Construction of prediction models for novel subtypes in patients with arteriosclerosis obliterans undergoing endovascular therapy: an unsupervised machine learning study.
Arteriosclerosis obliterans
Cluster analysis
Endovascular therapy
Machine learning
Prediction model
Journal
Journal of cardiothoracic surgery
ISSN: 1749-8090
Titre abrégé: J Cardiothorac Surg
Pays: England
ID NLM: 101265113
Informations de publication
Date de publication:
25 Jun 2024
25 Jun 2024
Historique:
received:
09
01
2024
accepted:
15
06
2024
medline:
26
6
2024
pubmed:
26
6
2024
entrez:
25
6
2024
Statut:
epublish
Résumé
Arteriosclerosis obliterans (ASO) is a chronic arterial disease that can lead to critical limb ischemia. Endovascular therapy is increasingly used for limb salvage in ASO patients, but the outcomes vary. The development of prediction models using unsupervised machine learning may lead to the identification of novel subtypes to guide patient prognosis and treatment. This retrospective study analyzed clinical data from 448 patients with ASOs who underwent endovascular therapy. Unsupervised machine learning algorithms were employed to identify subgroups. To validate the precision of the clustering outcomes, an analysis of the postoperative results of the clusters was conducted. A prediction model was constructed using binary logistic regression. Two distinct subgroups were identified by unsupervised machine learning and characterized by differing patterns of clinical features. Patients in Cluster 2 had significantly worse conditions and prognoses than those in Cluster 1. For the novel ASO subtypes, a nomogram was developed using six predictive factors, namely, platelet count, ankle brachial index, Rutherford category, operation method, hypertension, and diabetes status. The nomogram achieved excellent discrimination for predicting membership in the two identified clusters, with an area under the curve of 0.96 and 0.95 in training cohort and internal test cohort. This study demonstrated that unsupervised machine learning can reveal novel phenotypic subgroups of patients with varying prognostic risk who underwent endovascular therapy. The prediction model developed could support clinical decision-making and risk counseling for this complex patient population. Further external validation is warranted to assess the generalizability of the findings.
Sections du résumé
BACKGROUND
BACKGROUND
Arteriosclerosis obliterans (ASO) is a chronic arterial disease that can lead to critical limb ischemia. Endovascular therapy is increasingly used for limb salvage in ASO patients, but the outcomes vary. The development of prediction models using unsupervised machine learning may lead to the identification of novel subtypes to guide patient prognosis and treatment.
METHODS
METHODS
This retrospective study analyzed clinical data from 448 patients with ASOs who underwent endovascular therapy. Unsupervised machine learning algorithms were employed to identify subgroups. To validate the precision of the clustering outcomes, an analysis of the postoperative results of the clusters was conducted. A prediction model was constructed using binary logistic regression.
RESULTS
RESULTS
Two distinct subgroups were identified by unsupervised machine learning and characterized by differing patterns of clinical features. Patients in Cluster 2 had significantly worse conditions and prognoses than those in Cluster 1. For the novel ASO subtypes, a nomogram was developed using six predictive factors, namely, platelet count, ankle brachial index, Rutherford category, operation method, hypertension, and diabetes status. The nomogram achieved excellent discrimination for predicting membership in the two identified clusters, with an area under the curve of 0.96 and 0.95 in training cohort and internal test cohort.
CONCLUSION
CONCLUSIONS
This study demonstrated that unsupervised machine learning can reveal novel phenotypic subgroups of patients with varying prognostic risk who underwent endovascular therapy. The prediction model developed could support clinical decision-making and risk counseling for this complex patient population. Further external validation is warranted to assess the generalizability of the findings.
Identifiants
pubmed: 38918804
doi: 10.1186/s13019-024-02913-6
pii: 10.1186/s13019-024-02913-6
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
370Subventions
Organisme : National Natural Science Foundation of China
ID : 81960091
Informations de copyright
© 2024. The Author(s).
