bims-arihec Biomed News
on Artificial intelligence in healthcare
Issue of 2019–10–27
25 papers selected by
Céline Bélanger, Cogniges Inc.
  1. Artificial Intelligence in Medicine: Where Are We Now?
  2. Artificial intelligence-assisted care in medicine: a revolution or yet another blunt weapon?
  3. The importance of study design in the application of artificial intelligence methods in medicine.
  4. Trends and Focus of Machine Learning Applications for Health Research.
  5. Reaping the benefits of Open Data in public health.
  6. On the Potential, Feasibility, and Effectiveness of Chat Bots in Public Health Research Going Forward.
  7. Dissecting racial bias in an algorithm used to manage the health of populations.
  8. Has Drug Design Augmented by Artificial Intelligence Become a Reality?
  9. Rethinking Drug Repositioning and Development with Artificial Intelligence, Machine Learning, and Omics.
  10. A systematic review of natural language processing for classification tasks in the field of incident reporting and adverse event analysis.
  11. AI Meets Exascale Computing: Advancing Cancer Research With Large-Scale High Performance Computing.
  12. Recommendations and future directions for supervised machine learning in psychiatry.
  13. Machine Learning for Suicide Research-Can It Improve Risk Factor Identification?
  14. Prediction of Sex-Specific Suicide Risk Using Machine Learning and Single-Payer Health Care Registry Data From Denmark.
  15. Triaging ophthalmology outpatient referrals with machine learning: A pilot study.
  16. Identification of postoperative complications using electronic health record data and machine learning.
  17. Clinical applications of artificial intelligence in sepsis: A narrative review.
  18. Deep lessons learned: Radiology, oncology, pathology, and computer science experts unite around artificial intelligence to strive for earlier pancreatic cancer diagnosis.
  19. Translational AI and Deep Learning in Diagnostic Pathology.
  20. Machine Learning Approaches to Predict 6-Month Mortality Among Patients With Cancer.
  21. A machine learning approach for the prediction of pulmonary hypertension.
  22. Artificial intelligence and the detection of pediatric concussion using epigenomic analysis.
  23. Glaucoma management in the era of artificial intelligence.
  24. Machine Learning and Cochlear Implantation-A Structured Review of Opportunities and Challenges.
  25. Application of Artificial Intelligence in Gastrointestinal Endoscopy.
  1. Acad Radiol. 2019 Oct 18. pii: S1076-6332(19)30458-1. [Epub ahead of print]
    Artificial Intelligence in Medicine: Where Are We Now?
    Sagar Kulkarni, Nuran Seneviratne, Mirza Shaheer Baig, Ameer Hamid Ahmed Khan.
      Artificial intelligence in medicine has made dramatic progress in recent years. However, much of this progress is seemingly scattered, lacking a cohesive structure for the discerning observer. In this article, we will provide an up-to-date review of artificial intelligence in medicine, with a specific focus on its application to radiology, pathology, ophthalmology, and dermatology. We will discuss a range of selected papers that illustrate the potential uses of artificial intelligence in a technologically advanced future.
    Keywords:  Artificial intelligence; Deep learning; Dermatology; Ophthalmology; Pathology; Radiology; Review
    DOI:  https://doi.org/10.1016/j.acra.2019.10.001
  2. Eur Heart J. 2019 Oct 21. 40(40): 3286-3289
    Artificial intelligence-assisted care in medicine: a revolution or yet another blunt weapon?
    Alexander Meyer, Mario A Cypko, Carsten Eickhoff, Volkmar Falk, Maximilian Y Emmert.
      
    DOI:  https://doi.org/10.1093/eurheartj/ehz701
  3. NPJ Digit Med. 2019 ;2 101
    The importance of study design in the application of artificial intelligence methods in medicine.
    Martin Eklund, Kimmo Kartasalo, Henrik Olsson, Peter Ström.
      
    Keywords:  Epidemiology; Prostate cancer
    DOI:  https://doi.org/10.1038/s41746-019-0174-1
  4. JAMA Netw Open. 2019 Oct 02. 2(10): e1914051
    Trends and Focus of Machine Learning Applications for Health Research.
    Brett Beaulieu-Jones, Samuel G Finlayson, Corey Chivers, Irene Chen, Matthew McDermott, Jaz Kandola, Adrian V Dalca, Andrew Beam, Madalina Fiterau, Tristan Naumann.
       Importance: The use of machine learning applications related to health is rapidly increasing and may have the potential to profoundly affect the field of health care.
    Objective: To analyze submissions to a popular machine learning for health venue to assess the current state of research, including areas of methodologic and clinical focus, limitations, and underexplored areas.
    Design, Setting, and Participants: In this data-driven qualitative analysis, 166 accepted manuscript submissions to the Third Annual Machine Learning for Health workshop at the 32nd Conference on Neural Information Processing Systems on December 8, 2018, were analyzed to understand research focus, progress, and trends. Experts reviewed each submission against a rubric to identify key data points, statistical modeling and analysis of submitting authors was performed, and research topics were quantitatively modeled. Finally, an iterative discussion of topics common in submissions and invited speakers at the workshop was held to identify key trends.
