Clinical decision support systems for diabetic foot ulcers: a scoping review

A scoping review based on the JBI Manual for Evidence Synthesis and registered on the Open Science Framework platform. Searches were carried out in primary and secondary sources on prototypes and computerized tools aimed at assisting patients with diabetic foot or at risk of having it, published in any language or period, in eleven databases and grey literature.

Results:

A total of 710 studies were identified and, following the eligibility criteria, 23 were selected, which portrayed the use of decision support systems in diabetic foot screening, predicting the risk of ulcers and amputations, classifying the stage of severity, deciding on the treatment plan, and evaluating the effectiveness of interventions, by processing data relating to clinical and sociodemographic information.

Conclusion:

Expert systems stand out for their satisfactory results, with high precision and sensitivity when it comes to guiding and qualifying the decision-making process in diabetic foot prevention and care.

DESCRIPTORS
Diabetes Mellitus; Diabetic Foot; Decision Support Systems; Clinical; Review

	P	C	C
Extraction	People with Diabetes Mellitus	Decision Support Systems	Diabetic Foot
Conversion	Diabetes Mellitus	Decision Support Systems	Diabetic Foot
Combination	Diabetes Mellitus; Diabetes; Diabetic; Diabetic Patient	Decision Support Systems; Clinical Decision Support Systems; Clinical Decision Support; Specialist Systems	Diabetic Foot; Diabetic Feet; Diabetic Foot Ulcer
Construction	“Diabetes Mellitus” OR Diabetes OR Diabetic OR “Diabetic Patient”	“Decision Support Systems” OR “Clinical Decision Support Systems” OR “Clinical Decision Support” OR “Specialist Systems”	“Diabetic Foot” OR “Diabetic Feet” OR “Diabetic Foot Ulcer”
Use	(“Diabetes Mellitus” OR Diabetes OR Diabetic OR “Diabetic Patient”) AND (“Decision Support Systems” OR “Clinical Decision Support Systems” OR “Clinical Decision Support” OR “Specialist Systems”) AND (“Diabetic Foot” OR “Diabetic Feet” OR “Diabetic Foot Ulcer”)

No.	Author/Year/Country/Journal	Objectives	Technology used	Clinical applicability	Main results
1.	Bender C, Cichosz SL, Malovini A, Bellazzi R, Pape-Haugaard L, Hejlesen O (2021)/Denmark/Journal of Diabetes Science and Technology(⁹9. Bender C, Cichosz SL, Malovini A, Bellazzi R, Pape-Haugaard L, Hejlesen O. Using case-based reasoning in a learning system: a prototype of a pedagogical nurse tool for evidence-based diabetic foot ulcer care. J Diabetes Sci Technol. 2021;16(2):454–9. doi: http://dx.doi.org/10.1177/1932296821991127. PubMed PMID: 33583205. https://doi.org/10.1177/1932296821991127... )	Build a prototype of an interactive teaching tool, using case-based reasoning, for evidence-based diabetic foot ulcer care.	Machine learning/Case-based reasoning(⁹9. Bender C, Cichosz SL, Malovini A, Bellazzi R, Pape-Haugaard L, Hejlesen O. Using case-based reasoning in a learning system: a prototype of a pedagogical nurse tool for evidence-based diabetic foot ulcer care. J Diabetes Sci Technol. 2021;16(2):454–9. doi: http://dx.doi.org/10.1177/1932296821991127. PubMed PMID: 33583205. https://doi.org/10.1177/1932296821991127... )	Educational tool for nurses for diabetic foot care and screening.	The prototype is capable of calculating a dissimilarity score that provides a quantitative measure between a new case and stored cases.
2.	Casal-Guisande M, Cerqueiro-Pequeño J, Comesaña-Campos A, Bouza-Rodríguez JB (2020)/Spain/Diabetic Medicine(⁷7. Casal-Guisande M, Cerqueiro-Pequeño J, Comesaña-Campos A, Bouza-Rodríguez JB. Proposal of a methodology based on expert systems for the treatment of diabetic foot condition. TEEM’20. 2020;(21):491–6. doi: http://dx.doi.org/10.1145/3434780.3436625. https://doi.org/10.1145/3434780.3436625... )	Adapting a methodology based on expert systems to monitor patients prone to developing diabetic foot wounds.	Machine learning/Decision manager supported by fuzzy inference(⁷7. Casal-Guisande M, Cerqueiro-Pequeño J, Comesaña-Campos A, Bouza-Rodríguez JB. Proposal of a methodology based on expert systems for the treatment of diabetic foot condition. TEEM’20. 2020;(21):491–6. doi: http://dx.doi.org/10.1145/3434780.3436625. https://doi.org/10.1145/3434780.3436625... )	Determining the risk of developing diabetic foot and evaluating the effectiveness of the care received.	The system includes the initial stage of data collection, by taking a photo of the lesion and filling in a questionnaire on risk factors, followed by image processing (Wagner scale), calculation, and modeling of the results for interpretation and generation of alerts, decision-making, and application of treatment.
