Development of an explainable artificial intelligence model for Asian vascular wound images.

Chronic wounds contribute to significant healthcare and economic burden worldwide. Wound assessment remains challenging given its complex and dynamic nature. The use of artificial intelligence (AI) and machine learning methods in wound analysis is promising. Explainable modelling can help its integration and acceptance in healthcare systems. We aim to develop an explainable AI model for analysing vascular wound images among an Asian population. Two thousand nine hundred and fifty-seven wound images from a vascular wound image registry from a tertiary institution in Singapore were utilized. The dataset was split into training, validation and test sets. Wound images were classified into four types (neuroischaemic ulcer [NIU], surgical site infections [SSI], venous leg ulcers [VLU], pressure ulcer [PU]), measured with automatic estimation of width, length and depth and segmented into 18 wound and peri-wound features. Data pre-processing was performed using oversampling and augmentation techniques. Convolutional and deep learning models were utilized for model development. The model was evaluated with accuracy, F1 score and receiver operating characteristic (ROC) curves. Explainability methods were used to interpret AI decision reasoning. A web browser application was developed to demonstrate results of the wound AI model with explainability. After development, the model was tested on additional 15 476 unlabelled images to evaluate effectiveness. After the development on the training and validation dataset, the model performance on unseen labelled images in the test set achieved an AUROC of 0.99 for wound classification with mean accuracy of 95.9%. For wound measurements, the model achieved AUROC of 0.97 with mean accuracy of 85.0% for depth classification, and AUROC of 0.92 with mean accuracy of 87.1% for width and length determination. For wound segmentation, an AUROC of 0.95 and mean accuracy of 87.8% was achieved. Testing on unlabelled images, the model confidence score for wound classification was 82.8% with an explainability score of 60.6%. Confidence score was 87.6% for depth classification with 68.0% explainability score, while width and length measurement obtained 93.0% accuracy score with 76.6% explainability. Confidence score for wound segmentation was 83.9%, while explainability was 72.1%. Using explainable AI models, we have developed an algorithm and application for analysis of vascular wound images from an Asian population with accuracy and explainability. With further development, it can be utilized as a clinical decision support system and integrated into existing healthcare electronic systems.

Prospective study on the clinical and economic burden of venous leg ulcers in the tropics.

OBJECTIVE: Venous leg ulcers (VLUs) are both chronic and recurrent. The treatment of such ulcers often require multiple outpatient visits and dressing changes. Several reports on the costs of treating such VLUs have been reported in the west. We prospectively evaluated the clinical and economic burden of VLUs in a population of Asian patients in the tropics. METHODS: Patients from a prospective two-center study conducted at two tertiary hospitals in Singapore, as a part of the Wound Care Innovation in the Tropics program, between August 2018 and September 2021 were recruited. The patients were followed up for 12 weeks (visit 1 to visit 12), until index ulcer healing, death, or lost to follow-up (whichever came first). These patients were then followed up 12 weeks later to determine the longer term outcome of the wound (healed, recurrence, remained unhealed). The itemized costs derived from the medical service were retrieved from the relevant departments of the study sites. The patients' health-related quality of life was assessed at baseline and the last visit of the 12-week follow-up period (or until index ulcer healing), using the official Singapore version of the EuroQol five-dimension-5L questionnaire, which also includes a visual analog scale (EQ-VAS). RESULTS: A total of 116 patients were enrolled; 63% were men, and the mean patient age was 64.7 years. Of the 116 patients, 85 (73%) had a healed ulcer at 24 weeks (mean duration to ulcer healing, 49 days), and 11 (12.9%) had experienced ulcer recurrence within the study period. Within the 6-month follow-up period, the mean direct healthcare cost per patient was USD$1998. The patients with healed ulcers had significantly lower costs per patient compared with those with unhealed ulcers (USD$1713 vs USD$2780). Regarding health-related quality of life, 71% of the patients had a lower quality of life at baseline, which had improved at 12 weeks of follow-up, with only 58% of the patients reported to have a lower quality of life. Also, the patients with healed ulcers scored higher for both utilities (societal preference weights) and EQ-VAS at follow-up (P < .001). In contrast, patients with unhealed ulcers only scored higher EQ-VAS at follow-up (P = .003). CONCLUSIONS: The findings from this exploratory study provide information on the clinical, quality of life, and economic burden of VLUs in an Asian population and suggest the importance of healing VLUs to reduce the effects on patients. The present study provides data as a basis for economic evaluation as a consideration for the treatment of VLUs.

Clinical validation of a smartphone application for automated wound measurement in patients with venous leg ulcers.

