Development of a localization-based algorithm for the prediction of leg ulcer etiology.
Leg ulcer
arteriolosclerotic ulcer of Martorell
chronic venous insufficiency
localization mapping
peripheral arterial occlusive disease
vasculitis
Journal
Journal der Deutschen Dermatologischen Gesellschaft = Journal of the German Society of Dermatology : JDDG
ISSN: 1610-0387
Titre abrégé: J Dtsch Dermatol Ges
Pays: Germany
ID NLM: 101164708
Informations de publication
Date de publication:
11 2023
11 2023
Historique:
received:
27
11
2022
accepted:
22
06
2023
medline:
13
11
2023
pubmed:
2
9
2023
entrez:
2
9
2023
Statut:
ppublish
Résumé
Diagnostic work-up of leg ulcers is time- and cost-intensive. This study aimed at evaluating ulcer location as a diagnostic criterium and providing a diagnostic algorithm to facilitate differential diagnosis. The study consisted of 277 patients with lower leg ulcers. The following five groups were defined: Venous leg ulcer, arterial ulcers, mixed ulcer, arteriolosclerosis, and vasculitis. Using computational surface rendering, predilection sites of different ulcer types were evaluated. The results were integrated in a multinomial logistic regression model to calculate the likelihood of a specific diagnosis depending on location, age, bilateral involvement, and ulcer count. Additionally, neural network image analysis was performed. The majority of venous ulcers extended to the medial malleolar region. Arterial ulcers were most frequently located on the dorsal aspect of the forefoot. Arteriolosclerotic ulcers were distinctly localized at the middle third of the lower leg. Vasculitic ulcers appeared to be randomly distributed and were markedly smaller, multilocular and bilateral. The multinomial logistic regression model showed an overall satisfactory performance with an estimated accuracy of 0.68 on unseen data. The presented algorithm based on ulcer location may serve as a basic tool to narrow down potential diagnoses and guide further diagnostic work-up.
Sections du résumé
BACKGROUND
Diagnostic work-up of leg ulcers is time- and cost-intensive. This study aimed at evaluating ulcer location as a diagnostic criterium and providing a diagnostic algorithm to facilitate differential diagnosis.
PATIENTS AND METHODS
The study consisted of 277 patients with lower leg ulcers. The following five groups were defined: Venous leg ulcer, arterial ulcers, mixed ulcer, arteriolosclerosis, and vasculitis. Using computational surface rendering, predilection sites of different ulcer types were evaluated. The results were integrated in a multinomial logistic regression model to calculate the likelihood of a specific diagnosis depending on location, age, bilateral involvement, and ulcer count. Additionally, neural network image analysis was performed.
RESULTS
The majority of venous ulcers extended to the medial malleolar region. Arterial ulcers were most frequently located on the dorsal aspect of the forefoot. Arteriolosclerotic ulcers were distinctly localized at the middle third of the lower leg. Vasculitic ulcers appeared to be randomly distributed and were markedly smaller, multilocular and bilateral. The multinomial logistic regression model showed an overall satisfactory performance with an estimated accuracy of 0.68 on unseen data.
CONCLUSIONS
The presented algorithm based on ulcer location may serve as a basic tool to narrow down potential diagnoses and guide further diagnostic work-up.
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
1339-1349Informations de copyright
© 2023 The Authors. Journal der Deutschen Dermatologischen Gesellschaft published by John Wiley & Sons Ltd on behalf of Deutsche Dermatologische Gesellschaft.
Références
Frykberg RG, Banks J. Challenges in the treatment of chronic wounds. Adv Wound Care (New Rochelle). 2015;4:560-582.
Duschek N, Trautinger F. [Chronic leg ulcers in older patients]. Z Gerontol Geriatr. 2019;52:377-390.
Richmond NA, Maderal AD, Vivas AC. Evidence-based management of common chronic lower extremity ulcers. Dermatol Ther. 2013;26:187-196.
Hellström A, Nilsson C, Nilsson A, Fagerström C. Leg ulcers in older people: a national study addressing variation in diagnosis, pain and sleep disturbance. BMC geriatrics. 2016;16:25.
Makrantonaki E, Wlaschek M, Scharffetter-Kochanek K. Pathogenesis of wound healing disorders in the elderly. J Dtsch Dermatol Ges. 2017;15:255-275.
Spentzouris G, Labropoulos N. The evaluation of lower-extremity ulcers. Semin Intervent Radiol. 2009; 6: 86-95.
Mekkes JR, Loots MA, Van Der Wal AC, Bos JD. Causes, investigation and treatment of leg ulceration. Br J Dermatol. 2003;148:388-401.
Finlayson KJ, Parker CN, Miller C, et al. Predicting the likelihood of venous leg ulcer recurrence: The diagnostic accuracy of a newly developed risk assessment tool. Int Wound J. 2018;15:686-694.
McDaniel HB, Marston WA, Farber MA, et al. Recurrence of chronic venous ulcers on the basis of clinical, etiologic, anatomic, and pathophysiologic criteria and air plethysmography. J Vasc Surg. 2002; 35:723-728.
Nelson EA, Harper DR, Prescott RJ, et al. Prevention of recurrence of venous ulceration: Randomized controlled trial of class 2 and class 3 elastic compression. J Vasc Surg. 2006;44:803-808.
Margolis DJ, Berlin JA, Strom BL. Risk factors associated with the failure of a venous leg ulcer to heal. Arch Dermatol. 1999;135:920-926.
Fritsch P. Dermatologie Venerlogoie: Grundlagen. Klinik. Atlas. Springer-Verlag, Berlin-Heidelberg, 2004.