3.	Chappell FM, Crawford F, Horne M, Leese GP, Martin A, Weller D, et al (2021)/United Kingdom/BMJ open Diabetes Research & Care(¹⁵15. Chappell FM, Crawford F, Horne M, Leese GP, Martin A, Weller D, et al. Development and validation of a clinical prediction rule for development of diabetic foot ulceration: an analysis of data from five cohort studies. BMJ Open Diabetes Res Care. 2021;9(1):e002150. doi: http://dx.doi.org/10.1136/bmjdrc-2021-002150. PubMed PMID: 34035053. https://doi.org/10.1136/bmjdrc-2021-0021... )	Developing and validating a clinical prediction rule for foot ulceration in people with diabetes.	Clinical prediction rule(¹⁵15. Chappell FM, Crawford F, Horne M, Leese GP, Martin A, Weller D, et al. Development and validation of a clinical prediction rule for development of diabetic foot ulceration: an analysis of data from five cohort studies. BMJ Open Diabetes Res Care. 2021;9(1):e002150. doi: http://dx.doi.org/10.1136/bmjdrc-2021-002150. PubMed PMID: 34035053. https://doi.org/10.1136/bmjdrc-2021-0021... )	Predicting the risk of diabetic foot ulceration through plantar thermal imaging analysis.	The clinical prediction rule scores (0, 1, 2, 3, and 4) show a two-year ulcer risk of 2.4%, 6.0%, 14.0%, 29.2%, and 51.1%, respectively. It is a simple tool that uses routinely obtained data and helps prevent ulcers by directing care to patients with a score of 1 or more.
4.	Crawford F, Bekker HL, Jovem M, Sheikh A (2010)/United Kingdom/Journal of Innovation in Health Informatics(¹⁶16. Crawford F, Bekker HL, Jovem M, Sheikh A. General practitioners’ and nurses’ experiences of using computerised decision support in screening for diabetic foot disease: implementing Scottish Clinical Information - Diabetes Care in routine clinical practice. J Inovation Health Inf. 2010;18(4):259–68. doi: http://dx.doi.org/10.14236/jhi.v18i4.781. https://doi.org/10.14236/jhi.v18i4.781... )	Understanding the vision of primary health care professionals in relation to diabetic foot disease screening and their experience with the SCI-DC system.	Machine learning(¹⁶16. Crawford F, Bekker HL, Jovem M, Sheikh A. General practitioners’ and nurses’ experiences of using computerised decision support in screening for diabetic foot disease: implementing Scottish Clinical Information - Diabetes Care in routine clinical practice. J Inovation Health Inf. 2010;18(4):259–68. doi: http://dx.doi.org/10.14236/jhi.v18i4.781. https://doi.org/10.14236/jhi.v18i4.781... )	Diabetic foot screening.	SCI-DC is an information system designed to create a shared electronic record for use in the care of patients with DM. There were favorable perspectives on the system, especially with regard to the foot screening screens, the transfer of information from primary to secondary care, the reduction of variability in information from podiatrists, and the source of information for auditing purposes.
5.	Crawford F, Cezard G, Chappell FM (2018)/United Kingdom/Diabetic Medicine(¹⁷17. Crawford F, Cezard G, Chappell FM, PODUS Group. The development and validation of a multivariable prognostic model to predict foot ulceration in diabetes using a systematic review and individual patient data meta-analyses. Diabet Med. 2018;35(11):1480–93. doi: http://dx.doi.org/10.1111/dme.13797. PubMed PMID: 30102422. https://doi.org/10.1111/dme.13797... )	Developing and validating a prognostic model of independent risk factors for foot ulceration in diabetes.	Clinical prediction rule(¹⁷17. Crawford F, Cezard G, Chappell FM, PODUS Group. The development and validation of a multivariable prognostic model to predict foot ulceration in diabetes using a systematic review and individual patient data meta-analyses. Diabet Med. 2018;35(11):1480–93. doi: http://dx.doi.org/10.1111/dme.13797. PubMed PMID: 30102422. https://doi.org/10.1111/dme.13797... )	Predicting the risk of diabetic foot ulceration through plantar thermal imaging analysis.	A simple prognostic model was developed with three independent predictive risk factors that were statistically associated with diabetic foot ulcers: history of ulceration/inability to feel a 10g monofilament/at least one absent pulse.
