1
|
Li B, Verma R, Beaton D, Tamim H, Hussain MA, Hoballah JJ, Lee DS, Wijeysundera DN, de Mestral C, Mamdani M, Al-Omran M. Predicting outcomes following lower extremity open revascularization using machine learning. Sci Rep 2024; 14:2899. [PMID: 38316811 PMCID: PMC10844206 DOI: 10.1038/s41598-024-52944-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/11/2023] [Accepted: 01/25/2024] [Indexed: 02/07/2024] Open
Abstract
Lower extremity open revascularization is a treatment option for peripheral artery disease that carries significant peri-operative risks; however, outcome prediction tools remain limited. Using machine learning (ML), we developed automated algorithms that predict 30-day outcomes following lower extremity open revascularization. The National Surgical Quality Improvement Program targeted vascular database was used to identify patients who underwent lower extremity open revascularization for chronic atherosclerotic disease between 2011 and 2021. Input features included 37 pre-operative demographic/clinical variables. The primary outcome was 30-day major adverse limb event (MALE; composite of untreated loss of patency, major reintervention, or major amputation) or death. Our data were split into training (70%) and test (30%) sets. Using tenfold cross-validation, we trained 6 ML models. Overall, 24,309 patients were included. The primary outcome of 30-day MALE or death occurred in 2349 (9.3%) patients. Our best performing prediction model was XGBoost, achieving an area under the receiver operating characteristic curve (95% CI) of 0.93 (0.92-0.94). The calibration plot showed good agreement between predicted and observed event probabilities with a Brier score of 0.08. Our ML algorithm has potential for important utility in guiding risk mitigation strategies for patients being considered for lower extremity open revascularization to improve outcomes.
Collapse
Affiliation(s)
- Ben Li
- Department of Surgery, University of Toronto, Toronto, Canada
- Division of Vascular Surgery, St. Michael's Hospital, Unity Health Toronto, University of Toronto, 30 Bond Street, Toronto, ON, M5B 1W8, Canada
- Institute of Medical Science, University of Toronto, Toronto, Canada
- Temerty Centre for Artificial Intelligence Research and Education in Medicine (T-CAIREM), University of Toronto, Toronto, Canada
| | - Raj Verma
- School of Medicine, Royal College of Surgeons in Ireland, University of Medicine and Health Sciences, Dublin, Ireland
| | - Derek Beaton
- Data Science & Advanced Analytics, Unity Health Toronto, University of Toronto, Toronto, Canada
| | - Hani Tamim
- Faculty of Medicine, Clinical Research Institute, American University of Beirut Medical Center, Beirut, Lebanon
- College of Medicine, Alfaisal University, Riyadh, Kingdom of Saudi Arabia
| | - Mohamad A Hussain
- Division of Vascular and Endovascular Surgery and the Center for Surgery and Public Health, Brigham and Women's Hospital, Harvard Medical School, Boston, USA
| | - Jamal J Hoballah
- Division of Vascular and Endovascular Surgery, Department of Surgery, American University of Beirut Medical Center, Beirut, Lebanon
| | - Douglas S Lee
- Division of Cardiology, Peter Munk Cardiac Centre, University Health Network, Toronto, Canada
- Institute of Health Policy, Management and Evaluation, University of Toronto, Toronto, Canada
- ICES, University of Toronto, Toronto, Canada
| | - Duminda N Wijeysundera
- Institute of Health Policy, Management and Evaluation, University of Toronto, Toronto, Canada
- ICES, University of Toronto, Toronto, Canada
- Department of Anesthesia, St. Michael's Hospital, Unity Health Toronto, Toronto, Canada
- Li Ka Shing Knowledge Institute, St. Michael's Hospital, Unity Health Toronto, Toronto, Canada
| | - Charles de Mestral
- Department of Surgery, University of Toronto, Toronto, Canada
- Division of Vascular Surgery, St. Michael's Hospital, Unity Health Toronto, University of Toronto, 30 Bond Street, Toronto, ON, M5B 1W8, Canada
- Institute of Health Policy, Management and Evaluation, University of Toronto, Toronto, Canada
- ICES, University of Toronto, Toronto, Canada
- Li Ka Shing Knowledge Institute, St. Michael's Hospital, Unity Health Toronto, Toronto, Canada
| | - Muhammad Mamdani
- Institute of Medical Science, University of Toronto, Toronto, Canada
- Temerty Centre for Artificial Intelligence Research and Education in Medicine (T-CAIREM), University of Toronto, Toronto, Canada
- Data Science & Advanced Analytics, Unity Health Toronto, University of Toronto, Toronto, Canada
- Institute of Health Policy, Management and Evaluation, University of Toronto, Toronto, Canada
- ICES, University of Toronto, Toronto, Canada
- Li Ka Shing Knowledge Institute, St. Michael's Hospital, Unity Health Toronto, Toronto, Canada
- Leslie Dan Faculty of Pharmacy, University of Toronto, Toronto, Canada
| | - Mohammed Al-Omran
- Department of Surgery, University of Toronto, Toronto, Canada.
