expert clinicians.
    DESIGN: Systematic review.
    DATA SOURCES: Medline, Embase, Cochrane Central Register of Controlled Trials, and the World Health Organization trial registry from 2010 to June 2019.
    ELIGIBILITY CRITERIA FOR SELECTING STUDIES: Randomised trial registrations and non-randomised studies comparing the performance of a deep learning algorithm in medical imaging with a contemporary group of one or more expert clinicians. Medical imaging has seen a growing interest in deep learning research. The main distinguishing feature of convolutional neural networks (CNNs) in deep learning is that when CNNs are fed with raw data, they develop their own representations needed for pattern recognition. The algorithm learns for itself the features of an image that are important for classification rather than being told by humans which features to use. The selected studies aimed to use medical imaging for predicting absolute risk of existing disease or classification into diagnostic groups (eg, disease or non-disease). For example, raw chest radiographs tagged with a label such as pneumothorax or no pneumothorax and the CNN learning which pixel patterns suggest pneumothorax.
    REVIEW METHODS: Adherence to reporting standards was assessed by using CONSORT (consolidated standards of reporting trials) for randomised studies and TRIPOD (transparent reporting of a multivariable prediction model for individual prognosis or diagnosis) for non-randomised studies. Risk of bias was assessed by using the Cochrane risk of bias tool for randomised studies and PROBAST (prediction model risk of bias assessment tool) for non-randomised studies.
    RESULTS: Only 10 records were found for deep learning randomised clinical trials, two of which have been published (with low risk of bias, except for lack of blinding, and high adherence to reporting standards) and eight are ongoing. Of 81 non-randomised clinical trials identified, only nine were prospective and just six were tested in a real world clinical setting. The median number of experts in the comparator group was only four (interquartile range 2-9). Full access to all datasets and code was severely limited (unavailable in 95% and 93% of studies, respectively). The overall risk of bias was high in 58 of 81 studies and adherence to reporting standards was suboptimal (<50% adherence for 12 of 29 TRIPOD items). 61 of 81 studies stated in their abstract that performance of artificial intelligence was at least comparable to (or better than) that of clinicians. Only 31 of 81 studies (38%) stated that further prospective studies or trials were required.
    CONCLUSIONS: Few prospective deep learning studies and randomised trials exist in medical imaging. Most non-randomised trials are not prospective, are at high risk of bias, and deviate from existing reporting standards. Data and code availability are lacking in most studies, and human comparator groups are often small. Future studies should diminish risk of bias, enhance real world clinical relevance, improve reporting and transparency, and appropriately temper conclusions.
    STUDY REGISTRATION: PROSPERO CRD42019123605.
    DOI:  https://doi.org/10.1136/bmj.m689
  5. Curr Opin Nephrol Hypertens. 2020 Mar 19.
       PURPOSE OF REVIEW: Successful integration of artificial intelligence into extant clinical workflows is contingent upon a number of factors including clinician comprehension and interpretation of computer vision. This article discusses how image analysis and machine learning have enabled comprehensive characterization of kidney morphology for development of automated diagnostic and prognostic renal pathology applications.
    RECENT FINDINGS: The primordial digital pathology informatics work employed classical image analysis and machine learning to prognosticate renal disease. Although this classical approach demonstrated tremendous potential, subsequent advancements in hardware technology rendered artificial neural networks '(ANNs) the method of choice for machine vision in computational pathology'. Offering rapid and reproducible detection, characterization and classification of kidney morphology, ANNs have facilitated the development of diagnostic and prognostic applications. In addition, modern machine learning with ANNs has revealed novel biomarkers in kidney disease, demonstrating the potential for machine vision to elucidate novel pathologic mechanisms beyond extant clinical knowledge.
    SUMMARY: Despite the revolutionary developments potentiated by modern machine learning, several challenges remain, including data quality control and curation, image annotation and ontology, integration of multimodal data and interpretation of machine vision or 'opening the black box'. Resolution of these challenges will not only revolutionize diagnostic pathology but also pave the way for precision medicine and integration of artificial intelligence in the process of care.
    DOI:  https://doi.org/10.1097/MNH.0000000000000598
  6. Crit Care Med. 2020 Apr;48(4): e285-e289
       OBJECTIVES: As the performance of a conventional track and trigger system in a rapid response system has been unsatisfactory, we developed and implemented an artificial intelligence for predicting in-hospital cardiac arrest, denoted the deep learning-based early warning system. The purpose of this study was to compare the performance of an artificial intelligence-based early warning system with that of conventional methods in a real hospital situation.