6.	Cruz-Vega I, Peregrina-Barreto H, Rangel-Magdaleno JJ, Ramires-Cortes MJ (2019)/New Zealand/IEEE Xplore(¹⁸18. Cruz-Vega I, Peregrina-Barreto H, Rangel-Magdaleno JJ, Ramires-Cortes MJ. A comparison of intelligent classifiers of thermal patterns in diabetic foot. In: 2019 IEEE International Instrumentation and Measurement Technology Conference (I2MTC); 2019; Auckland, New Zealand. USA: IEEE; 2019. p. 1–6. doi: http://dx.doi.org/10.1109/I2MTC.2019.8827044 https://doi.org/10.1109/I2MTC.2019.88270... )	Comparing intelligent classifiers of diabetic foot thermal patterns in patients with diabetes mellitus and a control group.	Machine learning(¹⁸18. Cruz-Vega I, Peregrina-Barreto H, Rangel-Magdaleno JJ, Ramires-Cortes MJ. A comparison of intelligent classifiers of thermal patterns in diabetic foot. In: 2019 IEEE International Instrumentation and Measurement Technology Conference (I2MTC); 2019; Auckland, New Zealand. USA: IEEE; 2019. p. 1–6. doi: http://dx.doi.org/10.1109/I2MTC.2019.8827044 https://doi.org/10.1109/I2MTC.2019.88270... )	Predicting the risk of diabetic foot ulceration through plantar thermal imaging analysis.	The results of using support vector machines and multi-layer perception neural networks to classify medical image patterns are highly accurate and satisfactory. However, the use of deep learning is gaining momentum, given the increased accuracy and dispensability of feature extraction and pattern segmentation.
7.	Gamage C, Wijesinghe I, Perera I (2019)/Sri Lanka/IEEE Xplore(¹⁹19. Gamage C, Wijesinghe I, Perera I. Automatic scoring of diabetic foot ulcers through Deep CNN based feature extraction with low rank matrix factorization. In: 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE); 2019; Athens, Greece. USA: IEEE; 2019. pp. 352–6. doi: http://dx.doi.org/10.1109/BIBE.2019.00069. https://doi.org/10.1109/BIBE.2019.00069... )	Using a convolutional neural network to predict stages of diabetic foot severity.	Machine learning/Convolutional neural networks(¹⁹19. Gamage C, Wijesinghe I, Perera I. Automatic scoring of diabetic foot ulcers through Deep CNN based feature extraction with low rank matrix factorization. In: 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE); 2019; Athens, Greece. USA: IEEE; 2019. pp. 352–6. doi: http://dx.doi.org/10.1109/BIBE.2019.00069. https://doi.org/10.1109/BIBE.2019.00069... )	Classification of the stage of diabetic foot severity according to Wagner’s criteria using images.	The dataset of wound images was subdivided for experimentation with pre-trained convolutional neural networks. Among the decision algorithms, artificial neural networks performed most successfully.
8.	Goulionis JE, Vozikis A, Benos VC, Nikolakis D (2010)/Greece/ClinicoEconomics and Outcomes Research(²⁰20. Goulionis JE, Vozikis A, Benos VC, Nikolakis D. On the decision rules of cost-effective treatment for patients with diabetic foot syndrome. Clinicoecon Outcomes Res. 2010;2:121–6. doi: http://dx.doi.org/10.2147/CEOR.S11981. PubMed PMID: 21935321. https://doi.org/10.2147/CEOR.S11981... )	Assessing the cost-benefit ratio of two treatments (medical treatment and amputation) in patients with diabetic foot syndrome, using a decision algorithm.	Heuristic decision algorithm, based on the partially observable Markov decision process(²⁰20. Goulionis JE, Vozikis A, Benos VC, Nikolakis D. On the decision rules of cost-effective treatment for patients with diabetic foot syndrome. Clinicoecon Outcomes Res. 2010;2:121–6. doi: http://dx.doi.org/10.2147/CEOR.S11981. PubMed PMID: 21935321. https://doi.org/10.2147/CEOR.S11981... )	Evaluation of the cost-effectiveness of medical treatment and diabetic foot amputation.	A simple model for cost-effective decision-making for diabetic foot treatment was created, explaining two pathways between primary clinical data and early and efficient medical decision-making. The use of the model provided improved quality of care, cost-effective clinical decision-making, and adaptability and transferability across different healthcare settings.
