The impact of machine learning on the prediction of diabetic foot ulcers - A systematic review.

INTRODUCTION: Globally, diabetes mellitus poses a significant health challenge as well as the associated complications of diabetes, such as diabetic foot ulcers (DFUs). The early detection of DFUs is important in the healing process and machine learning may be able to help inform clinical staff during the treatment process. METHODS: A PRISMA-informed search of the literature was completed via the Cochrane Library and MEDLINE (OVID), EMBASE, CINAHL Plus and Scopus databases for reports published in English and in the last ten years. The primary outcome of interest was the impact of machine learning on the prediction of DFUs. The secondary outcome was the statistical performance measures reported. Data were extracted using a predesigned data extraction tool. Quality appraisal was undertaken using the evidence-based librarianship critical appraisal tool. RESULTS: A total of 18 reports met the inclusion criteria. Nine reports proposed models to identify two classes, either healthy skin or a DFU. Nine reports proposed models to predict the progress of DFUs, for example, classing infection versus non-infection, or using wound characteristics to predict healing. A variety of machine learning techniques were proposed. Where reported, sensitivity = 74.53-98 %, accuracy = 64.6-99.32 %, precision = 62.9-99 %, and the F-measure = 52.05-99.0 %. CONCLUSIONS: A variety of machine learning models were suggested to successfully classify DFUs from healthy skin, or to inform the prediction of DFUs. The proposed machine learning models may have the potential to inform the clinical practice of managing DFUs and may help to improve outcomes for individuals with DFUs. Future research may benefit from the development of a standard device and algorithm that detects, diagnoses and predicts the progress of DFUs.

Genomics and insurance in the United Kingdom: increasing complexity and emerging challenges.

This article identifies issues relating to the use of genetics and genomics in risk-rated insurance that may challenge existing regulatory models in the UK and elsewhere. We discuss three core issues: (1) As genomic testing advances, and results are increasingly relevant to guide healthcare across an individual's lifetime, the distinction between diagnostic and predictive testing that the current UK insurance code relies on becomes increasingly blurred. (2) The emerging category of pharmacogenetic tests that are predictive only in the context of a specific prescribing moment. (3) The increasing availability and affordability of polygenic scores that are neither clearly diagnostic nor highly predictive, but which nonetheless might have incremental value for risk-rated insurance underwriting beyond conventional factors. We suggest a deliberative approach is required to establish when and how genetic information can be used in risk-rated insurance.

Public preferences for pharmacogenetic testing in the NHS: Embedding a discrete choice experiment within service design to better meet user needs.

AIMS: Genetic testing can be used to improve the safety and effectiveness of commonly prescribed medicines-a concept known as pharmacogenetics. This study aimed to quantify members of the UK public's preferences for a pharmacogenetic service to be delivered in primary care in the National Health Service. METHODS: Members of the UK population were surveyed via an online panel company. Respondents completed 1 of 2 survey versions, asking respondents to select their preferred pharmacogenetic testing service in the context of a presentation of low mood or pain. A conditional logit model was estimated, before the best functional form for the dataset was identified. Preference heterogeneity was identified via latent class analysis. Coefficients from the final selected models were used to estimate uptake in the context of different hypothetical pharmacogenetic services. RESULTS: Responses from 1993 individuals were included in the analysis. There were no differences observed in preference between the 2 clinical scenarios. Conditional logit analysis, using maximum likelihood estimation, indicated that respondents preferred to have noninvasive tests and wanted their data to be shared between different healthcare organizations to guide future prescribing. There was a preference for regional over national data sharing initiatives, and respondents preferred to have access to their data. Predicted uptake varied considerably, ranging from 51% to >99%, depending on design of the service. CONCLUSION: This study identifies public preferences for a pharmacogenetic testing service and demonstrates how predicted uptake can be impacted by relatively minor adaptations. This highlights areas for prioritization during development of future pharmacogenetic services.

A metabolic signature for NADSYN1-dependent congenital NAD deficiency disorder.

Nicotinamide adenine dinucleotide (NAD) is essential for embryonic development. To date, biallelic loss-of-function variants in 3 genes encoding nonredundant enzymes of the NAD de novo synthesis pathway - KYNU, HAAO, and NADSYN1 - have been identified in humans with congenital malformations defined as congenital NAD deficiency disorder (CNDD). Here, we identified 13 further individuals with biallelic NADSYN1 variants predicted to be damaging, and phenotypes ranging from multiple severe malformations to the complete absence of malformation. Enzymatic assessment of variant deleteriousness in vitro revealed protein domain-specific perturbation, complemented by protein structure modeling in silico. We reproduced NADSYN1-dependent CNDD in mice and assessed various maternal NAD precursor supplementation strategies to prevent adverse pregnancy outcomes. While for Nadsyn1+/- mothers, any B3 vitamer was suitable to raise NAD, preventing embryo loss and malformation, Nadsyn1-/- mothers required supplementation with amidated NAD precursors (nicotinamide or nicotinamide mononucleotide) bypassing their metabolic block. The circulatory NAD metabolome in mice and humans before and after NAD precursor supplementation revealed a consistent metabolic signature with utility for patient identification. Our data collectively improve clinical diagnostics of NADSYN1-dependent CNDD, provide guidance for the therapeutic prevention of CNDD, and suggest an ongoing need to maintain NAD levels via amidated NAD precursor supplementation after birth.

