Stepping Up the Personalized Approach in COPD with Machine Learning

Evgeni      Mekov; Marc      Miravitlles; Marko      Topalovic; Aran      Singanayagam; Rosen      Petkov

Abstract

Introduction: There is increasing interest in the application of artificial intelligence (AI) and machine learning (ML) in all fields of medicine to facilitate greater personalisation of management.

Methods: ML could be the next step of personalized medicine in chronic obstructive pulmonary disease (COPD) by giving the exact risk (risk for exacerbation, death, etc.) of every patient (based on his/her parameters like lung function, clinical data, demographics, previous exacerbations, etc.), thus providing a prognosis/risk for the specific patient based on individual characteristics (individual approach).

Result: ML algorithm might utilise some traditional risk factors along with some others that may be location-specific (e.g. the risk of exacerbation thatmay be related to ambient pollution but that could vary massively between different countries, or between different regions of a particular country).

Conclusion: This is a step forward from the commonly used assignment of patients to a specific group for which prognosis/risk data are available (group approach).

[1]
 Global Initiative for Chronic Obstructive Lung Disease. Global strategy for the diagnosis, management and prevention of COPD. 2023. Available from: http://www.goldcopd.org/ (Accessed on 26 Mar 2023).

[2]
Mekov E, Miravitlles M, Petkov R. Artificial intelligence and machine learning in respiratory medicine. Expert Rev Respir Med  2020; 14(6): 559-64.
 [http://dx.doi.org/10.1080/17476348.2020.1743181] [PMID: 32166988]

[3]
James G, Witten D, Hastie T, Tibshirani R.  An introduction to statistical learning: With applications in R. Springer 2013. Available from: https://faculty.marshall.usc.edu/gareth-james/ISL/ (Access ed on: 20 May 2022).

[4]
Sethi S. Personalised medicine in exacerbations of copd: The beginnings. Eur Respir J  2012; 40(6): 1318-9.
 [http://dx.doi.org/10.1183/09031936.00136412] [PMID: 23204018]

[5]
Agusti A. The path to personalised medicine in COPD. Thorax  2014; 69(9): 857-64.
 [http://dx.doi.org/10.1136/thoraxjnl-2014-205507] [PMID: 24781218]

[6]
McDonald VM, Fingleton J, Agusti A, et al. participants of the Treatable Traits Down Under International Workshop; Treatable Traits Down Under International Workshop participants. Treatable traits: A new paradigm for 21st century management of chronic airway diseases: Treatable traits down under international workshop report. Eur Respir J  2019; 53(5): 1802058.
 [http://dx.doi.org/10.1183/13993003.02058-2018] [PMID: 30846468]

[7]
Franssen FME, Alter P, Bar N, et al. Perlth COPD: Where are we? Int J Chron Obstruct Pulmon Dis  2019; 14: 1465-84.
 [http://dx.doi.org/10.2147/COPD.S175706] [PMID: 31371934]

[8]
Verstraete K, Das N, Gyselinck I, De Vos M, Janssens W. Machine learning for estimating individual treatment effects in randomized controlled trials. Eur Respir J  2021; 58(65): PA3450.

[9]
Gonem S, Janssens W, Das N, Topalovic M. Applications of artificial intelligence and machine learning in respiratory medicine. Thorax  2020; 75(8): 695-701.
 [http://dx.doi.org/10.1136/thoraxjnl-2020-214556] [PMID: 32409611]

[10]
Rokach L. Ensemble-based classifiers. Artif Intell Rev  2010; 33(1-2): 1-39.
 [http://dx.doi.org/10.1007/s10462-009-9124-7]

[11]
Mekov E, Nuñez A, Sin DD, et al. Update on asthma–copd overlap (aco): A narrative review. Int J Chron Obstruct Pulmon Dis  2021; 16: 1783-99.
 [http://dx.doi.org/10.2147/COPD.S312560] [PMID: 34168440]

[12]
Fernández-Granero MA, Sánchez-Morillo D, León-Jiménez A, Crespo LF. Automatic prediction of chronic obstructive pulmonary disease exacerbations through home telemonitoring of symptoms. Biomed Mater Eng  2014; 24(6): 3825-32.
 [http://dx.doi.org/10.3233/BME-141212] [PMID: 25227099]

[13]
Kor CT, Li YR, Lin PR, Lin SH, Wang BY, Lin CH. Explainable machine learning model for predicting first-time acute exacerbation in patients with chronic obstructive pulmonary disease. J Pers Med  2022; 12(2): 228.
 [http://dx.doi.org/10.3390/jpm12020228] [PMID: 35207716]