    DESIGN: Retrospective cohort study.
    SETTING: This study was conducted at a hospital in which deep learning-based early warning system was implemented.
    PATIENTS: We reviewed the records of adult patients who were admitted to the general ward of our hospital from April 2018 to March 2019.
    INTERVENTIONS: The study population included 8,039 adult patients. A total 83 events of deterioration occurred during the study period. The outcome was events of deterioration, defined as cardiac arrest and unexpected ICU admission. We defined a true alarm as an alarm occurring within 0.5-24 hours before a deteriorating event.
    MEASUREMENTS AND MAIN RESULTS: We used the area under the receiver operating characteristic curve, area under the precision-recall curve, number needed to examine, and mean alarm count per day as comparative measures. The deep learning-based early warning system (area under the receiver operating characteristic curve, 0.865; area under the precision-recall curve, 0.066) outperformed the modified early warning score (area under the receiver operating characteristic curve, 0.682; area under the precision-recall curve, 0.010) and reduced the number needed to examine and mean alarm count per day by 69.2% and 59.6%, respectively. At the same specificity, deep learning-based early warning system had up to 257% higher sensitivity than conventional methods.
    CONCLUSIONS: The developed artificial intelligence based on deep-learning, deep learning-based early warning system, accurately predicted deterioration of patients in a general ward and outperformed conventional methods. This study showed the potential and effectiveness of artificial intelligence in an rapid response system, which can be applied together with electronic health records. This will be a useful method to identify patients with deterioration and help with precise decision-making in daily practice.
    DOI:  https://doi.org/10.1097/CCM.0000000000004236
  7. Phys Med Biol. 2020 Mar 24.
      Deep convolutional neural network (DCNN), now popularly called artificial intelligence (AI), has shown the potential to improve over previous computer-assisted tools in medical imaging developed in the past decades. A DCNN has millions of free parameters that need to be trained, but the training sample set is limited in size for most medical imaging tasks so that transfer learning is typically used. Automatic data mining may be an efficient way to enlarge the collected data set but the data can be noisy such as incorrect labels or even a wrong type of images. In this work we studied the generalization error of DCNN with transfer learning in medical imaging for the task of classifying malignant and benign masses on mammograms. With a finite available data set, we simulated a training set containing corrupted data or noisy labels. The balance between learning and memorization of the DCNN was manipulated by varying the proportion of corrupted data in the training set. The generalization error of DCNN was analyzed by the area under the receiver operating characteristic curve for the training and test sets and the weight changes after transfer learning. The study demonstrates that the transfer learning strategy of DCNN for such tasks needs to be designed properly, taking into consideration the constraints of the available training set having limited size and quality for the classification task at hand, to minimize memorization and improve generalizability.
    Keywords:  artificial intelligence; breast cancer; deep convolutional neural network; generalization error; mammography
    DOI:  https://doi.org/10.1088/1361-6560/ab82e8
  8. J Med Toxicol. 2020 Mar 25.
      Artificial intelligence (AI) refers to machines or software that process information and interact with the world as understanding beings. Examples of AI in medicine include the automated reading of chest X-rays and the detection of heart dysrhythmias from wearables. A key promise of AI is its potential to apply logical reasoning at the scale of data too vast for the human mind to comprehend. This scaling up of logical reasoning may allow clinicians to bring the entire breadth of current medical knowledge to bear on each patient in real time. It may also unearth otherwise unreachable knowledge in the attempt to integrate knowledge and research across disciplines. In this review, we discuss two complementary aspects of artificial intelligence: deep learning and knowledge representation. Deep learning recognizes and predicts patterns. Knowledge representation structures and interprets those patterns or predictions. We frame this review around how deep learning and knowledge representation might expand the reach of Poison Control Centers and enhance syndromic surveillance from social media.
    Keywords:  Artificial intelligence; Big data; Knowledge representation; Machine learning
    DOI:  https://doi.org/10.1007/s13181-020-00769-5
  9. Adv Clin Exp Med. 2020 Mar 24.
      Innovative computer techniques are starting to be employed not only in academic research, but also in commercial production, finding use in many areas of dentistry. This is conducive to the digitalization of dentistry and its increasing treatment and diagnostic demands. In many areas of dentistry, such as orthodontics and maxillofacial surgery, but also periodontics or prosthetics, only a correct diagnosis ensures the correct treatment plan, which is the only way to restore the patient's health. The diagnosis and treatment plan is based on the specialist's knowledge, but is subject to a large, multi-factorial risk of error. Therefore, the introduction of multiparametric pattern recognition methods (statistics, machine learning and artificial intelligence (AI)) is a great hope for both the physicians and the patients. However, the general use of clinical decision support systems (CDSS) in a dental clinic is not yet realistic and requires work in many aspects - methodical, technological and business. The article presents a review of the latest attempts to apply AI, such as CDSS or genetic algorithms (GAs) in research and clinical dentistry, taking under consideration all of the main dental specialties. Work on the introduction of public CDSS has been continued for years. The article presents the latest achievements in this field, analyzing their real-life application and credibility.