MT-RNR1 Genotype Should Not Affect Childhood Vaccination-Unintended Consequences of Guidelines.

This Viewpoint discusses whether routine vaccination is safe for children with MT-RNR1 gene variants that predispose to aminoglycoside-induced hearing loss.

Metastatic HER2 lacrimal/salivary gland duct adenocarcinoma.

In this report, we present a case of a patient with a 30-year history of orbital asymmetry who presented with metastatic human epidermal growth factor receptor 2 (HER2) positive lacrimal/salivary gland ductal adenocarcinoma. The patient was treated with chemoradiotherapy and trastuzumab. Tumours of lacrimal gland origin are rare, and unfortunately can frequently present in late stage. There are no current guidelines on the optimal treatment of metastatic lacrimal gland tumours, in particular those with HER2 amplified malignancy. This case highlights a unique presentation of a rare disease, and the potential for targeted therapy.

The Implementation of Pharmacogenetics in the United Kingdom.

There is considerable inter-individual variability in the effectiveness and safety of pharmaceutical interventions. This phenomenon can be attributed to a multitude of factors; however, it is widely acknowledged that common genetic variation affecting drug absorption or metabolism play a substantial contributory role. This is a concept known as pharmacogenetics. Understanding how common genetic variants influence responses to medications, and using this knowledge to inform prescribing practice, could yield significant advantages for both patients and healthcare systems. Some health services around the world have introduced pharmacogenetics into routine practice, whereas others are less advanced along the implementation pathway. This chapter introduces the field of pharmacogenetics, the existing body of evidence, and discusses barriers to implementation. The chapter will specifically focus on efforts to introduce pharmacogenetics in the NHS, highlighting key challenges related to scale, informatics, and education.

Utility of screening for silent myocardial ischaemia in diabetes with an annual electrocardiogram.

BACKGROUND AND METHODS: Asymptomatic coronary artery disease (CAD) is common in people with diabetes mellitus, but there is a lack of consensus regarding appropriate screening for the condition. We performed a 12-lead electrocardiogram (ECG) on 312 consecutive participants with diabetes mellitus attending for routine annual outpatient review in order to determine the effectiveness of a yearly ECG in screening people with diabetes for asymptomatic CAD. RESULTS: Three of 312 participants (0.96%, 95% CI 0.2%-2.78%) had a newly identified ECG abnormality. One person had newly discovered atrial fibrillation. Two people had abnormalities which prompted further investigation for asymptomatic CAD. One of these participants underwent percutaneous coronary intervention. Seventeen further participants had abnormalities on ECG which had been previously documented, the majority having been present since their diagnosis of diabetes. CONCLUSION: A low positive yield of routine annual ECG in our study does not support its use as a screening tool for asymptomatic CAD in diabetes. Our findings support advice to perform an ECG at diagnosis of diabetes and to repeat only if a person develops relevant symptoms.

Thematic Daily Sleep Routine Analysis of Adults Not in Employment Living with Type 2 Diabetes Mellitus.

BACKGROUND: Day-to-day variations in sleep timing have been associated with poorer glycemic control in type 2 diabetes mellitus, although the factors that influence this sleep timing variability are poorly understood. METHODS: Daily routines of sleep in a sample of seventeen adults with type 2 diabetes mellitus who were either retired or not currently working were examined qualitatively through the application of semi-structured interviews and a thematic analysis of the resulting transcripts. RESULTS: Four themes were identified: "Consistent Sleeping Patterns", "Fluctuating Sleep Timing", "Night-Time Disruptions" and "Lasting Effort Needed with Type Two Diabetes Mellitus". The subthemes reflected that many participants had consistent sleep schedules across the seven-day week, but that a desire to maintain a sense of normality, household routines, television schedules and socializing were associated with different sleep timing on weekends. Active disease monitoring and timed medication taking were not identified as important factors in shaping sleep timing. Nocturia, stress and rumination were identified as important factors linked to disrupted sleep. Sleep was not reported as an issue discussed during routine clinical care. CONCLUSION: Sleep timing in participants appears to be driven by interacting psychosocial and physiological factors, although active disease management does not emerge as a major influence on sleep schedules.

