1
|
Ruchonnet-Métrailler I, Siebert JN, Hartley MA, Lacroix L. Automated Interpretation of Lung Sounds by Deep Learning in Children With Asthma: Scoping Review and Strengths, Weaknesses, Opportunities, and Threats Analysis. J Med Internet Res 2024; 26:e53662. [PMID: 39178033 PMCID: PMC11380063 DOI: 10.2196/53662] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/14/2023] [Revised: 03/28/2024] [Accepted: 07/10/2024] [Indexed: 08/24/2024] Open
Abstract
BACKGROUND The interpretation of lung sounds plays a crucial role in the appropriate diagnosis and management of pediatric asthma. Applying artificial intelligence (AI) to this task has the potential to better standardize assessment and may even improve its predictive potential. OBJECTIVE This study aims to objectively review the literature on AI-assisted lung auscultation for pediatric asthma and provide a balanced assessment of its strengths, weaknesses, opportunities, and threats. METHODS A scoping review on AI-assisted lung sound analysis in children with asthma was conducted across 4 major scientific databases (PubMed, MEDLINE Ovid, Embase, and Web of Science), supplemented by a gray literature search on Google Scholar, to identify relevant studies published from January 1, 2000, until May 23, 2023. The search strategy incorporated a combination of keywords related to AI, pulmonary auscultation, children, and asthma. The quality of eligible studies was assessed using the ChAMAI (Checklist for the Assessment of Medical Artificial Intelligence). RESULTS The search identified 7 relevant studies out of 82 (9%) to be included through an academic literature search, while 11 of 250 (4.4%) studies from the gray literature search were considered but not included in the subsequent review and quality assessment. All had poor to medium ChAMAI scores, mostly due to the absence of external validation. Identified strengths were improved predictive accuracy of AI to allow for prompt and early diagnosis, personalized management strategies, and remote monitoring capabilities. Weaknesses were the heterogeneity between studies and the lack of standardization in data collection and interpretation. Opportunities were the potential of coordinated surveillance, growing data sets, and new ways of collaboratively learning from distributed data. Threats were both generic for the field of medical AI (loss of interpretability) but also specific to the use case, as clinicians might lose the skill of auscultation. CONCLUSIONS To achieve the opportunities of automated lung auscultation, there is a need to address weaknesses and threats with large-scale coordinated data collection in globally representative populations and leveraging new approaches to collaborative learning.
Collapse
Affiliation(s)
- Isabelle Ruchonnet-Métrailler
- Pediatric Pulmonology Unit, Department of Pediatrics, Geneva Children's Hospital, University Hospitals of Geneva, Geneva, Switzerland
- Faculty of Medicine, University of Geneva, Geneva, Switzerland
| | - Johan N Siebert
- Faculty of Medicine, University of Geneva, Geneva, Switzerland
- Division of Pediatric Emergency Medicine, Department of Pediatrics, Geneva Children's Hospital, Geneva University Hospitals, Geneva, Switzerland
| | - Mary-Anne Hartley
- Intelligent Global Health Research Group, Machine Learning and Optimization Laboratory, Swiss Federal Institute of Technology, Lausanne, Switzerland
- Laboratory of Intelligent Global Health Technologies, Bioinformatics and Data Science, Yale School of Medicine, New Haven, CT, United States
| | - Laurence Lacroix
- Faculty of Medicine, University of Geneva, Geneva, Switzerland
- Division of Pediatric Emergency Medicine, Department of Pediatrics, Geneva Children's Hospital, Geneva University Hospitals, Geneva, Switzerland
| |
Collapse
|
2
|
Faulkner SM, Drake RJ, Ogden M, Gardani M, Bee PE. A mixed methods expert opinion study on the optimal content and format for an occupational therapy intervention to improve sleep in schizophrenia spectrum disorders. PLoS One 2022; 17:e0269453. [PMID: 35666738 PMCID: PMC9170103 DOI: 10.1371/journal.pone.0269453] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/06/2021] [Accepted: 05/22/2022] [Indexed: 11/18/2022] Open
Abstract
Introduction People with schizophrenia spectrum disorder diagnoses commonly have poor sleep, which predicts various negative outcomes. The problems are diverse, including substantial circadian dysregulation, sleep-wake timing issues, hypersomnia (excessive sleep), and more classic insomnia. Methods This paper reports on a mixed methods expert opinion study based on the principles of Delphi methodology. The study examines and explores opinion on the optimal contents and format for an occupational therapy intervention to improve poor sleep in this population. Views of clinical and academic topic experts (n = 56), were elicited, examined and explored in three rounds, views from previous rounds being presented back to participants in subsequent rounds. Participants with relevant personal experience (n = 26) then rated and commented on suggestions, with a focus on acceptability. Descriptive statistics and graphs of ratings were triangulated with qualitative content analysis of free-text. Results Participants emphasised the central importance of intervention personalisation, although the manner and extent of personalisation suggested varied. Many components and domains were acknowledged as important, with the challenge being how to keep such an intervention simple, brief, and feasible for end-users, for sustainable implementation. The strongest consensus was to address evening routine, daytime activity, and environmental interventions. Relaxation, mindfulness, thermoregulation, sensory factors, and cognitive or psychological approaches were rated as less important. There was disagreement on whether to include time in bed restriction, and how to address napping, as well as how far to address medication timing. Clinicians and researchers advocated some version of stimulus control, but participants with personal experience reported low levels of acceptability for this, describing entirely negative experiences using ‘the 15-minute rule’ (part of stimulus control). Conclusion These results are informative for clinicians treating sleep problems in people with schizophrenia and related conditions, as well as for decision makers considering the potential contribution of the profession of occupational therapy toward sleep treatment.