    Main Outcomes and Measures: Frequency and statistical measures of methods, topics, goals, and author attributes were derived from an expert review of submissions guided by a rubric.
    Results: Of the 166 accepted submissions, 58 (34.9%) had clinician involvement and 83 submissions (50.0%) that focused on clinical practice included clinical collaborators. A total of 97 data sets (58.4%) used in submissions were publicly available or required a standard registration process. Clinical practice was the most common application area (70 manuscripts [42.2%]), with brain and mental health (25 [15.1%]), oncology (21 [12.7%]), and cardiovascular (19 [11.4%]) being the most common specialties.
    Conclusions and Relevance: Trends in machine learning for health research indicate the importance of well-annotated, easily accessed data and the benefit from greater clinician involvement in the development of translational applications.
    DOI:  https://doi.org/10.1001/jamanetworkopen.2019.14051
  5. Can Commun Dis Rep. 2019 Oct 03. 45(11): 252-256
    Reaping the benefits of Open Data in public health.
    P Huston, V L Edge, E Bernier.
      Open Data is part of a broad global movement that is not only advancing science and scientific communication but also transforming modern society and how decisions are made. What began with a call for Open Science and the rise of online journals has extended to Open Data, based on the premise that if reports on data are open, then the generated or supporting data should be open as well. There have been a number of advances in Open Data over the last decade, spearheaded largely by governments. A real benefit of Open Data is not simply that single databases can be used more widely; it is that these data can also be leveraged, shared and combined with other data. Open Data facilitates scientific collaboration, enriches research and advances analytical capacity to inform decisions. In the human and environmental health realms, for example, the ability to access and combine diverse data can advance early signal detection, improve analysis and evaluation, inform program and policy development, increase capacity for public participation, enable transparency and improve accountability. However, challenges remain. Enormous resources are needed to make the technological shift to open and interoperable databases accessible with common protocols and terminology. Amongst data generators and users, this shift also involves a cultural change: from regarding databases as restricted intellectual property, to considering data as a common good. There is a need to address legal and ethical considerations in making this shift. Finally, along with efforts to modify infrastructure and address the cultural, legal and ethical issues, it is important to share the information equitably and effectively. While there is great potential of the open, timely, equitable and straightforward sharing of data, fully realizing the myriad of benefits of Open Data will depend on how effectively these challenges are addressed.
    Keywords:  Open Data; Open Science; Open access; big data; public health science
    DOI:  https://doi.org/10.14745/ccdr.v45i10a01
  6. Online J Public Health Inform. 2019 ;11(2): e4
    On the Potential, Feasibility, and Effectiveness of Chat Bots in Public Health Research Going Forward.
    Stanley Mierzwa, Samir Souidi, Terry Conroy, Mohammad Abusyed, Hiroki Watarai, Taammy Allen.
      This paper will discuss whether bots, particularly chat bots, can be useful in public health research and health or pharmacy systems operations. Bots have been discussed for many years; particularly when coupled with artificial intelligence, they offer the opportunity of automating mundane or error-ridden processes and tasks by replacing human involvement. This paper will discuss areas where there are greater advances in the use of bots, as well as areas that may benefit from the use of bots, and will offer practical ways to get started with bot technology. Several popular bot applications and bot development tools along with practical security considerations will be discussed, and a toolbox that one can begin to use to implement bots will be presented.
    Keywords:  AI; Artificial Intelligence; Bot Framework; Bots; Chat Bots; Pharmacy Technology; Public Health Technology
    DOI:  https://doi.org/10.5210/ojphi.v11i2.9998
  7. Science. 2019 10 25. 366(6464): 447-453
    Dissecting racial bias in an algorithm used to manage the health of populations.
    Ziad Obermeyer, Brian Powers, Christine Vogeli, Sendhil Mullainathan.
      Health systems rely on commercial prediction algorithms to identify and help patients with complex health needs. We show that a widely used algorithm, typical of this industry-wide approach and affecting millions of patients, exhibits significant racial bias: At a given risk score, Black patients are considerably sicker than White patients, as evidenced by signs of uncontrolled illnesses. Remedying this disparity would increase the percentage of Black patients receiving additional help from 17.7 to 46.5%. The bias arises because the algorithm predicts health care costs rather than illness, but unequal access to care means that we spend less money caring for Black patients than for White patients. Thus, despite health care cost appearing to be an effective proxy for health by some measures of predictive accuracy, large racial biases arise. We suggest that the choice of convenient, seemingly effective proxies for ground truth can be an important source of algorithmic bias in many contexts.
    DOI:  https://doi.org/10.1126/science.aax2342
  8. Trends Pharmacol Sci. 2019 Oct 16. pii: S0165-6147(19)30215-9. [Epub ahead of print]
    Has Drug Design Augmented by Artificial Intelligence Become a Reality?
    Hongming Chen, Ola Engkvist.
