1
|
Wang H, Pujos-Guillot E, Comte B, de Miranda JL, Spiwok V, Chorbev I, Castiglione F, Tieri P, Watterson S, McAllister R, de Melo Malaquias T, Zanin M, Rai TS, Zheng H. Deep learning in systems medicine. Brief Bioinform 2021; 22:1543-1559. [PMID: 33197934 PMCID: PMC8382976 DOI: 10.1093/bib/bbaa237] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/13/2020] [Revised: 08/25/2020] [Accepted: 08/26/2020] [Indexed: 12/11/2022] Open
Abstract
Systems medicine (SM) has emerged as a powerful tool for studying the human body at the systems level with the aim of improving our understanding, prevention and treatment of complex diseases. Being able to automatically extract relevant features needed for a given task from high-dimensional, heterogeneous data, deep learning (DL) holds great promise in this endeavour. This review paper addresses the main developments of DL algorithms and a set of general topics where DL is decisive, namely, within the SM landscape. It discusses how DL can be applied to SM with an emphasis on the applications to predictive, preventive and precision medicine. Several key challenges have been highlighted including delivering clinical impact and improving interpretability. We used some prototypical examples to highlight the relevance and significance of the adoption of DL in SM, one of them is involving the creation of a model for personalized Parkinson's disease. The review offers valuable insights and informs the research in DL and SM.
Collapse
Affiliation(s)
| | - Estelle Pujos-Guillot
- metabolomic platform dedicated to metabolism studies in nutrition and health in the French National Research Institute for Agriculture, Food and Environment
| | - Blandine Comte
- French National Research Institute for Agriculture, Food and Environment
| | - Joao Luis de Miranda
- (ESTG/IPP) and a Researcher (CERENA/IST) in optimization methods and process systems engineering
| | - Vojtech Spiwok
- Molecular Modelling Researcher applying machine learning to accelerate molecular simulations
| | - Ivan Chorbev
- Faculty for Computer Science and Engineering, University Ss Cyril and Methodius in Skopje, North Macedonia working in the area of eHealth and assistive technologies
| | | | - Paolo Tieri
- National Research Council of Italy (CNR) and a lecturer at Sapienza University in Rome, working in the field of network medicine and computational biology
| | | | - Roisin McAllister
- Research Associate working in CTRIC, University of Ulster, Derry, and has worked in clinical and academic roles in the fields of molecular diagnostics and biomarker discovery
| | | | - Massimiliano Zanin
- Researcher working in the Institute for Cross-Disciplinary Physics and Complex Systems, Spain, with an interest on data analysis and integration using statistical physics techniques
| | - Taranjit Singh Rai
- Lecturer in cellular ageing at the Centre for Stratified Medicine. Dr Rai’s research interests are in cellular senescence, which is thought to promote cellular and tissue ageing in disease, and the development of senolytic compounds to restrict this process
| | - Huiru Zheng
- Professor of computer sciences at Ulster University
| |
Collapse
|
2
|
Jamin A, Abraham P, Humeau-Heurtier A. Machine learning for predictive data analytics in medicine: A review illustrated by cardiovascular and nuclear medicine examples. Clin Physiol Funct Imaging 2020; 41:113-127. [PMID: 33316137 DOI: 10.1111/cpf.12686] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/05/2019] [Revised: 11/01/2020] [Accepted: 12/01/2020] [Indexed: 12/13/2022]
Abstract
The evidence-based medicine allows the physician to evaluate the risk-benefit ratio of a treatment through setting and data. Risk-based choices can be done by the doctor using different information. With the emergence of new technologies, a large amount of data is recorded offering interesting perspectives with machine learning for predictive data analytics. Machine learning is an ensemble of methods that process data to model a learning problem. Supervised machine learning algorithms consist in using annotated data to construct the model. This category allows to solve prediction data analytics problems. In this paper, we detail the use of supervised machine learning algorithms for predictive data analytics problems in medicine. In the medical field, data can be split into two categories: medical images and other data. For brevity, our review deals with any kind of medical data excluding images. In this article, we offer a discussion around four supervised machine learning approaches: information-based, similarity-based, probability-based and error-based approaches. Each method is illustrated with detailed cardiovascular and nuclear medicine examples. Our review shows that model ensemble (ME) and support vector machine (SVM) methods are the most popular. SVM, ME and artificial neural networks often lead to better results than those given by other algorithms. In the coming years, more studies, more data, more tools and more methods will, for sure, be proposed.