9.	Das SK, Roy P, Mishra AK (2022)/India/Concurrency and Computation Practice and Experience(²¹21. Das SK, Roy P, Mishra AK. Fusion of handcrafted and deep convolutional neural network features for effective identification of diabetic foot ulcer. Concurr Comput. 2022;34(5):e6690. doi: http://dx.doi.org/10.1002/cpe.6690. https://doi.org/10.1002/cpe.6690... )	Merging high-level resources based on machine learning with low-level and convolutional neural networks to improve the automatic diagnosis of diabetic feet.	Machine learning/Convolutional neural networks(²¹21. Das SK, Roy P, Mishra AK. Fusion of handcrafted and deep convolutional neural network features for effective identification of diabetic foot ulcer. Concurr Comput. 2022;34(5):e6690. doi: http://dx.doi.org/10.1002/cpe.6690. https://doi.org/10.1002/cpe.6690... )	Predicting risk and diagnosing diabetic foot ulceration through images.	The fusion of resources from classifiers of different machine learning, logistic regression, support vector machine, and artificial neural networks showed better results in identifying the diabetic foot. Logistic regression outperformed all the evaluation metrics, achieving 95.23% sensitivity and 95.37% specificity.
10.	Deschamps K, Matricali GA, Desmet D, Roosen P, Keijsers N, Nobel F, et al. (2016)/Belgium/Gait & Posture(²²22. Deschamps K, Matricali GA, Desmet D, Roosen P, Keijsers N, Nobel F, et al. Efficacy measures associated to a plantar pressure-based classification system in diabetic foot medicine. Gait Posture. 2016;49:168–75. doi: http://dx.doi.org/10.1016/j.gaitpost.2016.07.009. PubMed PMID: 27427834. https://doi.org/10.1016/j.gaitpost.2016.... )	Determine measures of effectiveness of a diabetic foot prediction system based on plantar pressure, analyzing the recognition rate, sensitivity, specificity, as well as its usefulness in implementing pressure distribution strategies.	Semi-automatic total mapping to identify regional metrics(²²22. Deschamps K, Matricali GA, Desmet D, Roosen P, Keijsers N, Nobel F, et al. Efficacy measures associated to a plantar pressure-based classification system in diabetic foot medicine. Gait Posture. 2016;49:168–75. doi: http://dx.doi.org/10.1016/j.gaitpost.2016.07.009. PubMed PMID: 27427834. https://doi.org/10.1016/j.gaitpost.2016.... ).	Predicting the risk and diagnosing diabetic foot ulceration through plantar grip measurements.	The comparison of the four groups associated with the classification system highlighted distinct regional differences. The overall recognition rate exceeded 90% for all cross-validation subsets. The sensitivity and specificity of the four groups associated with the classification system exceeded the 0.7 and 0.8 level, respectively.
11.	Farzi S, Kianian S, Rastkhadive I (2018)/Iran/IEEE Xplore(²³23. Farzi S, Kianian S, Rastkhadive I. Predicting serious diabetic complications using hidden pattern detection. In: 2017 IEEE 4th International Conference on Knowledge-Based Engineering and Innovation (KBEI); 2017; Tehran, Iran. USA: IEEE; 2018. p. 0063–8. doi: http://dx.doi.org/10.1109/KBEI.2017.8324885. https://doi.org/10.1109/KBEI.2017.832488... )	Identifying the best classification algorithm to detect diabetes complications.	Machine learning/Decision tree, Random forest, Multi-layer perception neural network, Naive Bayes, Radial base function(²³23. Farzi S, Kianian S, Rastkhadive I. Predicting serious diabetic complications using hidden pattern detection. In: 2017 IEEE 4th International Conference on Knowledge-Based Engineering and Innovation (KBEI); 2017; Tehran, Iran. USA: IEEE; 2018. p. 0063–8. doi: http://dx.doi.org/10.1109/KBEI.2017.8324885. https://doi.org/10.1109/KBEI.2017.832488... )	Predicting risk and diagnosing diabetic foot ulceration through sociodemographic and clinical variables.	The Random Forest algorithm showed the best accuracy in diagnosing diabetic foot, ahead of neural networks and Naive Bayes with the worst performance.