      The application of artificial intelligence (AI) to drug discovery has become a hot topic in recent years. Generative molecular design based on deep learning is a particular an area of attention. Zhavoronkov et al. recently published a novel approach in which de novo molecular design based on deep learning was used to discover novel potent DDR1 kinase inhibitors. It took 21 days from model building to compound design, and a total of six AI-designed compounds were synthesized and tested. The study highlights how quickly the field of AI-designed compounds is developing, and we can expect further developments in the coming years.
    Keywords:  DDR1; GENTRL; deep learning; drug design; drug discovery
    DOI:  https://doi.org/10.1016/j.tips.2019.09.004
  9. OMICS. 2019 Oct 25.
    Rethinking Drug Repositioning and Development with Artificial Intelligence, Machine Learning, and Omics.
    Maria Koromina, Maria-Theodora Pandi, George P Patrinos.
      Pharmaceutical industry and the art and science of drug development are sorely in need of novel transformative technologies in the current age of digital health and artificial intelligence (AI). Often described as game-changing technologies, AI and machine learning algorithms have slowly but surely begun to revolutionize pharmaceutical industry and drug development over the past 5 years. In this expert review, we describe the most frequently used machine learning algorithms in drug development pipelines and the -omics databases well poised to support machine learning and drug discovery. Subsequently, we analyze the emerging new computational approaches to drug discovery and the in silico pipelines for drug repositioning and the synergies among -omics system sciences, AI and machine learning. As with system sciences, AI and machine learning embody a system scale and Big Data driven vision for drug discovery and development. We conclude with a future outlook on the ways in which machine learning approaches can be implemented to buttress and expedite drug discovery and precision medicine. As AI and machine learning are rapidly entering pharmaceutical industry and the art and science of drug development, we need to critically examine the attendant prospects and challenges to benefit patients and public health.
    Keywords:  artificial intelligence; drug development; drug repositioning; machine learning; next-generation sequencing; omics; pharmaceutical industry
    DOI:  https://doi.org/10.1089/omi.2019.0151
  10. Int J Med Inform. 2019 Oct 05. pii: S1386-5056(19)30237-0. [Epub ahead of print]132 103971
    A systematic review of natural language processing for classification tasks in the field of incident reporting and adverse event analysis.
    Ian James Bruce Young, Saturnino Luz, Nazir Lone.
       CONTEXT: Adverse events in healthcare are often collated in incident reports which contain unstructured free text. Learning from these events may improve patient safety. Natural language processing (NLP) uses computational techniques to interrogate free text, reducing the human workload associated with its analysis. There is growing interest in applying NLP to patient safety, but the evidence in the field has not been summarised and evaluated to date.
    OBJECTIVE: To perform a systematic literature review and narrative synthesis to describe and evaluate NLP methods for classification of incident reports and adverse events in healthcare.
    METHODS: Data sources included Medline, Embase, The Cochrane Library, CINAHL, MIDIRS, ISI Web of Science, SciELO, Google Scholar, PROSPERO, hand searching of key articles, and OpenGrey. Data items were manually abstracted to a standardised extraction form.
    RESULTS: From 428 articles screened for eligibility, 35 met the inclusion criteria of using NLP to perform a classification task on incident reports, or with the aim of detecting adverse events. The majority of studies used free text from incident reporting systems or electronic health records. Models were typically designed to classify by type of incident, type of medication error, or harm severity. A broad range of NLP techniques are demonstrated to perform these classification tasks with favourable performance outcomes. There are methodological challenges in how these results can be interpreted in a broader context.
    CONCLUSION: NLP can generate meaningful information from unstructured data in the specific domain of the classification of incident reports and adverse events. Understanding what or why incidents are occurring is important in adverse event analysis. If NLP enables these insights to be drawn from larger datasets it may improve the learning from adverse events in healthcare.
    Keywords:  Adverse event analysis; Incident reporting; Machine learning; Natural language processing; Patient safety; Text classification
    DOI:  https://doi.org/10.1016/j.ijmedinf.2019.103971
  11. Front Oncol. 2019 ;9 984
    AI Meets Exascale Computing: Advancing Cancer Research With Large-Scale High Performance Computing.
    Tanmoy Bhattacharya, Thomas Brettin, James H Doroshow, Yvonne A Evrard, Emily J Greenspan, Amy L Gryshuk, Thuc T Hoang, Carolyn B Vea Lauzon, Dwight Nissley, Lynne Penberthy, Eric Stahlberg, Rick Stevens, Fred Streitz, Georgia Tourassi, Fangfang Xia, George Zaki.
