The Wound Healing Index for Predicting Venous Leg Ulcer Outcome

Establishing and clinically validating a machine learning model for predicting unplanned reoperation risk in colorectal cancer

BACKGROUND

Colorectal cancer significantly impacts global health, with unplanned reoperations post-surgery being key determinants of patient outcomes. Existing predictive models for these reoperations lack precision in integrating complex clinical data.

AIM

To develop and validate a machine learning model for predicting unplanned reoperation risk in colorectal cancer patients.

METHODS

Data of patients treated for colorectal cancer (n = 2044) at the First Affiliated Hospital of Wenzhou Medical University and Wenzhou Central Hospital from March 2020 to March 2022 were retrospectively collected. Patients were divided into an experimental group (n = 60) and a control group (n = 1984) according to unplanned reoperation occurrence. Patients were also divided into a training group and a validation group (7:3 ratio). We used three different machine learning methods to screen characteristic variables. A nomogram was created based on multifactor logistic regression, and the model performance was assessed using receiver operating characteristic curve, calibration curve, Hosmer-Lemeshow test, and decision curve analysis. The risk scores of the two groups were calculated and compared to validate the model.

RESULTS

More patients in the experimental group were ≥ 60 years old, male, and had a history of hypertension, laparotomy, and hypoproteinemia, compared to the control group. Multiple logistic regression analysis confirmed the following as independent risk factors for unplanned reoperation (P < 0.05): Prognostic Nutritional Index value, history of laparotomy, hypertension, or stroke, hypoproteinemia, age, tumor-node-metastasis staging, surgical time, gender, and American Society of Anesthesiologists classification. Receiver operating characteristic curve analysis showed that the model had good discrimination and clinical utility.

CONCLUSION

This study used a machine learning approach to build a model that accurately predicts the risk of postoperative unplanned reoperation in patients with colorectal cancer, which can improve treatment decisions and prognosis.

Dynamic prediction of time to wound healing at routine wound care visits

Objective Having a wound decreases patients' quality of life and brings uncertainty, especially if the wound does not show a healing tendency. The objective of this study was to develop and validate a model to dynamically predict time to wound healing at subsequent routine wound care visits. Approach A dynamic prediction model was developed in a cohort of wounds treated by nurse practitioners between 2017-2022. Potential predictors were selected based on literature, expert opinion, and availability in the routine care setting. To assess performance for future wound care visits, the model was validated in a new cohort of wounds visited in early 2023. Reporting followed TRIPOD guidelines. Results We analyzed data from 92,098 visits, corresponding to 14,248 wounds and 7,221 patients. At external validation, discriminative performance of our developed model was comparable to internal validation (c-statistic = 0.70 [95% CI 0.69, 0.71]) and the model remained well-calibrated. Strong predictors were wound-level characteristics and indicators of the healing process so far (e.g., wound surface area). Innovation Going beyond previous prediction studies in the field, the developed model dynamically predicts the remaining time to wound healing for many wound types at subsequent wound care visits, in line with the dynamic nature of wound care. In addition, the model was externally validated and showed stable performance. Conclusion: The developed model can potentially contribute to patient satisfaction and reduce uncertainty around wound healing times when implemented in practice. When the predicted time of wound healing remains high, practitioners can consider adapting their wound management.

An Improved Clinical and Genetics-Based Prediction Model for Diabetic Foot Ulcer Healing

Objective: The goal of this investigation was to use comprehensive prediction modeling tools and available genetic information to try to improve upon the performance of simple clinical models in predicting whether a diabetic foot ulcer (DFU) will heal. Approach: We utilized a cohort study (n = 206) that included clinical factors, measurements of circulating endothelial precursor cells (CEPCs), and fine sequencing of the NOS1AP gene. We derived and selected relevant predictive features from this patient-level information using statistical and machine learning techniques. We then developed prognostic models using machine learning approaches and assessed predictive performance. The presentation is consistent with TRIPOD requirements. Results: Models using baseline clinical and CEPC data had an area under the receiver operating characteristic curve (AUC) of 0.73 (0.66-0.80). Models using only single nucleotide polymorphisms (SNPs) of the NOS1AP gene had an AUC of 0.67 (95% confidence interval, CI: [0.59-0.75]). However, models incorporating baseline and SNP information resulted in improved AUC (0.80, 95% CI [0.73-0.87]). Innovation: We provide a rigorous analysis demonstrating the predictive potential of genetic information in DFU healing. In this process, we present a framework for using advanced statistical and bioinformatics techniques for creating superior prognostic models and identify potentially predictive SNPs for future research. Conclusion: We have developed a new benchmark for which future predictive models can be compared against. Such models will enable wound care experts to more accurately predict whether a patient will heal and aid clinical trialists in designing studies to evaluate therapies for subjects likely or unlikely to heal.