Collapse
Affiliation(s)
- Antoine Jamin
- COTTOS Médical, Avrillé, France.,LERIA-Laboratoire d'Etude et de Recherche en Informatique d'Angers, Univ. Angers, Angers, France.,LARIS-Laboratoire Angevin de Recherche en Ingénierie des Systèmes, Univ. Angers, Angers, France
| | - Pierre Abraham
- Sports Medicine Department, UMR Mitovasc CNRS 6015 INSERM 1228, Angers University Hospital, Angers, France
| | - Anne Humeau-Heurtier
- LARIS-Laboratoire Angevin de Recherche en Ingénierie des Systèmes, Univ. Angers, Angers, France
| |
Collapse
|
3
|
Lyu X, Hu J, Dong W, Xu X. Intellectual Structure and Evolutionary Trends of Precision Medicine Research: Coword Analysis. JMIR Med Inform 2020; 8:e11287. [PMID: 32014844 PMCID: PMC7055756 DOI: 10.2196/11287] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/13/2018] [Revised: 10/07/2019] [Accepted: 10/19/2019] [Indexed: 01/19/2023] Open
Abstract
BACKGROUND Precision medicine (PM) is playing a more and more important role in clinical practice. In recent years, the scale of PM research has been growing rapidly. Many reviews have been published to facilitate a better understanding of the status of PM research. However, there is still a lack of research on the intellectual structure in terms of topics. OBJECTIVE This study aimed to identify the intellectual structure and evolutionary trends of PM research through the application of various social network analysis and visualization methods. METHODS The bibliographies of papers published between 2009 and 2018 were extracted from the Web of Science database. Based on the statistics of keywords in the papers, a coword network was generated and used to calculate network indicators of both the entire network and local networks. Communities were then detected to identify subdirections of PM research. Topological maps of networks, including networks between communities and within each community, were drawn to reveal the correlation structure. An evolutionary graph and a strategic graph were finally produced to reveal research venation and trends in discipline communities. RESULTS The results showed that PM research involves extensive themes and, overall, is not balanced. A minority of themes with a high frequency and network indicators, such as Biomarkers, Genomics, Cancer, Therapy, Genetics, Drug, Target Therapy, Pharmacogenomics, Pharmacogenetics, and Molecular, can be considered the core areas of PM research. However, there were five balanced theme directions with distinguished status and tendencies: Cancer, Biomarkers, Genomics, Drug, and Therapy. These were shown to be the main branches that were both focused and well developed. Therapy, though, was shown to be isolated and undeveloped. CONCLUSIONS The hotspots, structures, evolutions, and development trends of PM research in the past ten years were revealed using social network analysis and visualization. In general, PM research is unbalanced, but its subdirections are balanced. The clear evolutionary and developmental trend indicates that PM research has matured in recent years. The implications of this study involving PM research will provide reasonable and effective support for researchers, funders, policymakers, and clinicians.