      The application of data science in cancer research has been boosted by major advances in three primary areas: (1) Data: diversity, amount, and availability of biomedical data; (2) Advances in Artificial Intelligence (AI) and Machine Learning (ML) algorithms that enable learning from complex, large-scale data; and (3) Advances in computer architectures allowing unprecedented acceleration of simulation and machine learning algorithms. These advances help build in silico ML models that can provide transformative insights from data including: molecular dynamics simulations, next-generation sequencing, omics, imaging, and unstructured clinical text documents. Unique challenges persist, however, in building ML models related to cancer, including: (1) access, sharing, labeling, and integration of multimodal and multi-institutional data across different cancer types; (2) developing AI models for cancer research capable of scaling on next generation high performance computers; and (3) assessing robustness and reliability in the AI models. In this paper, we review the National Cancer Institute (NCI) -Department of Energy (DOE) collaboration, Joint Design of Advanced Computing Solutions for Cancer (JDACS4C), a multi-institution collaborative effort focused on advancing computing and data technologies to accelerate cancer research on three levels: molecular, cellular, and population. This collaboration integrates various types of generated data, pre-exascale compute resources, and advances in ML models to increase understanding of basic cancer biology, identify promising new treatment options, predict outcomes, and eventually prescribe specialized treatments for patients with cancer.
    Keywords:  artificial intelligence; cancer research; deep learning; high performance computing; multi-scale modeling; natural language processing; precision medicine; uncertainty quantification
    DOI:  https://doi.org/10.3389/fonc.2019.00984
  12. Transl Psychiatry. 2019 Oct 22. 9(1): 271
    Recommendations and future directions for supervised machine learning in psychiatry.
    Micah Cearns, Tim Hahn, Bernhard T Baune.
      Machine learning methods hold promise for personalized care in psychiatry, demonstrating the potential to tailor treatment decisions and stratify patients into clinically meaningful taxonomies. Subsequently, publication counts applying machine learning methods have risen, with different data modalities, mathematically distinct models, and samples of varying size being used to train and test models with the promise of clinical translation. Consequently, and in part due to the preliminary nature of such works, many studies have reported largely varying degrees of accuracy, raising concerns over systematic overestimation and methodological inconsistencies. Furthermore, a lack of procedural evaluation guidelines for non-expert medical professionals and funding bodies leaves many in the field with no means to systematically evaluate the claims, maturity, and clinical readiness of a project. Given the potential of machine learning methods to transform patient care, albeit, contingent on the rigor of employed methods and their dissemination, we deem it necessary to provide a review of current methods, recommendations, and future directions for applied machine learning in psychiatry. In this review we will cover issues of best practice for model training and evaluation, sources of systematic error and overestimation, model explainability vs. trust, the clinical implementation of AI systems, and finally, future directions for our field.
    DOI:  https://doi.org/10.1038/s41398-019-0607-2
  13. JAMA Psychiatry. 2019 Oct 23.
    Machine Learning for Suicide Research-Can It Improve Risk Factor Identification?
    Seena Fazel, Lauren O'Reilly.
      
    DOI:  https://doi.org/10.1001/jamapsychiatry.2019.2896
  14. JAMA Psychiatry. 2019 Oct 23.
    Prediction of Sex-Specific Suicide Risk Using Machine Learning and Single-Payer Health Care Registry Data From Denmark.
    Jaimie L Gradus, Anthony J Rosellini, Erzsébet Horváth-Puhó, Amy E Street, Isaac Galatzer-Levy, Tammy Jiang, Timothy L Lash, Henrik T Sørensen.
       Importance: Suicide is a public health problem, with multiple causes that are poorly understood. The increased focus on combining health care data with machine-learning approaches in psychiatry may help advance the understanding of suicide risk.
    Objective: To examine sex-specific risk profiles for death from suicide using machine-learning methods and data from the population of Denmark.
    Design, Setting, and Participants: A case-cohort study nested within 8 national Danish health and social registries was conducted from January 1, 1995, through December 31, 2015. The source population was all persons born or residing in Denmark as of January 1, 1995. Data were analyzed from November 5, 2018, through May 13, 2019.
    Exposures: Exposures included 1339 variables spanning domains of suicide risk factors.
    Main Outcomes and Measures: Death from suicide from the Danish cause of death registry.
    Results: A total of 14 103 individuals died by suicide between 1995 and 2015 (10 152 men [72.0%]; mean [SD] age, 43.5 [18.8] years and 3951 women [28.0%]; age, 47.6 [18.8] years). The comparison subcohort was a 5% random sample (n = 265 183) of living individuals in Denmark on January 1, 1995 (130 591 men [49.2%]; age, 37.4 [21.8] years and 134 592 women [50.8%]; age, 39.9 [23.4] years). With use of classification trees and random forests, sex-specific differences were noted in risk for suicide, with physical health more important to men's suicide risk than women's suicide risk. Psychiatric disorders and possibly associated medications were important to suicide risk, with specific results that may increase clarity in the literature. For example, stress disorders among unmarried men older than 30 years were important factors for suicide risk in the presence of depression (risk, 0.54). Generally, diagnoses and medications measured 48 months before suicide were more important indicators of suicide risk than when measured 6 months earlier. Individuals in the top 5% of predicted suicide risk appeared to account for 32.0% of all suicide cases in men and 53.4% of all cases in women.
    Conclusions and Relevance: Despite decades of research on suicide risk factors, understanding of suicide remains poor. In this study, the first to date to develop risk profiles for suicide based on data from a full population, apparent consistency with what is known about suicide risk was noted, as well as potentially important, understudied risk factors with evidence of unique suicide risk profiles among specific subpopulations.