Chronic wounds are associated with significant clinical, economic and quality-of-life burden. Despite the variety of wound imaging systems available in the market for wound assessment and surveillance, few are clinically validated among patients of Asian ethnicity. We aimed to clinically validate the accuracy of a smartphone wound application (Tissue Analytics [TA], Net Health Systems Inc, Florida, USA), versus conventional wound measurements (visual approximation and paper rulers), in patients of Asian ethnicity with venous leg ulcers (VLU). A prospective cohort study of patients presenting with VLU to a specialist wound nurse clinic over a 5-week duration was conducted. Each patient received seven wound measurements: one by a trained wound nurse clinician, and three separate wound measurements using TA on each of the iOS and Android operating systems. Inter-rater and intra-rater reliability between clinical and TA-based measurements were analysed using intra-class correlation statistics, with values of <0.5, 0.5 to 0.75, 0.75 to 0.9, and >0.9 indicating poor, moderate, good and excellent reliability, respectively. 82 patients (51% males), with a mean age at 65.8 years, completed the 5-week study duration. 25 (30%) had underlying diabetes mellitus. Chinese, Malay and Indian ethnicity comprised 68%, 12% and 11%, respectively. The VLU healed in 26 (32%) of patients within the study period. In total, 358 wound episodes with 2334 wound images were analysed. Inter-rater reliability for length, width and area between wound nurse measurements and TA application measurements was good (range 0.799-0.919, P < 0.001). Separate measurements of intra-rater reliability for length, width and area within the iOS or Android systems were excellent (range 0.967-0.985 and range 0.977-0.984 respectively, P < 0.001). Inter-rater reliability between TA used on the iOS and Android systems was also excellent (0.987-0.989, P < 0.001). Tissue Analytics, a smartphone wound application, is a useful adjunct for wound assessment and surveillance in VLU patients of Asian ethnicity.

Clinical and economic outcomes of a multidisciplinary team approach in a lower extremity amputation prevention programme for diabetic foot ulcer care in an Asian population: A case-control study.

Present guidelines recommend a multidisciplinary team (MDT) approach to diabetic foot ulcer (DFU) care, but relevant data from Asia are lacking. We aim to evaluate the clinical and economic outcomes of an MDT approach in a lower extremity amputation prevention programme (LEAPP) for DFU care in an Asian population. We performed a case-control study of 84 patients with DFU between January 2017 and October 2017 (retrospective control) vs 117 patients with DFU between December 2017 and July 2018 (prospective LEAPP cohort). Comparing the clinical outcomes between the retrospective cohort and the LEAPP cohort, there was a significant decrease in mean time from referral to index clinic visit (38.6 vs 9.5 days, P < .001), increase in outpatient podiatry follow-up (33% vs 76%, P < .001), decrease in 1-year minor amputation rate (14% vs 3%, P = .007), and decrease in 1-year major amputation rate (9% vs 3%, P = .05). Simulation of cost avoidance demonstrated an annualised cost avoidance of USD $1.86m (SGD $2.5m) for patients within the LEAPP cohort. In conclusion, similar to the data from Western societies, an MDT approach in an Asian population, via a LEAPP for patients with DFU, demonstrated a significant reduction in minor and major amputation rates, with annualised cost avoidance of USD $1.86m.

Clinical validation of a machine-learning-based handheld 3-dimensional infrared wound imaging device in venous leg ulcers.

Chronic venous insufficiency is a chronic disease of the venous system with a prevalence of 25% to 40% in females and 10% to 20% in males. Venous leg ulcers (VLUs) result from venous insufficiency. VLUs have a prevalence of 0.18% to 1% with a 1-year recurrence of 25% to 50%, bearing significant socioeconomic burden. It is therefore important for regular assessment and monitoring of VLUs to prevent worsening. Our study aims to assess the intra- and inter-rater reliability of a machine learning-based handheld 3-dimensional infrared wound imaging device (WoundAide [WA] imaging system, Konica Minolta Inc, Tokyo, Japan) compared with traditional measurements by trained wound nurse. This is a prospective cross-sectional study on 52 patients with VLUs from September 2019 to January 2021 using three WA imaging systems. Baseline patient profile and clinical demographics were collected. Basic wound parameters (length, width and area) were collected for both traditional measurements and measurements taken by the WA imaging systems. Intra- and inter-rater reliability was analysed using intra-class correlation statistics. A total of 222 wound images from 52 patients were assessed. There is excellent intra-rater reliability of the WA imaging system on three different image captures of the same wound (intra-rater reliability ranging 0.978-0.992). In addition, there is excellent inter-rater reliability between the three WA imaging systems for length (0.987), width (0.990) and area (0.995). Good inter-rater reliability for length and width (range 0.875-0.900) and excellent inter-rater reliability (range 0.932-0.950) were obtained between wound nurse measurement and each of the WA imaging system. In conclusion, high intra- and inter-rater reliability was obtained for the WA imaging systems. We also obtained high inter-rater reliability of WA measurements against traditional wound measurement. The WA imaging system is a useful clinical adjunct in the monitoring of VLU wound documentation.

Effectiveness of skin cleanser and protectant regimen on incontinence-associated dermatitis outcomes in acute care patients: A cluster randomised trial.

Skin cleansers and protectants protect skin from incontinent matter to reduce the risk of incontinence-associated dermatitis (IAD), but their effectiveness treating established IAD in the tropics is unknown. We conducted an open-label cluster randomised trial to compare the effectiveness of a combined regimen of (1) specialised skin cleansers with disposable body wipes and (2) either an acrylic terpolymer (T1) or zinc oxide (T2) skin protectant against disposable body wipes and zinc oxide protectant (control) in promoting IAD healing and reducing the risk of deterioration. Eighty-four patients were recruited in a tertiary hospital in Singapore between April 2019 and January 2020 (T1: n = 23; T2: n = 37; Control: n = 24). Although not statistically significant, patients treated with T1 and T2 were 1.5 times as likely to experience IAD healing within seven days compared with the control (P = .66). Healing was more pronounced in participants with skin loss treated with T1 or T2. No treatment was superior in preventing IAD deterioration, the prevalence of which remained small (8%-14%). While skin cleaning and protectants reduced the overall risk of skin deterioration, the addition of skin cleansers enhanced IAD healing within a short period, an important consideration for future research examining IAD treatment in acute care.