Collapse
Affiliation(s)
- Xiaoguang Lyu
- The Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, China
| | - Jiming Hu
- School of Information Management, Wuhan University, Wuhan, China.,Center for the Study of Information Resources, Wuhan University, Wuhan, China
| | - Weiguo Dong
- The Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, China
| | - Xin Xu
- The Intensive Care Unit of Coronary Heart Disease, Renmin Hospital of Wuhan University, Wuhan, China
| |
Collapse
|
4
|
Bolgova KV, Kovalchuk SV, Balakhontceva MA, Zvartau NE, Metsker OG. Human Computer Interaction During Clinical Decision Support With Electronic Health Records Improvement. INTERNATIONAL JOURNAL OF E-HEALTH AND MEDICAL COMMUNICATIONS 2020. [DOI: 10.4018/ijehmc.2020010106] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
Abstract
This study investigated the most common challenges of human-computer interaction (HCI) while using electronic health records (EHR) based on the experience of a large Russian medical research center. The article presents the results of testing DSS implemented in the mode of an additional interface with the EHR. The percentage of erroneous data for two groups of users (with and without notifications) is presented for the entire period of the experiment and the weekly dynamics of changes. The implementation of CDSS in the supplemented interface mode of the main medical information system (MIS) has had a positive effect in reducing user errors in the data. The results of users' survey are presented, showing a satisfactory evaluation of the implemented system. This study is part of a larger project to develop complex CDSS on cardiovascular disorders for medical research centers.
Collapse
|
5
|
Nanobiotechnology: Paving the Way to Personalized Medicine. Nanobiomedicine (Rij) 2020. [DOI: 10.1007/978-981-32-9898-9_2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/25/2022] Open
|
6
|
Morton SE, Knopp JL, Chase JG, Docherty P, Howe SL, Möller K, Shaw GM, Tawhai M. Optimising mechanical ventilation through model-based methods and automation. ANNUAL REVIEWS IN CONTROL 2019; 48:369-382. [PMID: 36911536 PMCID: PMC9985488 DOI: 10.1016/j.arcontrol.2019.05.001] [Citation(s) in RCA: 27] [Impact Index Per Article: 5.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/15/2019] [Revised: 04/09/2019] [Accepted: 05/01/2019] [Indexed: 06/11/2023]
Abstract
Mechanical ventilation (MV) is a core life-support therapy for patients suffering from respiratory failure or acute respiratory distress syndrome (ARDS). Respiratory failure is a secondary outcome of a range of injuries and diseases, and results in almost half of all intensive care unit (ICU) patients receiving some form of MV. Funding the increasing demand for ICU is a major issue and MV, in particular, can double the cost per day due to significant patient variability, over-sedation, and the large amount of clinician time required for patient management. Reducing cost in this area requires both a decrease in the average duration of MV by improving care, and a reduction in clinical workload. Both could be achieved by safely automating all or part of MV care via model-based dynamic systems modelling and control methods are ideally suited to address these problems. This paper presents common lung models, and provides a vision for a more automated future and explores predictive capacity of some current models. This vision includes the use of model-based methods to gain real-time insight to patient condition, improve safety through the forward prediction of outcomes to changes in MV, and develop virtual patients for in-silico design and testing of clinical protocols. Finally, the use of dynamic systems models and system identification to guide therapy for improved personalised control of oxygenation and MV therapy in the ICU will be considered. Such methods are a major part of the future of medicine, which includes greater personalisation and predictive capacity to both optimise care and reduce costs. This review thus presents the state of the art in how dynamic systems and control methods can be applied to transform this core area of ICU medicine.
Collapse
Affiliation(s)
- Sophie E Morton
- Department of Mechanical Engineering, University of Canterbury, New Zealand
| | - Jennifer L Knopp
- Department of Mechanical Engineering, University of Canterbury, New Zealand
| | - J Geoffrey Chase
- Department of Mechanical Engineering, University of Canterbury, New Zealand
| | - Paul Docherty
- Department of Mechanical Engineering, University of Canterbury, New Zealand
| | - Sarah L Howe
- Department of Mechanical Engineering, University of Canterbury, New Zealand
| | - Knut Möller
- Institute of Technical Medicine, Furtwangen University, Villingen-Schwenningen, Germany
| | - Geoffrey M Shaw
- Department of Intensive Care, Christchurch Hospital, Christchurch, New Zealand
| | - Merryn Tawhai
- Auckland Bioengineering Institute, University of Auckland, Auckland, New Zealand
| |
Collapse
|
7
|
Stéphanou A, Fanchon E, Innominato PF, Ballesta A. Systems Biology, Systems Medicine, Systems Pharmacology: The What and The Why. Acta Biotheor 2018; 66:345-365. [PMID: 29744615 DOI: 10.1007/s10441-018-9330-2] [Citation(s) in RCA: 30] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/15/2018] [Accepted: 05/05/2018] [Indexed: 12/22/2022]
Abstract
Systems biology is today such a widespread discipline that it becomes difficult to propose a clear definition of what it really is. For some, it remains restricted to the genomic field. For many, it designates the integrated approach or the corpus of computational methods employed to handle the vast amount of biological or medical data and investigate the complexity of the living. Although defining systems biology might be difficult, on the other hand its purpose is clear: systems biology, with its emerging subfields systems medicine and systems pharmacology, clearly aims at making sense of complex observations/experimental and clinical datasets to improve our understanding of diseases and their treatments without putting aside the context in which they appear and develop. In this short review, we aim to specifically focus on these new subfields with the new theoretical tools and approaches that were developed in the context of cancer. Systems pharmacology and medicine now give hope for major improvements in cancer therapy, making personalized medicine closer to reality. As we will see, the current challenge is to be able to improve the clinical practice according to the paradigm shift of systems sciences.