    DOI:  https://doi.org/10.1001/jamapsychiatry.2019.2905
  15. Clin Exp Ophthalmol. 2019 Oct 24.
    Triaging ophthalmology outpatient referrals with machine learning: A pilot study.
    Yiran Tan, Stephen Bacchi, Robert J Casson, Dinesh Selva, Weng Onn Chan.
       IMPORTANCE: Triaging of outpatient referrals to ophthalmology services is required for the maintenance of patient care and appropriate resource allocation. Machine learning (ML), in particular natural language processing, may be able to assist with the triaging process.
    BACKGROUND: To determine whether ML can accurately predict triage category based on ophthalmology outpatient referrals.
    DESIGN: Retrospective cohort study.
    PARTICIPANTS: The data of 208 participants was included in the project.
    METHODS: The synopses of consecutive ophthalmology outpatient referrals at a tertiary hospital were extracted along with their triage categorisations. Following pre-processing, ML models were applied to determine how accurately they could predict the likely triage categorisation allocated. Data was split into training and testing sets (75%/25% split). ML models were tested on an unseen test set, after development on the training dataset.
    MAIN OUTCOME MEASURE: Area under the receiver operator curve (AUC) for category one vs non-category one classification.
    RESULTS: For the main outcome measure, convolutional neural network (CNN) provided the best AUC (0.83) and accuracy on the test set (0.81), with the artificial neural network (AUC 0.81 and accuracy 0.77) being the next best performing model. When the CNN was applied to the classification task of identifying which referrals should be allocated a category one vs category two vs category three priority, a lower accuracy was achieved (0.65).
    CONCLUSION AND RELEVANCE: ML may be able to accurately assist with the triaging of ophthalmology referrals. Future studies with data from multiple centres and larger sample sizes may be beneficial. This article is protected by copyright. All rights reserved.
    Keywords:  Deep Learning; Natural Language processing; machine learning; ophthalmology
    DOI:  https://doi.org/10.1111/ceo.13666
  16. Am J Surg. 2019 Oct 09. pii: S0002-9610(19)31150-X. [Epub ahead of print]
    Identification of postoperative complications using electronic health record data and machine learning.
    Michael Bronsert, Abhinav B Singh, William G Henderson, Karl Hammermeister, Robert A Meguid, Kathryn L Colborn.
       BACKGROUND: Using the American College of Surgeons National Surgical Quality Improvement Program (NSQIP) complication status of patients who underwent an operation at the University of Colorado Hospital, we developed a machine learning algorithm for identifying patients with one or more complications using data from the electronic health record (EHR).
    METHODS: We used an elastic-net model to estimate regression coefficients and carry out variable selection. International classification of disease codes (ICD-9), common procedural terminology (CPT) codes, medications, and CPT-specific complication event rate were included as predictors.
    RESULTS: Of 6840 patients, 922 (13.5%) had at least one of the 18 complications tracked by NSQIP. The model achieved 88% specificity, 83% sensitivity, 97% negative predictive value, 52% positive predictive value, and an area under the curve of 0.93.
    CONCLUSIONS: Using machine learning on EHR postoperative data linked to NSQIP outcomes data, a model with 163 predictors from the EHR identified complications well at our institution.
    Keywords:  Elastic-net; Machine learning; NSQIP; Postoperative complications
    DOI:  https://doi.org/10.1016/j.amjsurg.2019.10.009
  17. Comput Biol Med. 2019 Oct 07. pii: S0010-4825(19)30356-7. [Epub ahead of print]115 103488
    Clinical applications of artificial intelligence in sepsis: A narrative review.
    M Schinkel, K Paranjape, R S Nannan Panday, N Skyttberg, P W B Nanayakkara.
      Many studies have been published on a variety of clinical applications of artificial intelligence (AI) for sepsis, while there is no overview of the literature. The aim of this review is to give an overview of the literature and thereby identify knowledge gaps and prioritize areas with high priority for further research. A literature search was conducted in PubMed from inception to February 2019. Search terms related to AI were combined with terms regarding sepsis. Articles were included when they reported an area under the receiver operator characteristics curve (AUROC) as outcome measure. Fifteen articles on diagnosis of sepsis with AI models were included. The best performing model reached an AUROC of 0.97. There were also seven articles on prognosis, predicting mortality over time with an AUROC of up to 0.895. Finally, there were three articles on assistance of treatment of sepsis, where the use of AI was associated with the lowest mortality rates. Of the articles, twenty-two were judged to be at high risk of bias or had major concerns regarding applicability. This was mostly because predictor variables in these models, such as blood pressure, were also part of the definition of sepsis, which led to overestimation of the performance. We conclude that AI models have great potential for improving early identification of patients who may benefit from administration of antibiotics. Current AI prediction models to diagnose sepsis are at major risks of bias when the diagnosis criteria are part of the predictor variables in the model. Furthermore, generalizability of these models is poor due to overfitting and a lack of standardized protocols for the construction and validation of the models. Until these problems have been resolved, a large gap remains between the creation of an AI algorithm and its implementation in clinical practice.