Differences in Sleep Offset Timing between Weekdays and Weekends in 79,161 Adult Participants in the UK Biobank.

Variability in the timing of daily sleep is increasingly recognized as an important factor in sleep and general physical health. One potential driver of such daily variations in sleep timing is different work and social obligations during the "working week" and weekends. To investigate the nature of weekday/weekend differences in the timing of sleep offset, we examined actigraphy records of 79,161 adult participants in the UK Biobank who wore an actiwatch for 1 week. The time of sleep offset was found to be on average 36 min later on weekends than on weekdays, and when this difference was expressed as an absolute value (i.e., irrespective of sleep offset being either later or earlier on weekends), it was 63 min. Younger age, more socioeconomic disadvantage, currently being in employment, being a smoker, being male, being of non-white ethnicity and later chronotype were associated with greater differences in sleep offset between weekdays and weekend days. Greater differences in sleep offset timing were associated with age-independent small differences in cardiometabolic health indicators of BMI and diastolic blood pressure, but not HbA1c or systolic blood pressure. In a subset of participants with Type 2 Diabetes Mellitus, weekday/weekend sleep offset differences were associated weakly with BMI, systolic blood pressure and physical activity. Overall, this study demonstrates potentially substantive differences in sleep offset timings between weekdays and weekends in a large sample of UK adults, and that such differences may have public health implications.

Characterizing pharmacogenetic programs using the consolidated framework for implementation research: A structured scoping review.

Several healthcare organizations have developed pre-emptive pharmacogenetic testing programs, where testing is undertaken prior to the prescription of a medicine. This review characterizes the barriers and facilitators which influenced the development of these programs. A bidirectional citation searching strategy identified relevant publications before a standardized data extraction approach was applied. Publications were grouped by program and data synthesis was undertaken using the Consolidated Framework for Implementation Research (CFIR). 104 publications were identified from 40 programs and 4 multi-center initiatives. 26 (66%) of the programs were based in the United States and 95% in high-income countries. The programs were heterogeneous in their design and scale. The Characteristics of the Intervention, Inner Setting, and Process domains were referenced by 92.5, 80, and 77.5% of programs, respectively. A positive institutional culture, leadership engagement, engaging stakeholders, and the use of clinical champions were frequently described as facilitators to implementation. Clinician self-efficacy, lack of stakeholder knowledge, and the cost of the intervention were commonly cited barriers. Despite variation between the programs, there were several similarities in approach which could be categorized via the CFIR. These form a resource for organizations planning the development of pharmacogenetic programs, highlighting key facilitators which can be leveraged to promote successful implementation.

The role of CYP2C19 genotyping to guide antiplatelet therapy following ischemic stroke or transient ischemic attack.

INTRODUCTION: Clopidogrel is an antiplatelet agent recommended for secondary prevention of ischemic stroke (IS) and transient ischemic attack (TIA). Conversion of clopidogrel to its active metabolite by hepatic cytochrome P450-2C19 (CYP2C19) is essential for the inhibition of the P2Y12 receptor and subsequent platelet aggregation to prevent thrombotic events. CYP2C19 is highly polymorphic, with over 30 loss of function (LoF) alleles. This review considers whether there is sufficient data to support genotype guided antiplatelet therapy after stroke. AREAS COVERED: A systematic literature review retrieved articles, which describe the interaction between CYP2C19 genotype and clinical outcomes following IS or TIA when treated with clopidogrel. The review documents efforts to identify optimal antiplatelet regimens and explores the value genotype guided antiplatelet therapy. The work outlines the contemporary understanding of clopidogrel metabolism and appraises evidence linking CYP2C19 LoF variants with attenuated platelet inhibition and poorer outcomes. EXPERT OPINION: There is good evidence that CYP2C19 LoF allele carriers of Han-Chinese ancestry have increased risk for further vascular events following TIA or IS when treated with clopidogrel. The evidence base is less certain in other populations. The expansion of pharmacogenetics into routine clinical practice will facilitate further research and help tailor other aspects of secondary prevention.

Rapid Point-of-Care Genotyping to Avoid Aminoglycoside-Induced Ototoxicity in Neonatal Intensive Care.

