Machine Learning Analysis of Multispectral Imaging and Clinical Risk Factors to Predict Amputation Wound Healing

Abstract

Over 150,000 patients undergo nontraumatic lower extremity amputations in the United States annually. Selection of amputation level is a complicated clinical decision. The surgeon must balance the most functional level of amputation to maintain or improve quality of life against the likelihood for failure of healing at any given level of amputation (LOA). No single test is currently accepted as the gold standard for prediction of amputation wound healing. Surgeons must determine optimal LOA using clinical judgement, combining patient clinical risk factors, physical examination, and any available invasive or noninvasive vascular studies. Up to one-third of amputations fail to heal, requiring reamputation to a more proximal level. Failure of primary amputation wound healing decreases patient quality of life and adds substantially to the costs of care for patients with critical limb ischemia. Herein, we report the results of a pilot study evaluating the performance of an imaging system that implements a machine-learning algorithm to evaluate multispectral images of superficial tissues at selected LOA combined with patient clinical risk factors to predict amputation wound healing. This multicenter, institutional review board-approved, prospective study enrolled subjects with critical limb ischemia planned for lower extremity amputation. Adult patients were eligible for enrollment if they were planned for amputation due to critical limb ischemia with no option for revascularization and had an anticipated life expectancy exceeding 3 months. Patients scheduled for any procedure other than amputation which may affect wound healing (including invasive angiography) within the 30-days following amputation were excluded. Before imaging, the surgeon declared the intended LOA using clinical judgement based on subject history, physical examination, and any available perfusion studies such as invasive or noninvasive angiography, ankle-brachial indices, or toe pressures. Multispectral images of the superficial tissues at the intended LOA were acquired circumferentially to ensure inclusion of the amputation wound skin flap no more than 14 days before amputation. Surgeons were blinded to the multispectral imaging data. Subject past medical history including commonly accepted risk factors affecting wound healing were prospectively recorded. Postamputation wound care was performed according to the preferences of the operating surgeon. Subjects underwent a standardized wound healing assessment on approximately postoperative day 30. The surgeon, still blinded to multispectral imaging data, graded the amputation wound as “healing” or “nonhealing” according to prespecified criteria. Nonhealing status was assigned to any amputation wounds with necrosis, infection, ulceration, dehiscence, or hematoma formation; healing status was assigned to wounds with re-epithelialized tissue at the incision site with total absence of any criteria for nonhealing status. The multispectral imaging device measured reflectance of 8 wavelengths of light in the visible and near-infrared spectrum (400-1000 nanometers) to quantify key superficial tissue properties relevant to the microcirculation. A commonly used machine-learning architecture for image segmentation (Very Deep Convolutional Networks for Large-Scale Image Recognition) was modified with a Feature-wise Linear Modulation technique to integrate multispectral imaging data with patient clinical risk factors to train a machine-learning algorithm to predict primary amputation wound healing. The included patient clinical risk factors were determined by ranking absolute correlation coefficients between the prespecified clinical risk factors and 30-day wound healing outcome, utilizing clinical risk factors with an absolute correlation of greater than 0.25.The algorithm was trained and tested using leave-one-out cross-validation.8 The primary outcome was the performance of the machine learning algorithm using multispectral imaging and patient clinical risk factors as inputs to predict primary amputation wound healing. Secondary outcomes of interest were algorithm performance using only multispectral imaging data or only patient clinical risk factor data as inputs. Algorithm performance was assessed with measurements of accuracy, sensitivity, specificity, and area under the curve (AUC). Twenty-six patients were enrolled: 22 subjects completed the study and 4 were lost to early mortality. Twenty-five primary amputations were performed (10 toe, 5 transmetatarsal, 8 below-knee, and 2 above-knee). Of these, 11 (44%) were nonhealing after standardized assessment. Surgeon judgement was 56% accurate for predicting overall primary amputation wound healing: 40% accuracy for minor amputations (toe/transmetatarsal) and 80% accuracy for major amputations (below/above-knee). Patient demographics and clinical risk factors are listed in Table I; the 11 bolded entries had absolute correlation with wound healing exceeding 0.25 and were included in the machine-learning algorithm. When both multispectral imaging data and patient clinical risk factors were included in algorithm training, performance was 88% accuracy, 91% sensitivity and 86% specificity (AUC, 0.89). The algorithms trained on multispectral imaging data alone (71% accuracy, 66% sensitivity, and 75% specificity [AUC 0.70]) and clinical risk factors alone (70% accuracy, 46% sensitivity, 84% specificity [AUC 0.65]) underperformed as compared with the algorithm combining