Collapse
Affiliation(s)
- Angélique Stéphanou
- Université Grenoble Alpes, CNRS, TIMC-IMAG/DyCTIM2, 38000, Grenoble, France.
| | - Eric Fanchon
- Université Grenoble Alpes, CNRS, TIMC-IMAG/DyCTIM2, 38000, Grenoble, France
| | - Pasquale F Innominato
- North Wales Cancer Centre, Betsi Cadwaladr University Health Board, Bangor, Denbighshire, UK
- INSERM and Université Paris 11 Unit 935, Villejuif, France
- University of Warwick, Coventry, UK
| | - Annabelle Ballesta
- INSERM and Université Paris 11 Unit 935, Villejuif, France
- University of Warwick, Coventry, UK
| |
Collapse
|
8
|
|
9
|
Complex Data-driven Predictive Modeling in Personalized Clinical Decision Support for Acute Coronary Syndrome Episodes. ACTA ACUST UNITED AC 2016. [DOI: 10.1016/j.procs.2016.05.332] [Citation(s) in RCA: 17] [Impact Index Per Article: 2.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/21/2022]
|
10
|
Piedra D, Ferrer A, Gea J. Text mining and medicine: usefulness in respiratory diseases. Arch Bronconeumol 2014; 50:113-9. [PMID: 24507559 DOI: 10.1016/j.arbres.2013.04.009] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/28/2013] [Revised: 04/12/2013] [Accepted: 04/18/2013] [Indexed: 12/24/2022]
Abstract
It is increasingly common to have medical information in electronic format. This includes scientific articles as well as clinical management reviews, and even records from health institutions with patient data. However, traditional instruments, both individual and institutional, are of little use for selecting the most appropriate information in each case, either in the clinical or research field. So-called text or data «mining» enables this huge amount of information to be managed, extracting it from various sources using processing systems (filtration and curation), integrating it and permitting the generation of new knowledge. This review aims to provide an overview of text and data mining, and of the potential usefulness of this bioinformatic technique in the exercise of care in respiratory medicine and in research in the same field.
Collapse
Affiliation(s)
- David Piedra
- Instituto de Investigación del Hospital del Mar (IMIM), Barcelona, España.
| | - Antoni Ferrer
- Instituto de Investigación del Hospital del Mar (IMIM), Barcelona, España; Servicio de Neumología, Hospital del Mar, Barcelona, España; Facultat de Ciències de la Salut i de la Vida, Universitat Pompeu Fabra, Barcelona, España; CIBERES, ISC III, Bunyola, Mallorca, España
| | - Joaquim Gea
- Instituto de Investigación del Hospital del Mar (IMIM), Barcelona, España; Servicio de Neumología, Hospital del Mar, Barcelona, España; Facultat de Ciències de la Salut i de la Vida, Universitat Pompeu Fabra, Barcelona, España; CIBERES, ISC III, Bunyola, Mallorca, España
| |
Collapse
|