Importance: Aminoglycosides are commonly prescribed antibiotics used for the treatment of neonatal sepsis. The MT-RNR1 m.1555A>G variant predisposes to profound aminoglycoside-induced ototoxicity (AIO). Current genotyping approaches take several days, which is unfeasible in acute settings. Objective: To develop a rapid point-of-care test (POCT) for the m.1555A>G variant before implementation of this technology in the acute neonatal setting to guide antibiotic prescribing and avoid AIO. Design, Setting, and Participants: This pragmatic prospective implementation trial recruited neonates admitted to 2 large neonatal intensive care units between January 6, 2020, and November 30, 2020, in the UK. Interventions: Neonates were tested for the m.1555A>G variant via the rapid POCT on admission to the neonatal intensive care unit. Main Outcomes and Measures: The primary outcome assessed the proportion of neonates successfully tested for the variant of all infants prescribed antibiotics. Secondary outcomes measured whether implementation was negatively associated with routine clinical practice and the performance of the system. The study was statistically powered to detect a significant difference between time to antibiotic administration before and after implementation of the MT-RNR1 POCT. Results: A total of 751 neonates were recruited and had a median (range) age of 2.5 (0-198) days. The MT-RNR1 POCT was able to genotype the m.1555A>G variant in 26 minutes. Preclinical validation demonstrated a 100% sensitivity (95% CI, 93.9%-100.0%) and specificity (95% CI, 98.5%-100.0%). Three participants with the m.1555A>G variant were identified, all of whom avoided aminoglycoside antibiotics. Overall, 424 infants (80.6%) receiving antibiotics were successfully tested for the variant, and the mean time to antibiotics was equivalent to previous practice. Conclusions and Relevance: The MT-RNR1 POCT was integrated without disrupting normal clinical practice, and genotype was used to guide antibiotic prescription and avoid AIO. This approach identified the m.1555A>G variant in a practice-changing time frame, and wide adoption could significantly reduce the burden of AIO.

Growth hormone replacement may influence the biological action of thyroid hormone on liver and bone tissue.

OBJECTIVE: Growth hormone (GH) replacement alters the peripheral interconversion of thyroxine (T4) and triiodothyronine (T3). However, little is known about the clinical impact of these alterations. We aimed to compare changes observed in the serum T3:T4 ratio with known biological markers of thyroid hormone action derived from different peripheral tissues. DESIGN: We prospectively studied twenty GH deficient men before and after GH replacement in a tertiary referral endocrine center. Serum biochemical measurements included insulin like growth factor-1 (IGF-1), thyroid hormones (free & total T3, free & total T4 and reverse T3) and TSH. Changes in thyroid hormone concentration were compared to alterations in hepatic and bone biomarkers of thyroid hormone action. RESULTS: GH replacement provoked a decline in serum free T4 concentration (-1.09 ± 1.99 pmol/L; p = 0.02) and an increase in free T3 (+0.34 ± 0.15 pmol/L; p = 0.03); therefore, the free T3:free T4 ratio increased from 0.40 ± 0.02 to 0.47 ± 0.02 (p = 0.002). Sex hormone binding globulin (SHBG) level was unchanged. However, a decline in serum ferritin (-26.6 ± 8.5 ng/mL; p = 0.005) correlated with a fall in freeT4. Alterations in lipid profile, including a rise in large HDL sub-fractions and Lp (a) (+2.1 ± 21.1 nmol/L; p = 0.002) did not correlate with thyroid hormone levels. Significant increases were recorded in serum bone turnover markers - procollagen type 1 amino-terminal propeptide +57.4%; p = 0.0009, osteocalcin +48.6%; p = 0.0007; c-terminal telopeptides of type 1 collagen +73.7%; p = 0.002. Changes in bone formation markers occurred in parallel with fluctuations in thyroid hormone. CONCLUSION: GH-induced alterations in the thyroid axis are associated with complex, tissue specific effects on thyroid hormone action. Modulation of bone turnover markers suggests that GH may improve the biological action of thyroid hormone on bone.

Genomic and healthcare dynamics of nosocomial SARS-CoV-2 transmission.

Understanding the effectiveness of infection control methods in reducing and preventing SARS-CoV-2 transmission in healthcare settings is of high importance. We sequenced SARS-CoV-2 genomes for patients and healthcare workers (HCWs) across multiple geographically distinct UK hospitals, obtaining 173 high-quality SARS-CoV-2 genomes. We integrated patient movement and staff location data into the analysis of viral genome data to understand spatial and temporal dynamics of SARS-CoV-2 transmission. We identified eight patient contact clusters (PCC) with significantly increased similarity in genomic variants compared to non-clustered samples. Incorporation of HCW location further increased the number of individuals within PCCs and identified additional links in SARS-CoV-2 transmission pathways. Patients within PCCs carried viruses more genetically identical to HCWs in the same ward location. SARS-CoV-2 genome sequencing integrated with patient and HCW movement data increases identification of outbreak clusters. This dynamic approach can support infection control management strategies within the healthcare setting.