12.	Ferreira ACBH, Ferreira DD, Oliveira HC, Resende ICD, Anjos A, Lopes MHBDM (2020)/Brazil/Computers in Biology and Medicine(²⁴24. Ferreira ACBH, Ferreira DD, Oliveira HC, Resende ICD, Anjos A, Lopes MHBDM. Competitive neural layer-based method to identify people with high risk for diabetic foot. Comput Biol Med. 2020;120:103744. doi: http://dx.doi.org/10.1016/j.compbiomed.2020.103744. PubMed PMID: 32421649. https://doi.org/10.1016/j.compbiomed.202... )	Identifying patients with DM who are at high risk of developing diabetic foot, using an unsupervised machine learning technique.	Machine learning/Competitive neural layer-based method(²⁴24. Ferreira ACBH, Ferreira DD, Oliveira HC, Resende ICD, Anjos A, Lopes MHBDM. Competitive neural layer-based method to identify people with high risk for diabetic foot. Comput Biol Med. 2020;120:103744. doi: http://dx.doi.org/10.1016/j.compbiomed.2020.103744. PubMed PMID: 32421649. https://doi.org/10.1016/j.compbiomed.202... )	Predicting risk and diagnosing diabetic foot ulceration through sociodemographic and clinical variables.	The method was 90% accurate, 70% sensitive, and 100% specific. The use of the method can optimize nursing work by facilitating screening.
13.	Husers J, Hafer G, Heggemann J, Stefan W, Prysucha M, Dissemond J, Mooelleken M, Erfurt-Berge C, Hubner U (2022)/Germany/Studies in health technology and informatics(²⁵25. Husers J, Hafer G, Heggemann J, Wiemeyer S, John SM, Hubner U. Development and evaluation of a bayesian risk stratification method for major amputations in patients with diabetic foot ulcers. Stud Health Technol Inform. 2022;289:212–5. doi: http://dx.doi.org/10.3233/SHTI210897. PubMed PMID: 35062130. https://doi.org/10.3233/SHTI210897... )	Training an artificial intelligence system and evaluating its performance in diabetic foot detection.	Machine learning/Convolutional neural networks(²⁵25. Husers J, Hafer G, Heggemann J, Wiemeyer S, John SM, Hubner U. Development and evaluation of a bayesian risk stratification method for major amputations in patients with diabetic foot ulcers. Stud Health Technol Inform. 2022;289:212–5. doi: http://dx.doi.org/10.3233/SHTI210897. PubMed PMID: 35062130. https://doi.org/10.3233/SHTI210897... )	Early identification of patients at risk of diabetic foot ulcer and, consequently, amputation.	The model training showed convergence, with no overfitting. The final model yielded a score of 0.71 on the 108 validation images, with sensitivity of 0.69 and accuracy of 0.67, demonstrating satisfactory validity for classifying images of macerations for clinical use in wound documentation.
14.	Husers J, Hafer G, Heggemann J, Wiemeyer S, John SM, Hubner U (2022)/Germany/Studies in health technology and informatics(²⁶26. Hüsers J, Hafer G, Heggemann J, Stefan W, Prysucha M, Dissemond J, et al. Automatic classification of diabetic foot ulcer images - a transfer-learning approach to detect wound maceration. Stud Health Technol Inform. 2022;289:301–4. doi: http://dx.doi.org/10.3233/SHTI210919. PubMed PMID: 35062152. https://doi.org/10.3233/SHTI210919... )	Developing a stratification scheme that allows for the classification of patients with and without risk of major amputation.	Machine learning/Bayesian method(²⁶26. Hüsers J, Hafer G, Heggemann J, Stefan W, Prysucha M, Dissemond J, et al. Automatic classification of diabetic foot ulcer images - a transfer-learning approach to detect wound maceration. Stud Health Technol Inform. 2022;289:301–4. doi: http://dx.doi.org/10.3233/SHTI210919. PubMed PMID: 35062152. https://doi.org/10.3233/SHTI210919... )	Predicting the risk of amputations in patients with diabetic foot, based on sociodemographic and clinical characteristics.	The system revealed an adequate cut-off point for the risk of amputation of 0.28. Sensitivity and specificity were 0.83 and 0.66. Although the specificity is low, the decision method includes the majority of real patients at risk.