    Keywords:  Artificial intelligence; Machine learning; Mortality; PROBAST; Sepsis
    DOI:  https://doi.org/10.1016/j.compbiomed.2019.103488
  18. Diagn Interv Imaging. 2019 Oct 16. pii: S2211-5684(19)30211-6. [Epub ahead of print]
    Deep lessons learned: Radiology, oncology, pathology, and computer science experts unite around artificial intelligence to strive for earlier pancreatic cancer diagnosis.
    E M Weisberg, L C Chu, S Park, A L Yuille, K W Kinzler, B Vogelstein, E K Fishman.
      
    Keywords:  Artificial intelligence (AI); Deep learning; Pancreatic ductal adenocarcinoma (PDA); Pancreatic neuroendocrine tumor; Radiomics
    DOI:  https://doi.org/10.1016/j.diii.2019.09.002
  19. Front Med (Lausanne). 2019 ;6 185
    Translational AI and Deep Learning in Diagnostic Pathology.
    Ahmed Serag, Adrian Ion-Margineanu, Hammad Qureshi, Ryan McMillan, Marie-Judith Saint Martin, Jim Diamond, Paul O'Reilly, Peter Hamilton.
      There has been an exponential growth in the application of AI in health and in pathology. This is resulting in the innovation of deep learning technologies that are specifically aimed at cellular imaging and practical applications that could transform diagnostic pathology. This paper reviews the different approaches to deep learning in pathology, the public grand challenges that have driven this innovation and a range of emerging applications in pathology. The translation of AI into clinical practice will require applications to be embedded seamlessly within digital pathology workflows, driving an integrated approach to diagnostics and providing pathologists with new tools that accelerate workflow and improve diagnostic consistency and reduce errors. The clearance of digital pathology for primary diagnosis in the US by some manufacturers provides the platform on which to deliver practical AI. AI and computational pathology will continue to mature as researchers, clinicians, industry, regulatory organizations and patient advocacy groups work together to innovate and deliver new technologies to health care providers: technologies which are better, faster, cheaper, more precise, and safe.
    Keywords:  artificial intelligence; computational pathology; deep learning; digital pathology; image analysis; machine learning; neural network; pathology
    DOI:  https://doi.org/10.3389/fmed.2019.00185
  20. JAMA Netw Open. 2019 Oct 02. 2(10): e1915997
    Machine Learning Approaches to Predict 6-Month Mortality Among Patients With Cancer.
    Ravi B Parikh, Christopher Manz, Corey Chivers, Susan Harkness Regli, Jennifer Braun, Michael E Draugelis, Lynn M Schuchter, Lawrence N Shulman, Amol S Navathe, Mitesh S Patel, Nina R O'Connor.
       Importance: Machine learning algorithms could identify patients with cancer who are at risk of short-term mortality. However, it is unclear how different machine learning algorithms compare and whether they could prompt clinicians to have timely conversations about treatment and end-of-life preferences.
    Objectives: To develop, validate, and compare machine learning algorithms that use structured electronic health record data before a clinic visit to predict mortality among patients with cancer.
    Design, Setting, and Participants: Cohort study of 26 525 adult patients who had outpatient oncology or hematology/oncology encounters at a large academic cancer center and 10 affiliated community practices between February 1, 2016, and July 1, 2016. Patients were not required to receive cancer-directed treatment. Patients were observed for up to 500 days after the encounter. Data analysis took place between October 1, 2018, and September 1, 2019.
    Exposures: Logistic regression, gradient boosting, and random forest algorithms.
    Main Outcomes and Measures: Primary outcome was 180-day mortality from the index encounter; secondary outcome was 500-day mortality from the index encounter.
    Results: Among 26 525 patients in the analysis, 1065 (4.0%) died within 180 days of the index encounter. Among those who died, the mean age was 67.3 (95% CI, 66.5-68.0) years, and 500 (47.0%) were women. Among those who were alive at 180 days, the mean age was 61.3 (95% CI, 61.1-61.5) years, and 15 922 (62.5%) were women. The population was randomly partitioned into training (18 567 [70.0%]) and validation (7958 [30.0%]) cohorts at the patient level, and a randomly selected encounter was included in either the training or validation set. At a prespecified alert rate of 0.02, positive predictive values were higher for the random forest (51.3%) and gradient boosting (49.4%) algorithms compared with the logistic regression algorithm (44.7%). There was no significant difference in discrimination among the random forest (area under the receiver operating characteristic curve [AUC], 0.88; 95% CI, 0.86-0.89), gradient boosting (AUC, 0.87; 95% CI, 0.85-0.89), and logistic regression (AUC, 0.86; 95% CI, 0.84-0.88) models (P for comparison = .02). In the random forest model, observed 180-day mortality was 51.3% (95% CI, 43.6%-58.8%) in the high-risk group vs 3.4% (95% CI, 3.0%-3.8%) in the low-risk group; at 500 days, observed mortality was 64.4% (95% CI, 56.7%-71.4%) in the high-risk group and 7.6% (7.0%-8.2%) in the low-risk group. In a survey of 15 oncology clinicians with a 52.1% response rate, 100 of 171 patients (58.8%) who had been flagged as having high risk by the gradient boosting algorithm were deemed appropriate for a conversation about treatment and end-of-life preferences in the upcoming week.