Hafner J, Buset C, Anzengruber F, et al. [Leg ulcers (ulcus cruris): The frequent macrovascular causes]. Ther Umsch. 2018;75:506-514.
Hafner J, Böni T, Calcagni M, et al. [Differential diagnosis of clinical relevance]. Ther Umsch. 2011;68:139-147.
Dissemond J, Erfurt-Berge C, Goerge T, et al. Systemic therapies for leg ulcers. J Dtsch Dermatol Ges. 2018;16:873-890.
Raffetto JD, Ligi D, Maniscalco R, et al. Why venous leg ulcers have difficulty healing: overview on pathophysiology, clinical consequences, and treatment. J Clin Med. 2021;10:29.
Weller CD, Evans S. Monitoring patterns and quality of care for people diagnosed with venous leg ulcers: The argument for a national venous leg ulcer registry. Wound Practice & Research. 2014; 22.
Valencia IC, Falabella A, Kirsner RS, Eaglstein WH. Chronic venous insufficiency and venous leg ulceration. J Am Acad Dermatol. 2001;44:401-421;quiz 22-24.
Martinengo L, Olsson M, Bajpai R, et al. Prevalence of chronic wounds in the general population: systematic review and meta-analysis of observational studies. Ann Epidemiol. 2019;29: 8-15.
Hafner J, Nobbe S, Partsch H, et al. Martorell hypertensive ischemic leg ulcer: a model of ischemic subcutaneous arteriolosclerosis. Arch Dermatol. 2010;146:961-968.
Deinsberger J, Brugger J, Tschandl P, et al. Differentiating arteriolosclerotic ulcers of Martorell from other types of leg ulcers based on vascular histomorphology. Acta Derm Venereol. 2021;101:adv00449.
Deinsberger J, Sirovina S, Bromberger S, et al. Microstructural comparative analysis of calcification patterns in calciphylaxis versus arteriolosclerotic ulcer of Martorell. Eur J Dermatol. 2021;31:705-711.
Hedayati N, Carson JG, Chi YW, Link D. Management of mixed arterial venous lower extremity ulceration: A review. Vasc Med. 2015;20:479-486.
Santler B, Goerge T. Chronic venous insufficiency - a review of pathophysiology, diagnosis, and treatment. J Dtsch Dermatol Ges. 2017;15: 538-556.
Weber B, Deinsberger J, Hafner J, et al. Localization-mapping of arteriolosclerotic ulcers of Martorell using two-dimensional computational rendering reveals a predominant location on the mid-lateral lower leg. J Eur Acad Dermatol Venereol. 2021;35:e40-e42.
World Medical Association Declaration of Helsinki: ethical principles for medical research involving human subjects. JAMA. 2013;310:2191-4.
Kosmidis I, Firth D. Multinomial logit bias reduction via the Poisson log-linear model. Biometrika. 2011;98:755-59.
Liu Z, Lin Y, Cao Y, et al. Swin Transformer: Hierarchical Vision Transformer using Shifted Windows. 2021 IEEE/CVF International Conference on Computer Vision (ICCV). 2021:9992-10002.
Wolf T, Debut L, Sanh V, et al. Huggingface's transformers: State-of-the-art natural language processing. arXiv preprint arXiv:191003771. 2019.
O'Donnell TF, Jr., Passman MA, Marston WA, et al. Management of venous leg ulcers: clinical practice guidelines of the Society for Vascular Surgery® and the American Venous Forum. J Vasc Surg. 2014;60:3s-59s.
Evidence-based (S3) guidelines for diagnostics and treatment of venous leg ulcers. J Eur Acad Dermatol Venereol. 2016;30:1843-1875.
Raffetto JD, Mannello F. Pathophysiology of chronic venous disease. Int Angiol. 2014; 33:212-221.
Lim CS, Baruah M, Bahia SS. Diagnosis and management of venous leg ulcers. BMJ. 2018; 362:k3115.
Alavi A, Mayer D, Hanfer J, Sibbald RG. Martorell hypertensive ischemic leg ulcer: an underdiagnosed Entity©. Adv Skin Wound Care. 2012; 25: 563-572.
Lawall H, Pokrovsky A, Checinski P, et al. Efficacy and safety of alprostadil in patients with peripheral arterial occlusive disease Fontaine stage IV: Results of a placebo controlled randomised multicentre trial (ESPECIAL). Eur J Vasc Endovasc Surg. 2017;53:559-566.
Fritsch P, Schwarz, T. Dermatologie Venerologie: Grundlagen. Klinik. Atlas. In: Springer. 3. ed, 2018:598-616.
Dissemond J, Kröger K. Chronische Wunden: Diagnostik - Therapie - Versorgung. 1. ed. München: Elsevier GmbH, Urban & Fischer, 2020:111-112.
Wang S, Xing Y, Zhang L, et al. Deep convolutional neural network for ulcer recognition in wireless capsule endoscopy: experimental feasibility and optimization. Comput Math Methods Med. 2019; 2019:7546215.
Alaskar H, Hussain A, Al-Aseem N, et al. Application of convolutional neural networks for automated ulcer detection in wireless capsule endoscopy images. Sensors (Basel). 2019; 19.
Klang E, Kopylov U, Mortensen B, et al. A convolutional neural network deep learning model trained on cd ulcers images accurately identifies NSAID ulcers. Front Med. 2021;8:656493.
Liu TJ, Christian M, Chu Y-C, et al. A pressure ulcers assessment system for diagnosis and decision making using convolutional neural networks. J Formos Med Assoc. 2022;121:2227-2236.