15.	Jayashree J, Vijayashree J (2017)/India/International Journal of Civil Engineering and Technology(²⁷27. Jayashree J, Vijayashree J. Anticipating diabetic foot ulcer using generative fuzzy expert system framework. Int J Civil Engineering Tech. 2017 [cited 2022 Dec 24];8(12):642–50. Available from: https://research.vit.ac.in/publication/anticipating-diabetic-foot-ulcer-using-generative-fuzzy-expert https://research.vit.ac.in/publication/a... )	Proposing a system for predicting the severity of diabetic foot problems using fuzzy expert systems.	Machine learning/Decision manager supported by fuzzy inference(²⁷27. Jayashree J, Vijayashree J. Anticipating diabetic foot ulcer using generative fuzzy expert system framework. Int J Civil Engineering Tech. 2017 [cited 2022 Dec 24];8(12):642–50. Available from: https://research.vit.ac.in/publication/anticipating-diabetic-foot-ulcer-using-generative-fuzzy-expert https://research.vit.ac.in/publication/a... )	Describing the severity of the diabetic foot.	A model is proposed to describe the severity of diabetic foot based on fuzzy expert systems and Wagner’s classification.
16.	Medeiros RA (2015)/Brazil(²⁸28. Medeiros RA. Sistema inteligente de monitoramento da prevenção do pé diabético. [Dissertação]. Mossoró: Universidade do Estado do Rio Grande do Norte; 2015 [cited 2022 Dec 24]. Available from: https://ppgcc.ufersa.edu.br/wp-content/uploads/sites/42/2014/09/rodrigo-azevedo-de-medeiros.pdf. https://ppgcc.ufersa.edu.br/wp-content/u... )	Developing an intelligent diabetic foot prevention monitoring system.	Machine learning(²⁸28. Medeiros RA. Sistema inteligente de monitoramento da prevenção do pé diabético. [Dissertação]. Mossoró: Universidade do Estado do Rio Grande do Norte; 2015 [cited 2022 Dec 24]. Available from: https://ppgcc.ufersa.edu.br/wp-content/uploads/sites/42/2014/09/rodrigo-azevedo-de-medeiros.pdf. https://ppgcc.ufersa.edu.br/wp-content/u... )	Diabetic foot monitoring and self-care.	SIM2PeD consists of a platform integrated with a mobile device to capture data from individuals for monitoring by the medical team and alerts regarding care. Once captured, the information is passed on to the expert system, which generates recommendations based on the care provided. The experiments carried out in a real environment revealed satisfactory and adequate performance for remote monitoring of foot self-care activities.
17.	Nair HKR, Kaur G (2021)/Malaysia/Wounds International(²⁹29. Nair HKR, Kaur G. Using the diabetic foot ulcer aetiology-specific T.I.M.E. clinical decision support tool to promote consistent holistic wound management and eliminate variation in practice. Wounds International. [cited 2022 Dec 23] 2021;12(3):38–45. Available from: https://www.woundsinternational.com/resources/details/using-diabetic-foot-ulcer-aetiologyspecific-time-clinical-decision-support-tool-promote-consistent-holistic-wound-management-and-eliminate-variation-practice https://www.woundsinternational.com/reso... )	Describing the experience of using the TIME tool with diabetic foot patients.	Guiding flowchart(²⁹29. Nair HKR, Kaur G. Using the diabetic foot ulcer aetiology-specific T.I.M.E. clinical decision support tool to promote consistent holistic wound management and eliminate variation in practice. Wounds International. [cited 2022 Dec 23] 2021;12(3):38–45. Available from: https://www.woundsinternational.com/resources/details/using-diabetic-foot-ulcer-aetiologyspecific-time-clinical-decision-support-tool-promote-consistent-holistic-wound-management-and-eliminate-variation-practice https://www.woundsinternational.com/reso... )	Deciding on the treatment plan (wound bed preparation, dressing selection, and management).	Clinical decision support tool based on wound bed preparation, with a view to deciding on the treatment plan according to etiology. The tool facilitated decision-making, guidance, and unification on the appropriate treatment, allowing a systematic approach and communication between professionals.