    Conclusions and Relevance: In this cohort study, machine learning algorithms based on structured electronic health record data accurately identified patients with cancer at risk of short-term mortality. When the gradient boosting algorithm was applied in real time, clinicians believed that most patients who had been identified as having high risk were appropriate for a timely conversation about treatment and end-of-life preferences.
    DOI:  https://doi.org/10.1001/jamanetworkopen.2019.15997
  21. PLoS One. 2019 ;14(10): e0224453
    A machine learning approach for the prediction of pulmonary hypertension.
    Andreas Leha, Kristian Hellenkamp, Bernhard Unsöld, Sitali Mushemi-Blake, Ajay M Shah, Gerd Hasenfuß, Tim Seidler.
       BACKGROUND: Machine learning (ML) is a powerful tool for identifying and structuring several informative variables for predictive tasks. Here, we investigated how ML algorithms may assist in echocardiographic pulmonary hypertension (PH) prediction, where current guidelines recommend integrating several echocardiographic parameters.
    METHODS: In our database of 90 patients with invasively determined pulmonary artery pressure (PAP) with corresponding echocardiographic estimations of PAP obtained within 24 hours, we trained and applied five ML algorithms (random forest of classification trees, random forest of regression trees, lasso penalized logistic regression, boosted classification trees, support vector machines) using a 10 times 3-fold cross-validation (CV) scheme.
    RESULTS: ML algorithms achieved high prediction accuracies: support vector machines (AUC 0.83; 95% CI 0.73-0.93), boosted classification trees (AUC 0.80; 95% CI 0.68-0.92), lasso penalized logistic regression (AUC 0.78; 95% CI 0.67-0.89), random forest of classification trees (AUC 0.85; 95% CI 0.75-0.95), random forest of regression trees (AUC 0.87; 95% CI 0.78-0.96). In contrast to the best of several conventional formulae (by Aduen et al.), this ML algorithm is based on several echocardiographic signs and feature selection, with estimated right atrial pressure (RAP) being of minor importance.
    CONCLUSIONS: Using ML, we were able to predict pulmonary hypertension based on a broader set of echocardiographic data with little reliance on estimated RAP compared to an existing formula with non-inferior performance. With the conceptual advantages of a broader and unbiased selection and weighting of data our ML approach is suited for high level assistance in PH prediction.
    DOI:  https://doi.org/10.1371/journal.pone.0224453
  22. Brain Res. 2019 Oct 16. pii: S0006-8993(19)30564-5. [Epub ahead of print] 146510
    Artificial intelligence and the detection of pediatric concussion using epigenomic analysis.
    Ray O Bahado-Singh, Sangeetha Vishweswaraiah, Anıl Er, Buket Aydas, Onur Turkoglu, Birce D Taskin, Murat Duman, Durgül Yilmaz, Uppala Radhakrishna.
      Concussion, also referred to as mild traumatic brain injury (mTBI) is the most common type of traumatic brain injury. Currently concussion is an area ofintensescientific interest to better understand the biological mechanisms and for biomarker development. We evaluated whole genome-wide blood DNA cytosine ('CpG') methylation in 17 pediatric concussion isolated cases and 18 unaffected controls using Illumina Infinium MethylationEPIC assay. Pathway analysis was performed using Ingenuity Pathway Analysis to help elucidate the epigenetic and molecular mechanisms of the disorder. Area under the receiver operating characteristics (AUC) curves and FDR p-values were calculated for mTBI detection based on CpG methylation levels . Multiple Artificial Intelligence (AI) platforms including Deep Learning (DL), the newest form of AI, were used to predict concussion based on i) CpG methylation markers alone, and ii) combined epigenetic, clinical and demographic predictors. We found 449 CpG sites (473 genes), those were statistically significantly methylated in mTBI compared to controls. There were four CpGs with excellent accuracy (AUC ≥0.90-1.00) while 119 displayed good accuracy (AUC≥0.80-0.89) for the predictive of mTBI. The CpG methylation changes ≥10% were observed in many CpG loci after concussion suggesting biological significance. Pathway analysis identified several biologically important neurological pathways that were perturbed including those associated with: impaired brain function, cognition, memory, neurotransmission, intellectual disability and behavioral change and associated disorders. The combination of epigenomic and clinical predictors were highly accurate for the detection of concusion using AI techniques. Using DL/AI, a combination of epigenomic and clinical markers had sensitivity and specificity ≧95% for prediction of mTBI. In this novel study, we identified significant methylation changes in multiple genes in response to mTBI. Gene pathways that were epigenetically dysregulated included several known to be involved in neurological function, thus giving biological plausibility to our findings.