Comparative Effectiveness of Placental Allografts in the Treatment of Diabetic Lower Extremity Ulcers and Venous Leg Ulcers in U.S. Medicare Beneficiaries: A Retrospective Observational Cohort Study Using Real-World Evidence

Objective: To compare the effectiveness of cellular tissue products (CTP) versus standard care in U.S. Medicare beneficiaries with diabetic lower extremity ulcers (DLEUs) or venous leg ulcers (VLUs). Approach: We performed a retrospective cohort study using real-world evidence from U.S. Medicare claims for DLEUs or VLUs between 2016 and 2020. There were three cohorts evaluated: viable cryopreserved placental membrane (vCPM) or viable lyopreserved placental membrane (vLPM); other CTP; and standard care. Claims were collapsed into episodes of care. Univariate and bivariate statistics were used to examine the frequency distribution of demographics and clinical variables. Multivariable zero-inflated binomial regressions were used to evaluate mortality and recurrence trends. Logistic regression compared three adverse outcomes (AOs): amputation; 1-year mortality; and wound recurrence. Results: There were 333,362 DLEU episodes among 261,101 beneficiaries, and 122,012 VLU episodes among 80,415 beneficiaries. DLEU treatment with vLPM was associated with reduced 1-year mortality (-26%), reduced recurrence (-91%), and reduced AOs (-71%). VLU treatment with vCPM or vLPM was associated with reduced 1-year mortality (-23%), reduced recurrence (-80%), and 66.77% reduction in AOs. These allografts were also associated with a 49% and 73% reduced risk of recurrence in DLEU and VLU, respectively, compared with other CTPs. Finally, vCPM or vLPM were associated with noninferior prevention of AOs related to amputation, mortality, and recurrence (95% CI: 0.69-1.14). Conclusions: DLEUs and VLUs treated with vCPM and vLPM allografts are associated with lowered 1-year mortality, wound recurrence, and AOs in DLEUs and VLUs compared with standard care. Decision makers weighing coverage of placental allografts should consider these added short- and long-term clinical benefits relative to costly management and high mortality of Medicare's most frequent wounds.

Prognostic models for clinical outcomes in patients with venous leg ulcers: A systematic review

OBJECTIVE

The purpose of this review was to identify prognostic models for clinical application in patients with venous leg ulcers (VLUs).

METHODS

Literature searches were conducted in Embase, Medline, Cochrane, and CINAHL databases from inception to December 22, 2021. Eligible studies reported prognostic models aimed at developing, validating, and adjusting multivariable prognostic models that include multiple prognostic factors combined, and that predicted clinical outcomes. Methodological quality was assessed using the CHARMS checklist and PROBAST short form questionnaire.

RESULTS

Thirteen studies were identified, of which three were validation studies of previously published models, four reported derivation and validation of models, and the remainder reported derivation models only. There was substantial heterogeneity in the model characteristics, including 11 studies focused on wound healing outcomes reporting 91 different predictors. Three studies shared similar predicted outcomes, follow-up timepoint and used a Cox proportional hazards model. However, these models reported different predictor selection methods and different predictors and it was therefore not feasible to summarize performance, such as discriminative ability.

CONCLUSIONS

There are no standout risk prediction models in the literature with promising clinical application for patients with VLUs. Future research should focus on developing and validating high-performing models in wider VLU populations.

A prospective study on the wound healing and quality of life outcomes of patients with venous leg ulcers in Singapore-Interim analysis at 6 month follow up

Venous leg ulceration results in significant morbidity. However, the majority of studies conducted are on Western populations. This study aims to evaluate the wound healing and quality of life for patients with venous leg ulcers (VLUs) in a Southeast Asian population. This is a multi-centre prospective cohort study from Nov 2019 to Nov 2021. All patients were started on 2- or 4-layer compression bandage and were reviewed weekly or fortnightly. Our outcomes were wound healing, factors predictive of wound healing and the EuroQol 5-dimensional 5-level (EQ-5D-5L) health states. Within our cohort, there were 255 patients with VLU. Mean age was 65.2 ± 11.6 years. Incidence of diabetes mellitus was 42.0%. Median duration of ulcer at baseline was 0.30 years (interquartile range 0.136-0.834). Overall, the median time to wound healing was 4.5 months (95% confidence interval [CI]: 3.77-5.43). The incidence of complete wound healing at 3- and 6-month was 47.0% and 60.9%, respectively. The duration of the wound at baseline was independently associated with worse wound healing (Hazard ratio 0.94, 95% CI: 0.89-0.99, P = .014). Patients with healed VLU had a significantly higher incidence of perfect EQ-5D-5L health states at 6 months (57.8% vs 13.8%, P < .001). We intend to present longer term results in subsequent publications.