18.	Nguyen G, Agu E, Tulu B, Strong D, Mombini H, Pedersen P, et al. (2020)/USA/Smart Health(³⁰30. Nguyen G, Agu E, Tulu B, Strong D, Mombini H, Pedersen P, et al. Machine learning models for synthesizing actionable care decisions on lower extremity wounds. Smart Health. 2020;18:100139. doi: http://dx.doi.org/10.1016/j.smhl.2020.100139. https://doi.org/10.1016/j.smhl.2020.1001... )	Exploring machine learning classifiers to generate actionable decisions in wound care.	Machine learning/Gradient Boosted Machine/Support Vector Machine(³⁰30. Nguyen G, Agu E, Tulu B, Strong D, Mombini H, Pedersen P, et al. Machine learning models for synthesizing actionable care decisions on lower extremity wounds. Smart Health. 2020;18:100139. doi: http://dx.doi.org/10.1016/j.smhl.2020.100139. https://doi.org/10.1016/j.smhl.2020.1001... )	Deciding on a diabetic foot treatment plan using images.	The Gradient Boosted Machine outperformed other decision algorithms, achieving 81% accuracy, using visual and textual resources. The decisions were (1) continue treatment, (2) request a change in treatment, and (3) refer for specialized treatment.
19.	Peleg M, Shachak A, Wang D, Karnieli E (2009)/Israel/International Journal of Medical Informatics(³¹31. Peleg M, Shachak A, Wang D, Karnieli E. Using multi-perspective methodologies to study users’ interactions with the prototype front end of a guideline-based decision support system for diabetic foot care. Int J Med Inform. 2009;78(7):482–93. doi: http://dx.doi.org/10.1016/j.ijmedinf.2009.02.008. PubMed PMID: 19328739. https://doi.org/10.1016/j.ijmedinf.2009.... )	Developing a prototype decision support system based on guidelines to assist in the management of the diabetic foot.	Guiding flowchart(³¹31. Peleg M, Shachak A, Wang D, Karnieli E. Using multi-perspective methodologies to study users’ interactions with the prototype front end of a guideline-based decision support system for diabetic foot care. Int J Med Inform. 2009;78(7):482–93. doi: http://dx.doi.org/10.1016/j.ijmedinf.2009.02.008. PubMed PMID: 19328739. https://doi.org/10.1016/j.ijmedinf.2009.... )	Predicting the risk, diagnosing, and treating diabetic foot ulceration, based on guidelines.	Users had a positive response to the prototype, in terms of clarity of design, interaction, and ease of use. The sample expressed a clear intention to use the system in the future, to help with treatment, referrals, risk stratification, and follow-up.
20.	Peng B, Min R, Liao Y, Yu A (2021)/China/Journal of Diabetes Research(³²32. Peng B, Min R, Liao Y, Yu A. Development of predictive nomograms for clinical use to quantify the risk of amputation in patients with diabetic foot ulcer. J Diabetes Res. 2021;2021:6621035. doi: http://dx.doi.org/10.1155/2021/6621035. PubMed PMID: 33511218. https://doi.org/10.1155/2021/6621035... )	Determining the accuracy of the new model in predicting the risk of lower limb amputations in the diabetic foot	Guiding flowchart(³²32. Peng B, Min R, Liao Y, Yu A. Development of predictive nomograms for clinical use to quantify the risk of amputation in patients with diabetic foot ulcer. J Diabetes Res. 2021;2021:6621035. doi: http://dx.doi.org/10.1155/2021/6621035. PubMed PMID: 33511218. https://doi.org/10.1155/2021/6621035... )	Predicting the risk of diabetic foot amputation through clinical variables.	After identifying the main predictive factors of diabetic foot, a logistic regression was carried out to track the independent factors of amputation, which were applied to build a prediction model. The area under the curve was 0.876 and the calibration curve corrected for the normogram showed a good fit for predicting the risk of amputation. The decision analysis curve indicated that the model was most practical and accurate when the risk threshold was between 6% and 91%.