    Keywords:  Artificial Intelligence; Biomarkers; Epigenetics; Illumina Infinium MethylationEPIC BeadChip assay; Pediatric concussion; methylation
    DOI:  https://doi.org/10.1016/j.brainres.2019.146510
  23. Br J Ophthalmol. 2019 Oct 22. pii: bjophthalmol-2019-315016. [Epub ahead of print]
    Glaucoma management in the era of artificial intelligence.
    Sripad Krishna Devalla, Zhang Liang, Tan Hung Pham, Craig Boote, Nicholas G Strouthidis, Alexandre H Thiery, Michael J A Girard.
      Glaucoma is a result of irreversible damage to the retinal ganglion cells. While an early intervention could minimise the risk of vision loss in glaucoma, its asymptomatic nature makes it difficult to diagnose until a late stage. The diagnosis of glaucoma is a complicated and expensive effort that is heavily dependent on the experience and expertise of a clinician. The application of artificial intelligence (AI) algorithms in ophthalmology has improved our understanding of many retinal, macular, choroidal and corneal pathologies. With the advent of deep learning, a number of tools for the classification, segmentation and enhancement of ocular images have been developed. Over the years, several AI techniques have been proposed to help detect glaucoma by analysis of functional and/or structural evaluations of the eye. Moreover, the use of AI has also been explored to improve the reliability of ascribing disease prognosis. This review summarises the role of AI in the diagnosis and prognosis of glaucoma, discusses the advantages and challenges of using AI systems in clinics and predicts likely areas of future progress.
    Keywords:  Glaucoma; Imaging; Optic Nerve
    DOI:  https://doi.org/10.1136/bjophthalmol-2019-315016
  24. Otol Neurotol. 2019 Oct 21.
    Machine Learning and Cochlear Implantation-A Structured Review of Opportunities and Challenges.
    Matthew G Crowson, Vincent Lin, Joseph M Chen, Timothy C Y Chan.
       OBJECTIVE: The use of machine learning technology to automate intellectual processes and boost clinical process efficiency in medicine has exploded in the past 5 years. Machine learning excels in automating pattern recognition and in adapting learned representations to new settings. Moreover, machine learning techniques have the advantage of incorporating complexity and are free from many of the limitations of traditional deterministic approaches. Cochlear implants (CI) are a unique fit for machine learning techniques given the need for optimization of signal processing to fit complex environmental scenarios and individual patients' CI MAPping. However, there are many other opportunities where machine learning may assist in CI beyond signal processing. The objective of this review was to synthesize past applications of machine learning technologies for pediatric and adult CI and describe novel opportunities for research and development.
    DATA SOURCES: The PubMed/MEDLINE, EMBASE, Scopus, and ISI Web of Knowledge databases were mined using a directed search strategy to identify the nexus between CI and artificial intelligence/machine learning literature.
    STUDY SELECTION: Non-English language articles, articles without an available abstract or full-text, and nonrelevant articles were manually appraised and excluded. Included articles were evaluated for specific machine learning methodologies, content, and application success.
    DATA SYNTHESIS: The database search identified 298 articles. Two hundred fifty-nine articles (86.9%) were excluded based on the available abstract/full-text, language, and relevance. The remaining 39 articles were included in the review analysis. There was a marked increase in year-over-year publications from 2013 to 2018. Applications of machine learning technologies involved speech/signal processing optimization (17; 43.6% of articles), automated evoked potential measurement (6; 15.4%), postoperative performance/efficacy prediction (5; 12.8%), and surgical anatomy location prediction (3; 7.7%), and 2 (5.1%) in each of robotics, electrode placement performance, and biomaterials performance.
    CONCLUSION: The relationship between CI and artificial intelligence is strengthening with a recent increase in publications reporting successful applications. Considerable effort has been directed toward augmenting signal processing and automating postoperative MAPping using machine learning algorithms. Other promising applications include augmenting CI surgery mechanics and personalized medicine approaches for boosting CI patient performance. Future opportunities include addressing scalability and the research and clinical communities' acceptance of machine learning algorithms as effective techniques.
    DOI:  https://doi.org/10.1097/MAO.0000000000002440
  25. J Dig Dis. 2019 Oct 22.
    Application of Artificial Intelligence in Gastrointestinal Endoscopy.
    Yishan He, Jingran Su, Zhen Li, Xiuli Zuo, Yanqing Li.
      With significant improvement in artificial intelligence (AI), especially in the field of deep learning (DL), increasing number of studies applied AI in gastrointestinal (GI) endoscopy for detection and diagnosis of GI lesions. The present article summarizes current publications relating to AI applied in GI endoscopy and focus on the challenges and future of AI-aided system. We expect that AI could provide an effective and practical method for endoscopists in the aspects of lesion detection, characterization and endoscopy quality control. But so far, most of the studies remain in the pre-clinical stage. In the future, more attention should be paid on the performance of AI in real-clinical application. This article is protected by copyright. All rights reserved.
    Keywords:  artificial intelligence; gastrointestinal endoscopy
    DOI:  https://doi.org/10.1111/1751-2980.12827
This page is being maintained by Thomas Krichel. It was last updated on 2024‒11‒22 at 4:11.