- Division of Vascular Surgery, St. Michael's Hospital, Unity Health Toronto, University of Toronto, 30 Bond Street, Toronto, ON, M5B 1W8, Canada.
- Institute of Medical Science, University of Toronto, Toronto, Canada.
- Temerty Centre for Artificial Intelligence Research and Education in Medicine (T-CAIREM), University of Toronto, Toronto, Canada.
- College of Medicine, Alfaisal University, Riyadh, Kingdom of Saudi Arabia.
- Li Ka Shing Knowledge Institute, St. Michael's Hospital, Unity Health Toronto, Toronto, Canada.
- Department of Surgery, King Faisal Specialist Hospital and Research Center, Riyadh, Kingdom of Saudi Arabia.
| |
Collapse
|
2
|
Ingwersen M, Kunstmann I, Oswald C, Best N, Weisser B, Teichgräber U. Exercise Training for Patients With Peripheral Arterial Occlusive Disease. DEUTSCHES ARZTEBLATT INTERNATIONAL 2023; 120:879-885. [PMID: 38019155 PMCID: PMC10859744 DOI: 10.3238/arztebl.m2023.0231] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/17/2023] [Revised: 10/18/2023] [Accepted: 10/18/2023] [Indexed: 11/30/2023]
Abstract
BACKGROUND One-third of all persons with peripheral arterial occlusive disease (PAOD) suffer from intermittent claudication. Exercise training under appropriate supervision is recommended in the pertinent guidelines, but physicians order it too rarely, and so-called vascular exercise groups are not available everywhere. This situation needs improvement in view of the impor - tance of walking ability and cardiorespiratory fitness for patients' quality of life and long-term disease outcome. METHODS We review the scientific evidence on exercise training and on ways to lower barriers to the ordering of exercise training and to patient participation, on the basis of pertinent articles retrieved by a search of PubMed and in specialized sports science journals. RESULTS 10 meta-analyses, 12 randomized controlled trials (RCTs), and 7 cohort studies were considered for this review. Largescale cohort studies have shown that exercise is associated with a lower risk of death (relative risk 0.65-0.78 after 12 months of exercise training, compared to an inactive lifestyle). Exercise training also improves the maximal walking distance by a mean of 136 m (training at home) or 180-310 m (supervised training). An additional improvement by a mean of 282 m can be expected from a combination of exercise training and endovascular revascularization. Further behavior-modifying interventions, such as goal-setting, planning, and feedback, increase both the maximum walking distance and the weekly duration of exercise. CONCLUSION Exercise improves walking ability and lowers mortality. To attract patients with intermittent claudication to exercise training, a broad assortment of analog, digital and telemetric tools and a dense network of vascular exercise groups should be made available, along with regular contact between physicians and patients.
Collapse
Affiliation(s)
- Maja Ingwersen
- Institute of Diagnostic and Interventional Radiology, Jena University Hospital, Jena, Germany
| | - Ina Kunstmann
- Institute of Diagnostic and Interventional Radiology, Jena University Hospital, Jena, Germany
| | - Carolin Oswald
- Institute of Diagnostic and Interventional Radiology, Jena University Hospital, Jena, Germany
| | - Norman Best
- Institute of Physical and Rehabilitation Medicine, Sophien and Hufeland Hospital Weimar, Academic Teaching Hospital, University of Jena, Jena, Germany
| | - Burkhard Weisser
- Institute of Sports Science, Department of Sports Medicine, Kiel University, Kiel, Germany
| | - Ulf Teichgräber
- Institute of Diagnostic and Interventional Radiology, Jena University Hospital, Jena, Germany
| |
Collapse
|
4
|
Dovzhanskiy D, Behrendt CA, Görtz H, Uhl C, Classen S, Marchiori E, Neufang A, Rümenapf G, Stavroulakis K, Rother U, Jaron V, Kunert K. Das große Verbesserungspotenzial in der multimodalen Basisbehandlung der peripheren arteriellen Verschlusskrankheit (pAVK): ein Aufruf zum flächendeckenden Ausbau der pAVK-Gehtrainingsgruppen in Deutschland. GEFÄSSCHIRURGIE 2023. [DOI: 10.1007/s00772-022-00962-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/05/2023]
Abstract
ZusammenfassungDas Gehtraining gehört zu den wichtigsten Säulen der Behandlung der peripheren arteriellen Verschlusskrankheit (pAVK). Das Gehtraining in Gruppen unter Anleitung ist dabei besonders effektiv. In Deutschland ist ein flächendeckendes Angebot von Gehtrainingsgruppen nicht verfügbar. Von der Deutschen Gesellschaft für Gefäßchirurgie und Gefäßmedizin (DGG e. V.), vertreten durch die Kommission „pAVK und diabetischer Fuß“ wurde daher eine Kampagne zur bundesweiten Förderung des Aufbaus von lokalen Gehtrainingsgruppen gestartet. In diesem Artikel wird an Gefäßmediziner appelliert, bei sich vor Ort die Gehtrainingsgruppen auszubauen und mitzugestalten. Die Wege zum Ausbau solcher Gehtrainingsgruppen werden beschrieben.