[14]
Hussain A, Choi HE, Kim HJ, Aich S, Saqlain M, Kim HC. Forecast the exacerbation in patients of chronic obstructive pulmonary disease with clinical indicators using machine learning techniques. Diagnostics  2021; 11(5): 829.
 [http://dx.doi.org/10.3390/diagnostics11050829] [PMID: 34064395]

[15]
Zhudenkov K, Palmér R, Jauhiainen A, et al. Longitudinal FEV1 and exacerbation risk in copd: Quantifying the association using joint modelling. Int J Chron Obstruct Pulmon Dis  2021; 16: 101-11.
 [http://dx.doi.org/10.2147/COPD.S284720] [PMID: 33488073]

[16]
Dong H, Hao Y, Li D, et al. Risk factors for acute exacerbation of chronic obstructive pulmonary disease in industrial regions of china: A multicenter cross-sectional study. Int J Chron Obstruct Pulmon Dis  2020; 15: 2249-56.
 [http://dx.doi.org/10.2147/COPD.S270729] [PMID: 33061342]

[17]
Zhang H, Wu F, Yi H, et al. Gender differences in chronic obstructive pulmonary disease symptom clusters. Int J Chron Obstruct Pulmon Dis  2021; 16: 1101-7.
 [http://dx.doi.org/10.2147/COPD.S302877] [PMID: 33907396]

[18]
Fermont JM, Masconi KL, Jensen MT, et al. biomarkers and clinical outcomes in COPD: A systematic review and meta-analysis. Thorax  2019; 74(5): 439-46.
 [http://dx.doi.org/10.1136/thoraxjnl-2018-211855] [PMID: 30617161]

[19]
Cavaillès A, Brinchault-Rabin G, Dixmier A, et al. Comorbidities of COPD. Eur Respir Rev  2013; 22(130): 454-75.
 [http://dx.doi.org/10.1183/09059180.00008612] [PMID: 24293462]

[20]
Nuñez A, Marras V, Harlander M, et al. Association between routine blood biomarkers and clinical phenotypes and exacerbations in chronic obstructive pulmonary disease. Int J Chron Obstruct Pulmon Dis  2020; 15: 681-90.
 [http://dx.doi.org/10.2147/COPD.S240720] [PMID: 32280207]

[21]
Skoczyński S, Krzyżak D, Studnicka A, et al. Chronic obstructive pulmonary disease and platelet count. Adv Exp Med Biol  2019; 1160: 19-23.
 [http://dx.doi.org/10.1007/5584_2019_379] [PMID: 31049844]

[22]
Lu FY, Chen R, Li N, et al. Neutrophil-to-lymphocyte ratio predicts clinical outcome of severe acute exacerbation of COPD in frequent exacerbators. Int J Chron Obstruct Pulmon Dis  2021; 16: 341-9.
 [http://dx.doi.org/10.2147/COPD.S290422] [PMID: 33633446]

[23]
Celli BR, Cote CG, Marin JM, et al. The body-mass index, airflow obstruction, dyspnea, and exercise capacity index in chronic obstructive pulmonary disease. N Engl J Med  2004; 350(10): 1005-12.
 [http://dx.doi.org/10.1056/NEJMoa021322] [PMID: 14999112]

[24]
Waatevik M, Johannessen A, Gomez Real F, et al. Oxygen desaturation in 6-min walk test is a risk factor for adverse outcomes in COPD. Eur Respir J  2016; 48(1): 82-91.
 [http://dx.doi.org/10.1183/13993003.00975-2015] [PMID: 27076586]

[25]
Agrawal RK, Gupta NK, Srivastav AB, Ved ML. Echocardiographic evaluation of heart in chronic obstructive pulmonary disease patient and its co-relation with the severity of disease. Lung India  2011; 28(2): 105-9.
 [http://dx.doi.org/10.4103/0970-2113.80321] [PMID: 21712919]

[26]
Mekov E, Yanev N, Kurtelova N, et al. Diaphragmatic movement at rest and after exertion: A non-invasive and easy to obtain prognostic marker in COPD. Int J Chron Obstruct Pulmon Dis  2022; 17: 1041-50.
 [http://dx.doi.org/10.2147/COPD.S361235] [PMID: 35547783]

[27]
Rasch-Halvorsen Ø, Hassel E, Brumpton BM, et al. Lung function and peak oxygen uptake in chronic obstructive pulmonary disease phenotypes with and without emphysema. PLoS One  2021; 16(5): e0252386.
 [http://dx.doi.org/10.1371/journal.pone.0252386] [PMID: 34043708]

Cite As

Current Respiratory Medicine Reviews

Stepping Up the Personalized Approach in COPD with Machine Learning

Abstract