Références
Lian W, Nie H, Yuan Y, Wang K, Chen W, Ding L. Clinical Significance of Endothelin-1 And C Reaction Protein in Restenosis After the Intervention of Lower Extremity Arteriosclerosis Obliterans. Journal of investigative surgery : the official journal of the Academy of Surgical Research. 2021;34(7):765–70.
doi: 10.1080/08941939.2019.1690600
pubmed: 31996054
Takahara M. Diabetes Mellitus and Lower Extremity Peripheral Artery Disease. JMA journal. 2021;4(3):225–31.
doi: 10.31662/jmaj.2021-0042
pubmed: 34414316
pmcid: 8355746
Zheng YH, Song XT. Progress and prospect of the treatment of lower extremity arteriosclerosis obliterans. Zhonghua wai ke za zhi [Chinese journal of surgery]. 2021;59(12):961–4.
pubmed: 34865445
Eckhardt CM, Madjarova SJ, Williams RJ, Ollivier M, Karlsson J, Pareek A, et al. Unsupervised machine learning methods and emerging applications in healthcare. Knee Surg Sports Traumatol Arthrosc. 2023;31(2):376–81.
doi: 10.1007/s00167-022-07233-7
pubmed: 36378293
Conte MS, Pomposelli FB, Clair DG, Geraghty PJ, McKinsey JF, Mills JL, et al. Society for Vascular Surgery practice guidelines for atherosclerotic occlusive disease of the lower extremities: management of asymptomatic disease and claudication. J Vasc Surg. 2015;61(3 Suppl):2S-41S.
doi: 10.1016/j.jvs.2014.12.009
pubmed: 25638515
Hawkins KE, Valentine RJ, Duke JM, Wang Q, Reed AB. Ankle-brachial index use in peripheral vascular interventions for claudication. J Vasc Surg. 2022;76(1):196–201.
Rieß HC, Debus ES, Schwaneberg T, Hischke S, Maier J, Bublitz M, et al. Indicators of outcome quality in peripheral arterial disease revascularisations - a Delphi expert consensus. Vasa. 2018;47(6):491–7.
doi: 10.1024/0301-1526/a000720
pubmed: 29856270
Biagioni RB, Brandão GD, Biagioni LC, Nasser F, Burihan MC, Ingrund JC. Endovascular treatment of TransAtlantic Inter-Society Consensus II D femoropopliteal lesions in patients with critical limb ischemia. J Vasc Surg. 2019;69(5):1510–8.
doi: 10.1016/j.jvs.2018.08.176
pubmed: 30611581
Chantraine F, Schreiber C, Pereira JAC, Kaps J, Dierick F. Classification of stiff-knee gait kinematic severity after stroke using retrospective k-means clustering algorithm. J Clin Med. 2022;11(21):6270.
Garcia-Rudolph A, Garcia-Molina A, Opisso E, Tormos MJ. Personalized Web-Based Cognitive Rehabilitation Treatments for Patients with Traumatic Brain Injury: Cluster Analysis. JMIR Med Inform. 2020;8(10):e16077.
doi: 10.2196/16077
pubmed: 33021482
pmcid: 7576523
Mationg MLS, Williams GM, Tallo VL, Olveda RM, Aung E, Alday P, et al. Determining the Impact of a School-Based Health Education Package for Prevention of Intestinal Worm Infections in the Philippines: Protocol for a Cluster Randomized Intervention Trial. JMIR Res Protoc. 2020;9(6):e18419.
doi: 10.2196/18419
pubmed: 32584263
pmcid: 7381005
Lovmar L, Ahlford A, Jonsson M, Syvänen AC. Silhouette scores for assessment of SNP genotype clusters. BMC Genomics. 2005;6:35.
doi: 10.1186/1471-2164-6-35
pubmed: 15760469
pmcid: 555759
Huang YQ, Liang CH, He L, Tian J, Liang CS, Chen X, et al. Development and Validation of a Radiomics Nomogram for Preoperative Prediction of Lymph Node Metastasis in Colorectal Cancer. J Clin Oncol. 2016;34(18):2157–64.
doi: 10.1200/JCO.2015.65.9128
pubmed: 27138577
Kim H, Kim YH, Kim SJ, Choi MT. Pathological gait clustering in post-stroke patients using motion capture data. Gait Posture. 2022;94:210–6.
doi: 10.1016/j.gaitpost.2022.03.007
pubmed: 35367849
Eshaghi A, Young AL, Wijeratne PA, Prados F, Arnold DL, Narayanan S, et al. Identifying multiple sclerosis subtypes using unsupervised machine learning and MRI data. Nat Commun. 2021;12(1):2078.