Collapse
Affiliation(s)
- Sophie M. Faulkner
- Faculty of Biology, Medicine and Health, The University of Manchester, Manchester, United Kingdom
- Greater Manchester Mental Health NHS Foundation Trust, Manchester, United Kingdom
- * E-mail:
| | - Richard J. Drake
- Faculty of Biology, Medicine and Health, The University of Manchester, Manchester, United Kingdom
- Greater Manchester Mental Health NHS Foundation Trust, Manchester, United Kingdom
| | - Margaret Ogden
- Greater Manchester Mental Health NHS Foundation Trust, Manchester, United Kingdom
| | - Maria Gardani
- School of Health in Social Sciences, University of Edinburgh, Edinburgh, United Kingdom
| | - Penny E. Bee
- Faculty of Biology, Medicine and Health, The University of Manchester, Manchester, United Kingdom
| |
Collapse
|
3
|
Louis R, Satia I, Ojanguren I, Schleich F, Bonini M, Tonia T, Rigau D, Ten Brinke A, Buhl R, Loukides S, Kocks JWH, Boulet LP, Bourdin A, Coleman C, Needham K, Thomas M, Idzko M, Papi A, Porsbjerg C, Schuermans D, Soriano JB, Usmani OS. European Respiratory Society Guidelines for the Diagnosis of Asthma in Adults. Eur Respir J 2022; 60:2101585. [PMID: 35169025 DOI: 10.1183/13993003.01585-2021] [Citation(s) in RCA: 86] [Impact Index Per Article: 43.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/04/2021] [Accepted: 01/10/2022] [Indexed: 12/20/2022]
Abstract
Although asthma is very common affecting 5-10% of the population, the diagnosis of asthma in adults remains a challenge in the real world that results in both over- and under-diagnosis. A task force (TF) was set up by the European Respiratory Society to systematically review the literature on the diagnostic accuracy of tests used to diagnose asthma in adult patients and provide recommendation for clinical practice.The TF defined eight PICO (Population, Index, Comparator, and Outcome) questions that were assessed using the GRADE (Grading of Recommendations, Assessment, Development and Evaluation) approach, The TF utilised the outcomes to develop an evidenced-based diagnostic algorithm, with recommendations for a pragmatic guideline for everyday practice that was directed by real-life patient experiences.The TF support the initial use of spirometry followed, and if airway obstruction is present, by bronchodilator reversibility testing. If initial spirometry fails to show obstruction, further tests should be performed in the following order: FeNO, PEF variability or in secondary care, bronchial challenge. We present the thresholds for each test that are compatible with a diagnosis of asthma in the presence of current symptoms.The TF reinforce the priority to undertake spirometry and recognise the value of measuring blood eosinophils and serum IgE to phenotype the patient. Measuring gas trapping by body plethysmography in patients with preserved FEV1/FVC ratio deserves further attention. The TF draw attention on the difficulty of making a correct diagnosis in patients already receiving inhaled corticosteroids, the comorbidities that may obscure the diagnosis, the importance of phenotyping, and the necessity to consider the patient experience in the diagnostic process.
