Artificial intelligence for diabetes care: current and future prospects

Artificial intelligence (AI) use in diabetes care is increasingly being explored to personalise care for people with diabetes and adapt treatments for complex presentations. However, the rapid advancement of AI also introduces challenges such as potential biases, ethical considerations, and implementation challenges in ensuring that its deployment is equitable. Ensuring inclusive and ethical developments of AI technology can empower both health-care providers and people with diabetes in managing the condition. In this Review, we explore and summarise the current and future prospects of AI across the diabetes care continuum, from enhancing screening and diagnosis to optimising treatment and predicting and managing complications.

Clinical outcome and determinants of amputation in a large cohort of Iranian patients with diabetic foot ulcers

OBJECTIVE

Determining the predictive factors of diabetes foot ulcer (DFU) development and lower extremity amputations (LEA) in patients with diabetes mellitus (DM) is of great importance to compose risk stratification models. The aim of this study is to investigate the outcome and predictors of LEA in patients with DFU in large sample of Iranian patients.

METHODS

This prospective cohort study was conducted during a 2-year period from 2014 to 2016, in Shiraz, southern Iran. All the patients with type 1 and 2 DM and DFU were included in the cohort and were followed for 2 years at least. They were visited in the clinic on a monthly basis and development of new DFU and LEA were recorded. The two-year free-DFU survival and predictors of the DFU development and LEA were recorded. Multivariate regression models were used to determine the factors.

RESULTS

A total number of 432 patients with mean age of 56.8 ± 13.3 years were included. The two-year DFU-free survival rate was 0.826. The two-year DFU-free survival was associated with male gender (p = 0.005), foot deformity (p = 0.002), history of prior DFU (p < 0.001), cigarette smoking (p = 0.032), nephropathy (p = 0.005), retinopathy (p = 0.007), ischemic heart disease (p = 0.043), and neuropathy (p < 0.001).

CONCLUSION

Development of new DFU is associated with higher age, longer duration of disease, and type I diabetes. LEA was associated with increased white blood cell (WBC), Creatinine and ulcer history for major amputation and ulcer history, fasting blood sugar (FBS), infection, revascularization history, and foot deformity, for minor amputation.

Hyperspectral imaging in wound care: A systematic review

Multispectral and hyperspectral imaging (HSI) are emerging imaging techniques with the potential to transform the way patients with wounds are cared for, but it is not clear whether current systems are capable of delivering real-time tissue characterisation and treatment guidance. We conducted a systematic review of HSI systems that have been assessed in patients, published over the past 32 years. We analysed 140 studies, including 10 different HSI systems. Current in vivo HSI systems generate a tissue oxygenation map. Tissue oxygenation measurements may help to predict those patients at risk of wound formation or delayed healing. No safety concerns were reported in any studies. A small number of studies have demonstrated the capabilities of in vivo label-free HSI, but further work is needed to fully integrate it into the current clinical workflow for different wound aetiologies. As an emerging imaging modality for medical applications, HSI offers great potential for non-invasive disease diagnosis and guidance when treating patients with both acute and chronic wounds.

Hyperspectral imaging in wound care: A systematic review

Multispectral and hyperspectral imaging (HSI) are emerging imaging techniques with the potential to transform the way patients with wounds are cared for, but it is not clear whether current systems are capable of delivering real-time tissue characterisation and treatment guidance. We conducted a systematic review of HSI systems that have been assessed in patients, published over the past 32 years. We analysed 140 studies, including 10 different HSI systems. Current in vivo HSI systems generate a tissue oxygenation map. Tissue oxygenation measurements may help to predict those patients at risk of wound formation or delayed healing. No safety concerns were reported in any studies. A small number of studies have demonstrated the capabilities of in vivo label-free HSI, but further work is needed to fully integrate it into the current clinical workflow for different wound aetiologies. As an emerging imaging modality for medical applications, HSI offers great potential for non-invasive disease diagnosis and guidance when treating patients with both acute and chronic wounds.

Diagnosis of infection in the foot in diabetes: a systematic review

BACKGROUND

Securing an early accurate diagnosis of diabetic foot infections and assessment of their severity are of paramount importance since these infections can cause great morbidity and potentially mortality and present formidable challenges in surgical and antimicrobial treatment.

METHODS

In June 2018, we searched the literature using PuEbMed and EMBASE for published studies on the diagnosis of diabetic foot infection. On the basis of predetermined criteria, we reviewed prospective controlled, as well as noncontrolled, studies in any language, seeking translations for those not in English. We then developed evidence statements on the basis of the included papers.

RESULTS

From the 4242 records screened, we selected 35 papers that met our inclusion criteria. The quality of all but one of the evidence statements was low because of the weak methodology of nearly all of the studies. The available data suggest that diagnosing diabetic foot infections on the basis of clinical signs and symptoms and classified according to the International Working Group of the Diabetic Foot scheme correlates with the patient's likelihood of ulcer healing, of lower extremity amputation, and risk of death. Elevated levels of selected serum inflammatory markers are supportive, but not diagnostic, of soft tissue or bone infection. In patients with suspected diabetic foot osteomyelitis, both a positive probe-to-bone test and an elevated erythrocyte sedimentation rate are strongly associated with its presence. Culturing tissue samples of soft tissues or bone, when care is taken to avoid contamination, provides more accurate microbiological information than culturing superficial (swab) samples. Plain X-ray remains the first-line imaging examination when there is suspicion of diabetic foot osteomyelitis, but advanced imaging methods help in cases when either the diagnosis or the localization of infection is uncertain.

CONCLUSION

The results of this first reported systematic review on the diagnosis of diabetic foot infections provide some guidance for clinicians, but there is a need for more prospective controlled studies of high quality.