doi: 10.1038/s41467-021-22265-2
pubmed: 33824310
pmcid: 8024377
Kung B, Chiang M, Perera G, Pritchard M, Stewart R. Unsupervised Machine Learning to Identify Depressive Subtypes. Healthc Inform Res. 2022;28(3):256–66.
doi: 10.4258/hir.2022.28.3.256
pubmed: 35982600
pmcid: 9388921
Su QH, Chiang KN. Predicting Wafer-Level Package Reliability Life Using Mixed Supervised and Unsupervised Machine Learning Algorithms. Materials (Basel, Switzerland). 2022;15(11):3897.
doi: 10.3390/ma15113897
pubmed: 35683193
pmcid: 9182149
Marriott H, Kabiljo R, Hunt GP, Khleifat AA, Jones A, Troakes C, et al. Unsupervised machine learning identifies distinct ALS molecular subtypes in post-mortem motor cortex and blood expression data. Acta Neuropathol Commun. 2023;11(1):208.
doi: 10.1186/s40478-023-01686-8
pubmed: 38129934
pmcid: 10734072
Bhattacharyya T, Nayak S, Goswami S, Gadiyaram V, Mathew OK, Sowdhamini R. PASS2.7: a database containing structure-based sequence alignments and associated features of protein domain superfamilies from SCOPe. Database. 2022;2022:baac025.
doi: 10.1093/database/baac025
pubmed: 35411388
pmcid: 9216583
Haug CJ, Drazen JM. Artificial Intelligence and Machine Learning in Clinical Medicine, 2023. N Engl J Med. 2023;388(13):1201–8.
doi: 10.1056/NEJMra2302038
pubmed: 36988595
Tang YD, Wang W, Yang M, Zhang K, Chen J, Qiao S, et al. Randomized Comparisons of Double-Dose Clopidogrel or Adjunctive Cilostazol Versus Standard Dual Antiplatelet in Patients With High Posttreatment Platelet Reactivity: Results of the CREATIVE Trial. Circulation. 2018;137(21):2231–45.
doi: 10.1161/CIRCULATIONAHA.117.030190
pubmed: 29420189
Lee MS, Rha SW, Han SK, Choi BG, Choi SY, Ali J, et al. Comparison of diabetic and non-diabetic patients undergoing endovascular revascularization for peripheral arterial disease. J Invasive Cardiol. 2015;27(3):167–71.
pubmed: 25740971
Bakogiannis C, Sachse M, Stamatelopoulos K, Stellos K. Platelet-derived chemokines in inflammation and atherosclerosis. Cytokine. 2019;122:154157.
doi: 10.1016/j.cyto.2017.09.013
pubmed: 29198385
Habib A, Finn AV. Endothelialization of drug eluting stents and its impact on dual anti-platelet therapy duration. Pharmacol Res. 2015;93:22–7.
doi: 10.1016/j.phrs.2014.12.003
pubmed: 25533811
Zhu Z, Chen L, Yu W, Gao C, He B. Numerical Analysis of Stress Force on Vessel Walls in Atherosclerotic Plaque Removal through Coronary Rotational Atherectomy. Micromachines. 2023;14(12):2148.
doi: 10.3390/mi14122148
pubmed: 38138317
pmcid: 10745720
Sanon O, Carnevale M, Indes J, Gao Q, Lipsitz E, Koleilat I. Incidence of procedure-related complications in patients treated with atherectomy in the femoropopliteal and tibial vessels in the vascular quality initiative. J Endovasc Ther: an official journal of the International Society of Endovascular Specialists. 2023;30(5):693–702.
Tepe G, Brodmann M, Micari A, Scheinert D, Choi D, Menk J, et al. 5-Year Outcomes of Drug-Coated Balloons for Peripheral Artery In-Stent Restenosis, Long Lesions, and CTOs. JACC Cardiovasc Interv. 2023;16(9):1065–78.
doi: 10.1016/j.jcin.2023.03.032
pubmed: 37164605
Barbarawi M, Qazi AH, Lee J, Barbarawi O, Al-Abdouh A, Mhanna M, et al. Meta-analysis comparing drug-coated balloons and percutaneous transluminal angioplasty for infrapopliteal artery disease. Am J Cardiol. 2022;183:115–21.