Individualized Risk Prediction for Improved Chronic Wound Management

Significance: Chronic wounds are associated with significant morbidity, marked loss of quality of life, and considerable economic burden. Evidence-based risk prediction to guide improved wound prevention and treatment is limited by the complexity in their etiology, clinical underreporting, and a lack of studies using large high-quality datasets. Recent Advancements: The objective of this review is to summarize key components and challenges in the development of personalized risk prediction tools for both prevention and management of chronic wounds, while highlighting several innovations in the development of better risk stratification. Critical Issues: Regression-based risk prediction approaches remain important for assessment of prognosis and risk stratification in chronic wound management. Advances in statistical computing have boosted the development of several promising machine learning (ML) and other semiautomated classification tools. These methods may be better placed to handle large number of wound healing risk factors from large datasets, potentially resulting in better risk prediction when combined with conventional methods and clinical experience and expertise. Future Directions: Where the number of predictors is large and heterogenous, the correlations between various risk factors complex, and very large data sets are available, ML may prove a powerful adjuvant for risk stratifying patients predisposed to chronic wounds. Conventional regression-based approaches remain important, particularly where the number of predictors is relatively small. Translating estimated risk derived from ML algorithms into practical prediction tools for use in clinical practice remains challenging.

Initial Reduction in Ulcer Size As a Prognostic Indicator for Complete Wound Healing: A Systematic Review of Diabetic Foot and Venous Leg Ulcers

Significance: Percent area reduction (PAR) is commonly reported in trials including diabetic foot ulcers (DFUs) and venous leg ulcers (VLUs). It is unclear how well PAR performs as a surrogate marker for complete wound closure. This review aimed to summarize all available evidence evaluating PAR as a predictor of complete DFU and VLU healing. Recent Advances: A review searching the CENTRAL, MEDLINE, EMBASE, and EMCARE databases was conducted in accordance with Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). Randomized-controlled trials and observational studies reporting PAR and any measure of its predictive ability were included. Outcomes included performance measures of PAR, timing of PAR, outcome measurement, and specific PAR cutoffs. Critical Issues: Meta-analysis was not possible due to high variability in wound duration at study start (2-48 weeks), PAR timing (2-8 weeks), PAR cutoff (-3% to 90%; determined post hoc in most studies), and outcome assessment (10-24 weeks). Six studies (21,430 DFU patients) report PAR as having acceptable to outstanding discriminatory ability (C-statistic 0.720-0.910). Five studies (29,775 VLU patients) report PAR as having poor to excellent discriminatory ability (C-statistic 0.680-0.830). One study (241 DFU and VLU patients) reports PAR sensitivity and specificity of 58.5% and 90.5%, respectively. All studies were determined to have high risk of bias. Future Directions: Despite promising discriminatory ability, most studies report post hoc analysis of patients in randomized trials, are highly heterogenous in study design, and have high risk of bias. There is scant evidence to support PAR in isolation as a surrogate for complete DFU or VLU healing in routine clinical practice.

Association between cardiac conditions with venous leg ulcers in patients with chronic venous insufficiency

INTRODUCTION

Venous leg ulcers (VLUs) are the final stage of chronic venous insufficiency. This study aims to characterize the association between cardiovascular diseases and VLU.

METHODS

A multicentric case-control study analyzed 17,788 patients between 2015 and 2020. Cases were matched (1:2) by age and sex, and odds ratios (OR) were analyzed with conditional logistic regressions adjusted by risk factors.

RESULTS

The prevalence of VLU was 15.2%. 2390 cases were analyzed. Diseases found to be associated with VLU were atrial fibrillation (OR, 1.21; 95% CI: 1.03-1.42), pulmonary hypertension (OR, 1.45; 95% CI: 1.06-2.00), right heart failure (OR, 1.27; 95% CI: 1.13-1.43), peripheral artery disease (OR, 2.21; 95% CI: 1.90-2.56), and history of pulmonary embolism (OR, 1.45; 95% CI: 1.06-2.00).

CONCLUSIONS

Certain cardiovascular conditions showed an association with VLU. Further studies are warranted to evaluate the effect that treating concomitant cardiovascular diseases might exert on the natural history of venous leg ulcers.

A wound alkalinity measurement to predict non-healing wound outcomes

Objective:

As wound pH could influence wound healing rates, this study examined the alkalinity of the entire wound during patients' follow-up visits to predict the final non-healing outcome.

Method:

Wound alkalinity of patients with diabetic foot ulcers (DFUs), venous leg ulcers, and other wounds during three follow-up visits within a four week period was recorded. All wounds were followed until 12 weeks to confirm that healed wounds did not relapse. The alkalinity of various wounds over multiple visits with varying durations was compared with final wound status to assess whether one-time wound alkalinity measurement could predict non-healing wounds. The effect of wound types, infection, age and sex on such determinations was also studied.