both datasets (Table II). In this pilot study, we have demonstrated the potential utility of an imaging system that combines multispectral imaging, patient clinical risk factors, and machine-learning analysis to predict primary amputation wound healing. The imaging system outperformed surgeon judgment (88% vs 56% accuracy). Amputations due to critical limb ischemia place a significant burden on our healthcare system, and reamputation/reoperation that occur after failure to heal the primary amputation significantly increase costs and hinder patient quality of life. Surgeons must use their best judgement, considering patient clinical risk factors, physical examination, and potentially a variety of invasive and noninvasive vascular studies to select optimal LOA. To offer the best functional outcome, surgeons must also balance a desire for maximum limb salvage against the increased likelihood that primary amputation wounds will fail to heal at more distal LOAs. Unfortunately, there is currently no available technology that is widely accepted and validated to select optimal LOA. This information and technology gap was recently highlighted by the American Heart Association Council on Peripheral Vascular Disease, which released a scientific statement summarizing the limitations of current technology and advocating for the development of improved imaging technologies. Historically, ankle-brachial indices have been considered when selecting LOA. However, the limitations of ABI for prediction of amputation healing have been repeatedly demonstrated. Furthermore, nearly 20% of patients have noncompressible vessels, rendering ankle-brachial indices nondiagnostic. Other technologies, including transcutaneous oxygen measurement and laser Doppler imaging, have been thoroughly studied for predication of amputation wound healing. Neither have become widely adopted due to important limitations, including high intraoperative variability, sensitivity to motion artifact and ambient room temperature, and uncertainty about interpretation of data output thresholds to predict healing. The imaging system investigated in this study may overcome several limitations of transcutaneous oxygen measurement and laser Doppler imaging. The system combines imaging data with patient clinical risk factors that influence wound healing, rather than focusing on a single measurement in isolation from other important conditions that may affect wound healing. The algorithm was trained to provide an easily interpreTable, binary output—healing versus nonhealing—rather than complex imaging maps or indices that may be subject to variable interpretation. There are also several limitations. This is a small pilot study. Formal algorithm training must be performed with a larger sample size, and validation of the algorithm should occur in an independent dataset before the wound imaging system should be used to aid in clinical decision making. The performance of the wound imaging system may also be subject to other factors not considered in our study including ambient room temperature during image collection as well as patient skin tone. Up to one-third of primary amputations require revision to a more proximal level. There is no gold-standard test currently available to predict healing of an amputation wound with high reliability. In this pilot study, we have demonstrated proof-of-concept for a novel imaging system that combines multispectral superficial tissue imaging with patient clinical risk factors via machine-learning analysis to predict primary amputation wound healing. Larger algorithm training and validation studies are planned. If the validation studies confirm our findings, this imaging system may offer significant savings and improved quality of life for patients with critical limb ischemia undergoing lower extremity amputation.Table ISubject demographics and clinical risk factors with correlation to 30-day primary amputation wound healing (N = 26)Subject demographics and clinical risk factorsValueaCorrelationFemale6 (23)0.12Age, years66 ± 110.03Race/Ethnicity Black6 (23)−0.12 Hispanic4 (15)0.05 Non-Hispanic White15 (58)0.07BMI, kg/m231 ± 70.29Diabetes, Type II25 (96)0.31HbA1c, %8.0 ± 1.9−0.33Diabetic neuropathy8 (31)0.08Current tobacco use4 (15)0.05History of tobacco use11 (42)0.03Level of amputation Toe10 (38)0.26 Transmetatarsal6 (23)0.16 Below-knee14 (54)−0.26 Above-knee4 (15)−0.26Prior amputation14 (54)−0.51Prior revascularization of ipsilateral extremity14 (54)0.14Prior myocardial infarction4 (15)0.27Prior cerebrovascular accident3 (12)−0.08Taking anticoagulation17 (65)0.19Creatinine, mg/dL2.2 ± 2.40.27Chronic kidney disease10 (38)0.43Currently on hemodialysis4 (15)0.27aContinuous variables reported as mean ± standard deviation; categorical variables reported as number (%). Open table in a new tab Table IIPerformance of primary amputation wound healing prediction by surgeons and machine learning algorithmsMethodAccuracySensitivitySpecificityAUCAccuracy Minor AmpsAccuracy Major AmpsSurgeon Judgement56%n/an/an/a40%80%Clinical Risk Factors Only70%46%84%0.65––MSI only71%66%75%0.70––MSI + Clinical Risk Factors88%91%86%0.8987%90%AUC, Area under curve; MSI, multispectral imaging.Minor amputations: Toe and transmetatarsal amputations.Major amputations: Above-knee and below-knee amputations. Open table in a new tab aContinuous variables reported as mean ± standard deviation; categorical variables reported as number (%). AUC, Area under curve; MSI, multispectral imaging. Minor amputations: Toe and transmetatarsal amputations. Major amputations: Above-knee and below-knee amputations.