Collapse
Affiliation(s)
- Renaud Louis
- CHU de Liege University Hospital Centre Ville, Liege, Belgium
- First author, Task force chair
| | - Imran Satia
- McMaster University, Hamilton, Canada
- All authors contributed equally
| | - Inigo Ojanguren
- Vall d'Hebron University Hospital Barcelona, Barcelona, Spain
- All authors contributed equally
| | - Florence Schleich
- Department of Pulmonary Medicine, University of Liege, Liège, Belgium
- All authors contributed equally
| | - Matteo Bonini
- Sapienza University of Rome, Rome, Italy
- All authors contributed equally
| | - Thomy Tonia
- Institute of Social and Preventive Medicine, University of Bern, Bern, Switzerland
| | - David Rigau
- Iberoamerican Cochrane Centre, Barcelona, Spain
| | - Anne Ten Brinke
- CHU de Liege University Hospital Centre Ville, Liege, Belgium
| | - Roland Buhl
- Pulmonary Department, Mainz University Hospital, Mainz, Germany
| | | | | | - Louis-Philippe Boulet
- Pneumologie, Institut universitaire de cardiologie et de pneumologie de Québec - Université Laval, Quebec, Canada
| | | | | | | | - Mike Thomas
- Primary Care and Population Sciences Division, University of Southampton, Southampton, UK
| | - Marco Idzko
- Department of Respiratory Medicine, Medical University of Vienna, Vienna, Austria
| | - Alberto Papi
- Respiratory Medicine, University of Ferrara, Ferrara, Italy
| | - Celeste Porsbjerg
- Respiratory Medicine, Copenhagen University Hospital Bispebjerg, Copenhagen NV, Denmark
| | - Daniel Schuermans
- Respiratory Division, Academic Hospital UZBrussel, Brussels, Belgium
| | - Joan B Soriano
- Universidad Autónoma de Madrid, Hospital Universitario de la Princesa, Madrid, Spain
| | - Omar S Usmani
- Asthma Lab, National Heart and Lung Institute, London, UK
- Corresponding author, Task force co-chair
| |
Collapse
|
4
|
Louis R, Louis G, Bonhomme O. NOVELTY: a landmark study in phenotyping and endotyping chronic obstructive airway diseases in real clinical practice. Eur Respir J 2021; 58:58/3/2100627. [PMID: 34556532 DOI: 10.1183/13993003.00627-2021] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/02/2021] [Accepted: 03/02/2021] [Indexed: 11/05/2022]
Affiliation(s)
| | - Gilles Louis
- Dept of Public Health, University of Liege, Liege, Belgium
| | | |
Collapse
|
5
|
Gauld C, Dumas G, Darrason M, Salles N, Desvergnes P, Philip P, Micoulaud-Franchi JA. Médecine du sommeil personnalisée et syndrome d’apnées hypopnées obstructives du sommeil : entre précision et stratification, une proposition de clarification. ACTA ACUST UNITED AC 2020. [DOI: 10.1016/j.msom.2020.08.003] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/14/2022]
|
6
|
A systems approach to clinical oncology uses deep phenotyping to deliver personalized care. Nat Rev Clin Oncol 2019; 17:183-194. [DOI: 10.1038/s41571-019-0273-6] [Citation(s) in RCA: 25] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 08/30/2019] [Indexed: 02/06/2023]
|
7
|
Roche N, Antoniadis A, Hess D, Li PZ, Kelkel E, Leroy S, Pison C, Burgel PR, Aguilaniu B. Are there specific clinical characteristics associated with physician's treatment choices in COPD? Respir Res 2019; 20:189. [PMID: 31429756 PMCID: PMC6701115 DOI: 10.1186/s12931-019-1156-1] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/06/2019] [Accepted: 08/05/2019] [Indexed: 01/20/2023] Open
Abstract
Background The number of pharmacological agents and guidelines available for COPD has increased markedly but guidelines remain poorly followed. Understanding underlying clinical reasoning is challenging and could be informed by clinical characteristics associated with treatment prescriptions. Methods To determine whether COPD treatment choices by respiratory physicians correspond to specific patients’ features, this study was performed in 1171 patients who had complete treatment and clinical characterisation data. Multiple statistical models were applied to explain five treatment categories: A: no COPD treatment or short-acting bronchodilator(s) only; B: one long-acting bronchodilator (beta2 agonist, LABA or anticholinergic agent, LAMA); C: LABA+LAMA; D: a LABA or LAMA + inhaled corticosteroid (ICS); E: triple therapy (LABA+LAMA+ICS). Results Mean FEV1 was 60% predicted. Triple therapy was prescribed to 32.9% (treatment category E) of patients and 29.8% received a combination of two treatments (treatment categories C or D); ICS-containing regimen were present for 44% of patients altogether. Single or dual bronchodilation were less frequently used (treatment categories B and C: 19% each). While lung function was associated with all treatment decisions, exacerbation history, scores of clinical impact and gender were associated with the prescription of > 1 maintenance treatment. Statistical models could predict treatment decisions with a < 35% error rate. Conclusion In COPD, contrary to what has been previously reported in some studies, treatment choices by respiratory physicians appear rather rational since they can be largely explained by the patients’ characteristics proposed to guide them in most recommendations. Electronic supplementary material The online version of this article (10.1186/s12931-019-1156-1) contains supplementary material, which is available to authorized users.