    Keywords:  CDSS; artificial intelligence; clinical decision support systems; dentistry; machine learning
    DOI:  https://doi.org/10.17219/acem/115083
  10. Brain Sci. 2020 Mar 23. pii: E183. [Epub ahead of print]10(3):
      Alzheimer's disease (AD) imposes a considerable burden on those diagnosed. Faced with a neurodegenerative decline for which there is no effective cure or prevention method, sufferers of the disease are subject to judgement, both self-imposed and otherwise, that can have a great deal of effect on their lives. The burden of this stigma is more than just psychological, as reluctance to face an AD diagnosis can lead people to avoid early diagnosis, treatment, and research opportunities that may be beneficial to them, and that may help progress towards fighting AD and its progression. In this review, we discuss how recent advents in information technology may be employed to help fight this stigma. Using artificial intelligence (AI) technologies, specifically natural language processing (NLP), to classify the sentiment and tone of texts, such as those of online posts on various social media sites, has proven to be an effective tool for assessing the opinions of the general public on certain topics. These tools can be used to analyze the public stigma surrounding AD. Additionally, there is much concern among individuals that an AD diagnosis, or evidence of pre-clinical AD such as a biomarker or imaging test results, may wind up unintentionally disclosed to an entity that may discriminate against them. The lackluster security record of many medical institutions justifies this fear to an extent. Adopting more secure and decentralized methods of data transfer and storage, and giving patients enhanced ability to control their own data, such as a blockchain-based method, may help to alleviate some of these fears.
    Keywords:  Alzheimer’s disease; artificial intelligence; blockchain; natural language processing; sentiment analysis; social media; stigma
    DOI:  https://doi.org/10.3390/brainsci10030183
  11. Curr Treat Options Infect Dis. 2020 Mar 19. 1-10
       Purpose of Review: Artificial intelligence (AI) offers huge potential in infection prevention and control (IPC). We explore its potential IPC benefits in epidemiology, laboratory infection diagnosis, and hand hygiene.
    Recent Findings: AI has the potential to detect transmission events during outbreaks or predict high-risk patients, enabling development of tailored IPC interventions. AI offers opportunities to enhance diagnostics with objective pattern recognition, standardize the diagnosis of infections with IPC implications, and facilitate the dissemination of IPC expertise. AI hand hygiene applications can deliver behavior change, though it requires further evaluation in different clinical settings. However, staff can become dependent on automatic reminders, and performance returns to baseline if feedback is removed.
    Summary: Advantages for IPC include speed, consistency, and capability of handling infinitely large datasets. However, many challenges remain; improving the availability of high-quality representative datasets and consideration of biases within preexisting databases are important challenges for future developments. AI in itself will not improve IPC; this requires culture and behavior change. Most studies to date assess performance retrospectively so there is a need for prospective evaluation in the real-life, often chaotic, clinical setting. Close collaboration with IPC experts to interpret outputs and ensure clinical relevance is essential.
    Keywords:  Artificial intelligence; Epidemiology; Hand hygiene; Infection diagnosis; Infection prevention and control; Machine learning
    DOI:  https://doi.org/10.1007/s40506-020-00216-7
  12. Gen Psychiatr. 2020 ;33(2): e100197
      Mental health questions can be tackled through machine learning (ML) techniques. Apart from the two ML methods we introduced in our previous paper, we discuss two more advanced ML approaches in this paper: support vector machines and artificial neural networks. To illustrate how these ML methods have been employed in mental health, recent research applications in psychiatry were reported.
    Keywords:  mental health
    DOI:  https://doi.org/10.1136/gpsych-2020-100197
  13. JMIR Med Inform. 2020 Mar 23. 8(3): e17110
       BACKGROUND: Metabolic syndrome is a cluster of disorders that significantly influence the development and deterioration of numerous diseases. FibroScan is an ultrasound device that was recently shown to predict metabolic syndrome with moderate accuracy. However, previous research regarding prediction of metabolic syndrome in subjects examined with FibroScan has been mainly based on conventional statistical models. Alternatively, machine learning, whereby a computer algorithm learns from prior experience, has better predictive performance over conventional statistical modeling.