21.	Schafer Z, Mathisen A, Svendsen K, Engberg S, Thomsen RT, Kirketerp-Moler K (2021)/Denmark/Frontiers in Medicine(³³33. Schafer Z, Mathisen A, Svendsen K, Engberg S, Thomsen RT, Kirketerp-Moler K. Toward machine-learning-based decision support in diabetes care: a risk stratification study on diabetic foot ulcer and amputation. Front Med (Lausanne). 2021;7:601602. doi: http://dx.doi.org/10.3389/fmed.2020.601602. PubMed PMID: 33681236. https://doi.org/10.3389/fmed.2020.601602... )	Understanding the risk factors for diabetic foot and amputation among patients with diabetes, using data from national health registries and machine learning.	Machine learning(³³33. Schafer Z, Mathisen A, Svendsen K, Engberg S, Thomsen RT, Kirketerp-Moler K. Toward machine-learning-based decision support in diabetes care: a risk stratification study on diabetic foot ulcer and amputation. Front Med (Lausanne). 2021;7:601602. doi: http://dx.doi.org/10.3389/fmed.2020.601602. PubMed PMID: 33681236. https://doi.org/10.3389/fmed.2020.601602... )	Predicting the risk of diabetic foot ulceration and amputation through sociodemographic and clinical variables.	The risk of ulceration and amputation is increased in patients with diabetes and cardiovascular complications, peripheral arterial disease, neuropathy, and chronic renal complications. Machine learning proved useful for assessing risk factors for ulceration and amputation, based on secondary data.
22.	Schoen DE, Glance DG, Thompson SC (2015)/Australia/Journal of Foot and Ankle Research(³3. Schoen DE, Glance DG, Thompson SC. Clinical decision support software for diabetic foot risk stratification: development and formative evaluation. J Foot Ankle Res. 2015;8(1):73. doi: http://dx.doi.org/10.1186/s13047-015-0128-z. PubMed PMID: 26692903. https://doi.org/10.1186/s13047-015-0128-... )	Understanding opinions and experiences during the development and evaluation of an electronic diabetic foot risk stratification tool, based on guidelines.	Machine learning/Software(³3. Schoen DE, Glance DG, Thompson SC. Clinical decision support software for diabetic foot risk stratification: development and formative evaluation. J Foot Ankle Res. 2015;8(1):73. doi: http://dx.doi.org/10.1186/s13047-015-0128-z. PubMed PMID: 26692903. https://doi.org/10.1186/s13047-015-0128-... )	Predicting the risk of ulceration based on clinical variables.	The risk tool integrates a simple assessment readily available in a clinical setting and reflects current Australian guidelines, targeting foot examination and investigation of predictors such as previous amputation/ulceration, deformity, presence of pulses, and peripheral neuropathy.
23.	Wijesinghe I, Gamage C, Perera I, Chitranjan C (2019)/Sri Lanka/IEEE Xplore(³⁴34. Wijesinghe I, Gamage C, Perera I, Chitranjan C. A smart telemedicine system with deep learning to manage diabetic retinopathy and foot ulcers. In 2019 Moratuwa Engineering Research Conference (MERCon); 2019; Moratuwa, Sri Lanka. USA: IEEE; 2019. p. 686–91. doi: http://dx.doi.org/10.1109/MERCon.2019.8818682. https://doi.org/10.1109/MERCon.2019.8818... )	Proposing a prototype of an autonomous system to guide the diagnosis and treatment of diabetic feet.	Machine learning(³⁴34. Wijesinghe I, Gamage C, Perera I, Chitranjan C. A smart telemedicine system with deep learning to manage diabetic retinopathy and foot ulcers. In 2019 Moratuwa Engineering Research Conference (MERCon); 2019; Moratuwa, Sri Lanka. USA: IEEE; 2019. p. 686–91. doi: http://dx.doi.org/10.1109/MERCon.2019.8818682. https://doi.org/10.1109/MERCon.2019.8818... )	Predicting the risk and diagnosing diabetic foot ulceration.	The system consists of knowledge-based modules for classification based on severity level, clinical decision support and near real-time foot ulcer detection and triage. The average usability score was 88.5, proving to be good but not exceptional.

Universidade de São Paulo, Escola de Enfermagem Av. Dr. Enéas de Carvalho Aguiar, 419 , 05403-000 São Paulo - SP/ Brasil, Tel./Fax: (55 11) 3061-7553, - São Paulo - SP - Brazil
E-mail: reeusp@usp.br

Acompanhe os números deste periódico no seu leitor de RSS

[1] Corresponding author: Thiago Santos Garces, Av. Dr. Silas Munguba, 1700, Itaperi, 60714-903 – Fortaleza, CE, Brazil, thiagogarces0812@hotmail.com