Results:

A total of 96 patients were included in this study. Based on probability variations of pre- and post-test non-healing outcomes from multiple visits over 12 weeks, second visit assessment gave the highest increase in risk of non-healing for an alkaline test result (+8.0%) and decrease in risk of non-healing for a non-alkaline test result (–19.7%). Moreover, a second visit (7–21 days from first visit) showed a greater change in risk for non-healing based on alkaline and non-alkaline test results (+15.7% and –38.1% respectively), compared with a visit within seven days (+6.3% and –12.5%, respectively). Wound type, infection, age and sex did not affect the prognostic ability of wound alkalinity.

Conclusion:

The results of this study support that a single wound alkalinity measurement during the second visit (7–21 days from first visit) can be used to predict non-healing wounds. Wound alkalinity may be routinely assessed to predict non-healing wounds and to determine whether the wounds are healing as expected following initial treatment.

Outcomes of present-on-admission pressure injuries at discharge and potential prognostic factors: A historical cohort study in China

BACKGROUND

The prevalence of present-on-admission pressure injuries (POA-PIs) is much higher than hospital-acquired pressure injuries (HAPIs). But scant attention has been paid to POA-PIs, especially the healing rate and potential prognostic factors.

OBJECTIVE

To describe the characteristics of POA-PIs at admission and the outcomes of POA-PIs at discharge, and to explore potential prognostic factors of POA-PIs wound healing.

METHODS

This study analyzed electronic health records (EHRs) for 838 POA-PIs among 586 patients from a Chinese tertiary hospital in 2018. The outcomes of POA-PIs were identified into four categories by comparing POA-PIs' wound area and exudation amount scores at admission and discharge: deteriorating, stable, improving, and healed. The generalized estimating equation (GEE) was carried out to screen the prognostic factors of POA-PIs wound healing.

RESULTS

Among this population, 66.38% of the patients were male, 44.03% patients had a Braden Score less than 12 and the median of the Charlson comorbidity index was 5. The most common location of POA-PI wounds was the sacrum and the most common stage of them was Stage II. Nearly half of wounds (45.78%) were larger than 15 cm², 26.61% were deeper than 0.5 cm, and 61.81% of the wounds were painful. When the patients were discharged, 29.71% wounds were healed, 36.16% were in improving status, 25.78% kept stable, and 8.35% wounds were in deteriorating status. Wound depth was the only independent prognostic factor for POA-PIs wound healing.

CONCLUSIONS

The healing rate of POA-PIs is quite low, and the only independent prognostic factor of POA-PIs was wound depth.

Review of the Current Evidence for Topical Treatment for Venous Leg Ulcers

OBJECTIVE

The development of a venous leg ulcer (VLU) represents the most severe clinical manifestation of a chronic venous disease. Despite major progress, there is a limited understanding of VLU pathogenesis and wound healing biology. Treatment of VLUs remains a serious challenge for physicians of different specialties. This communication focuses on describing the rationale and scientific basis for topical wound care in the management of VLUs.

METHODS

A literature review was performed to summarize methods with proven efficacy in VLU management. A systematic literature search was also performed to identify new evidence from the randomized controlled trials published within 2014-2021. The scientific challenges, clinical practice concerns, economic obstacles, and possible directions for further research have been discussed.

RESULTS

Hundreds of topical products have been advertised for the treatment of VLUs. Published data on topical treatment of venous ulcers is insufficient, scattered, weak, and has significant methodological flaws. Forty-three randomized controlled trials on topical treatment of VLUs have been published within 2014-2021. Clinical practice guidelines need to be updated. Major gaps in knowledge have been identified, and suggestions for future research directions have been provided.

CONCLUSIONS

The American Venous Forum Research Committee would like to bring attention to topical wound care for VLUs as a critical gap in knowledge, and encourage scientists, practitioners, and industry to collaborate to fill this gap.

Wound Care for Venous Ulceration

Venous leg ulcers (VLUs) affect as many as 20% of patients with advanced chronic venous insufficiency and are associated with significant morbidity and health care costs. VLUs are the most common cause of leg ulcers; however, other etiologies of lower extremity ulcerations should be investigated, most notably arterial insufficiency, to ensure appropriate therapy. Careful clinical examination, standardized documentation, and ultrasound evaluation are needed for diagnosis and treatment success. Reduction of edema and venous hypertension through compression therapy, local wound care, and treatment of venous reflux or obstruction is the foundation of therapy. As key providers in venous disease, interventional radiologists should be aware of current standardized disease classification and scoring systems as well as treatment and wound care guidelines for venous ulcers.