Collapse
|
5
|
Süss JD, Gawenda M. Primärtherapie der Claudicatio intermittens – Anspruch und Wirklichkeit. Zentralbl Chir 2022; 147:453-459. [DOI: 10.1055/a-1798-0602] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/18/2022]
Abstract
ZusammenfassungDie narrative Übersichtsarbeit fasst die Studienlage zum Thema Gehtraining bei Patienten mit Claudicatio intermittens (CI) zusammen. Eindringlich wird auf die evidenzbasierten
Leitlinienempfehlungen und die dahinterstehenden Studien eingegangen. Aspekte zum angiomorphologischen Befund, zu Patientenadhärenz, Langzeitwirkung, Studienqualität und ihre
Vergleichbarkeit werden diskutiert. Der Problematik in der Versorgungsrealität mit Abweichungen von den Leitlinien und der oftmals invasiven Erstlinientherapie des PAVK-IIb-Patienten werden
besondere Bedeutung geschenkt. Dabei wird die Rolle des Rehasports und die gesundheitspolititsche Bedeutung von Gehtraining in Deutschland erörtert. Gründe für die fehlende Leitlinientreue
und deren Umsetzung im Gesundheitssystem werden analysiert. Dementsprechend werden Handlungsempfehlungen, in Anlehnung an internationale Erfahrungen (Niederlande, Dänemark), zur Besserung
der Situation in Deutschland formuliert.
Collapse
Affiliation(s)
- Jan David Süss
- Gefäßchirurgie, St-Antonius-Hospital gGmbH, Eschweiler, Deutschland
| | - Michael Gawenda
- Gefäßchirurgie, St-Antonius-Hospital gGmbH, Eschweiler, Deutschland
| |
Collapse
|
6
|
Torii R, Yacoub MH. CT-based fractional flow reserve: development and expanded application. Glob Cardiol Sci Pract 2021; 2021:e202120. [PMID: 34805378 PMCID: PMC8587224 DOI: 10.21542/gcsp.2021.20] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/13/2021] [Accepted: 09/30/2021] [Indexed: 11/28/2022] Open
Abstract
Computations of fractional flow reserve, based on CT coronary angiography and computational fluid dynamics (CT-based FFR) to assess the severity of coronary artery stenosis, was introduced around a decade ago and is now one of the most successful applications of computational fluid dynamic modelling in clinical practice. Although the mathematical modelling framework behind this approach and the clinical operational model vary, its clinical efficacy has been demonstrated well in general. In this review, technical elements behind CT-based FFR computation are summarised with some key assumptions and challenges. Examples of these challenges include the complexity of the model (such as blood viscosity and vessel wall compliance modelling), whose impact has been debated in the research. Efforts made to address the practical challenge of processing time are also reviewed. Then, further application areas—myocardial bridge, renal stenosis and lower limb stenosis—are discussed along with specific challenges expected in these areas.
Collapse
Affiliation(s)
- Ryo Torii
- Department of Mechanical Engineering, University College London, London, UK
| | - Magdi H Yacoub
- Department of Surgery and Department of Cardiology, Aswan Heart Centre, Magdi Yacoub Heart Foundation, Aswan, Egypt.,Magdi Yacoub Institute, Harefield Heart Science Centre, Harefield, UK.,National Heart and Lung Institute, Imperial College London, UK
| |
Collapse
|
9
|
Rümenapf G, Morbach S, Schmidt A, Sigl M. In Reply. DEUTSCHES ARZTEBLATT INTERNATIONAL 2020; 117:677-678. [PMID: 33357357 PMCID: PMC7838378 DOI: 10.3238/arztebl.2020.0677c] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/12/2023]
Affiliation(s)
- Gerhard Rümenapf
- *Gefäßzentrum Oberrhein Speyer-Mannheim, Klinik für Gefäßchirurgie, Diakonissen-Stiftungs-Krankenhaus, Speyer, Germany
| | - Stephan Morbach
- **Abteilung für Diabetologie und Angiologie, Marienkrankenhaus, Soest, Germany
| | - Andrej Schmidt
- ***Klinik und Poliklinik für Angiologie, Universitätsklinikum Leipzig, Germany
| | - Martin Sigl
- ****Abteilung für Angiologie, 1. Medizinische Klinik, Universitätsklinikum Mannheim, Germany
| |
Collapse
|