Collapse
Affiliation(s)
- Nicolas Roche
- Service de Pneumologie, Hôpitaux Universitaires Paris Centre, Hôpital Cochin, AP-HP and Université Paris Descartes, Sorbonne Paris Cité, 75014, Paris, France. .,Pneumologie et Soins Intensifs Respiratoires, Hôpital Cochin, 27, rue du Fbg St Jacques, 75014, Paris, France.
| | - Anestis Antoniadis
- Laboratoire LJK, Département de statistiques, Université Grenoble Alpes, Grenoble, France
| | - David Hess
- Programme Colibri-Pneumo, ACCPP (Association pour la Complémentarité des Connaissances et des Pratiques de la Pneumologie), Grenoble, France
| | - Pei Zhi Li
- Respiratory Epidemiology and Clinical Research Unit, Montreal Chest Institute, McGill University, Montreal, Canada
| | - Eric Kelkel
- Service de pneumologie, Pôle médecines spécialisées et cancérologie, Centre hospitalier général, Chambéry, France
| | - Sylvie Leroy
- Department of Pulmonary Medicine and Oncology, CHU de Nice, University Hospital Federation OncoAge, Nice, France.,CNRS UMR 7275 - Institut de Pharmacologie Moléculaire et Cellulaire, Université de Nice Sophia Antipolis, Nice, France
| | - Christophe Pison
- Service Hospitalier Universitaire Pneumologie Physiologie, Pôle Thorax et Vaisseaux, Centre Hospitalier Universitaire Grenoble Alpes, Inserm 1055, Université Grenoble Alpes, Grenoble, France
| | - Pierre-Régis Burgel
- Service de Pneumologie, Hôpitaux Universitaires Paris Centre, Hôpital Cochin, AP-HP and Université Paris Descartes, Sorbonne Paris Cité, 75014, Paris, France
| | - Bernard Aguilaniu
- Université Grenoble Alpes and Programme Colibri-Pneumo (aCCPP), Grenoble, France
| | | |
Collapse
|
8
|
Roche N, Martin C, Burgel PR. [Personalised COPD care: Where are we going?]. REVUE DE PNEUMOLOGIE CLINIQUE 2018; 74:315-326. [PMID: 30316649 DOI: 10.1016/j.pneumo.2018.09.003] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/08/2023]
Abstract
The concept of personalised medicine is recent but the underlying notions are not new: knowing how to adapt care to patients' characteristics is one of the components of the "art of medicine". The advances of science allow to refine considerably the applications of the concept in many fields of medicine including COPD: research has identified phenotypes, endotypes and treatable traits. Personalisation can be applied to all components of care. For instance, the decision to perform screening spirometry relies not only on risk factors (age, smoking, other exposures) but also on symptoms. Assessment of comorbidities often associated with COPD is based on risk factors and their combinations, variable between individuals. Rehabilitation and its components are in essence highly individualised, which a major condition for their success. Last but not least, personalisation of pharmacological therapy, which has long been rather poor, could not benefit from biomarkers of interest (predictive of response), such as blood eosinophil count. Practical strategies using these still need to be established, and new biomarkers may usefully enrich the collection!
Collapse
Affiliation(s)
- N Roche
- EA2511, service de pneumologie, université Paris Descartes, hôpital Cochin, hôpitaux universitaires Paris Centre, AP-HP 5, 27, rue du Faubourg-Saint-Jacques, 75014 Paris, France.
| | - C Martin
- EA2511, service de pneumologie, université Paris Descartes, hôpital Cochin, hôpitaux universitaires Paris Centre, AP-HP 5, 27, rue du Faubourg-Saint-Jacques, 75014 Paris, France
| | - P-R Burgel
- EA2511, service de pneumologie, université Paris Descartes, hôpital Cochin, hôpitaux universitaires Paris Centre, AP-HP 5, 27, rue du Faubourg-Saint-Jacques, 75014 Paris, France
| |
Collapse
|