    OBJECTIVE: We aimed to evaluate the accuracy of different decision tree machine learning algorithms to predict the state of metabolic syndrome in self-paid health examination subjects who were examined with FibroScan.
    METHODS: Multivariate logistic regression was conducted for every known risk factor of metabolic syndrome. Principal components analysis was used to visualize the distribution of metabolic syndrome patients. We further applied various statistical machine learning techniques to visualize and investigate the pattern and relationship between metabolic syndrome and several risk variables.
    RESULTS: Obesity, serum glutamic-oxalocetic transaminase, serum glutamic pyruvic transaminase, controlled attenuation parameter score, and glycated hemoglobin emerged as significant risk factors in multivariate logistic regression. The area under the receiver operating characteristic curve values for classification and regression trees and for the random forest were 0.831 and 0.904, respectively.
    CONCLUSIONS: Machine learning technology facilitates the identification of metabolic syndrome in self-paid health examination subjects with high accuracy.
    Keywords:  controlled attenuation parameter technology; decision tree; machine learning; metabolic syndrome
    DOI:  https://doi.org/10.2196/17110
  14. J Thorac Imaging. 2020 Mar 20.
      In this review article, the current and future impact of artificial intelligence (AI) technologies on diagnostic imaging is discussed, with a focus on cardio-thoracic applications. The processing of imaging data is described at 4 levels of increasing complexity and wider implications. At the examination level, AI aims at improving, simplifying, and standardizing image acquisition and processing. Systems for AI-driven automatic patient iso-centering before a computed tomography (CT) scan, patient-specific adaptation of image acquisition parameters, and creation of optimized and standardized visualizations, for example, automatic rib-unfolding, are discussed. At the reading and reporting levels, AI focuses on automatic detection and characterization of features and on automatic measurements in the images. A recently introduced AI system for chest CT imaging is presented that reports specific findings such as nodules, low-attenuation parenchyma, and coronary calcifications, including automatic measurements of, for example, aortic diameters. At the prediction and prescription levels, AI focuses on risk prediction and stratification, as opposed to merely detecting, measuring, and quantifying images. An AI-based approach for individualizing radiation dose in lung stereotactic body radiotherapy is discussed. The digital twin is presented as a concept of individualized computational modeling of human physiology, with AI-based CT-fractional flow reserve modeling as a first example. Finally, at the cohort and population analysis levels, the focus of AI shifts from clinical decision-making to operational decisions.
    DOI:  https://doi.org/10.1097/RTI.0000000000000499
  15. Int J Med Inform. 2019 Dec 30. pii: S1386-5056(19)31012-3. [Epub ahead of print]137 104072
       BACKGROUND: To explore attitudes about artificial intelligence (AI) among staff who utilized AI-based clinical decision support (CDS).
    METHODS: A survey was designed to assess staff attitudes about AI-based CDS tools. The survey was anonymously and voluntarily completed by clinical staff in three primary care outpatient clinics before and after implementation of an AI-based CDS system aimed to improve glycemic control in patients with diabetes as part of a quality improvement project. The CDS identified patients at risk for poor glycemic control and generated intervention recommendations intended to reduce patients' risk.
    RESULTS: Staff completed 45 surveys pre-intervention and 38 post-intervention. Following implementation, staff felt that care was better coordinated (11 favorable responses, 14 unfavorable responses pre-intervention; 21 favorable responses, 3 unfavorable responses post-intervention; p < 0.01). However, only 14 % of users would recommend the AI-based CDS. Staff feedback revealed that the most favorable aspect of the CDS was that it promoted team dialog about patient needs (N = 14, 52 %), and the least favorable aspect was inadequacy of the interventions recommended by the CDS.
    CONCLUSIONS: AI-based CDS tools that are perceived negatively by staff may reduce staff excitement about AI technology, and hands-on experience with AI may lead to more realistic expectations about the technology's capabilities. In our setting, although AI-based CDS prompted an interdisciplinary discussion about the needs of patients at high risk for poor glycemic control, the interventions recommended by the CDS were often perceived to be poorly tailored, inappropriate, or not useful. Developers should carefully consider tasks that are best performed by AI and those best performed by the patient's care team.
    Keywords:  Artificial; Clinical; Decision support systems; Diabetes mellitus; Intelligence
    DOI:  https://doi.org/10.1016/j.ijmedinf.2019.104072