The Future Role of Machine Learning in Clinical Transplantation.

The use of artificial intelligence and machine learning (ML) has revolutionized our daily lives and will soon be instrumental in healthcare delivery. The rise of ML is due to multiple factors: increasing access to massive datasets, exponential increases in processing power, and key algorithmic developments that allow ML models to tackle increasingly challenging questions. Progressively more transplantation research is exploring the potential utility of ML models throughout the patient journey, although this has not yet widely transitioned into the clinical domain. In this review, we explore common approaches used in ML in solid organ clinical transplantation and consider opportunities for ML to help clinicians and patients. We discuss ways in which ML can aid leverage of large complex datasets, generate cutting-edge prediction models, perform clinical image analysis, discover novel markers in molecular data, and fuse datasets to generate novel insights in modern transplantation practice. We focus on key areas in transplantation in which ML is driving progress, explore the future potential roles of ML, and discuss the challenges and limitations of these powerful tools.

Identifying cell-enriched miRNAs in kidney injury and repair.

Small noncoding RNAs, miRNAs (miRNAs), are emerging as important modulators in the pathogenesis of kidney disease, with potential as biomarkers of kidney disease onset, progression, or therapeutic efficacy. Bulk tissue small RNA-sequencing (sRNA-Seq) and microarrays are widely used to identify dysregulated miRNA expression but are limited by the lack of precision regarding the cellular origin of the miRNA. In this study, we performed cell-specific sRNA-Seq on tubular cells, endothelial cells, PDGFR-ß+ cells, and macrophages isolated from injured and repairing kidneys in the murine reversible unilateral ureteric obstruction model. We devised an unbiased bioinformatics pipeline to define the miRNA enrichment within these cell populations, constructing a miRNA catalog of injury and repair. Our analysis revealed that a significant proportion of cell-specific miRNAs in healthy animals were no longer specific following injury. We then applied this knowledge of the relative cell specificity of miRNAs to deconvolute bulk miRNA expression profiles in the renal cortex in murine models and human kidney disease. Finally, we used our data-driven approach to rationally select macrophage-enriched miR-16-5p and miR-18a-5p and demonstrate that they are promising urinary biomarkers of acute kidney injury in renal transplant recipients.

Novel Plaque Enriched Long Noncoding RNA in Atherosclerotic Macrophage Regulation (PELATON).

OBJECTIVE: Long noncoding RNAs (lncRNAs) are an emergent class of molecules with diverse functional roles, widely expressed in human physiology and disease. Although some lncRNAs have been identified in cardiovascular disease, their potential as novel targets in the prevention of atherosclerosis is unknown. We set out to discover important lncRNAs in unstable plaque and gain insight into their functional relevance. Approach and Results: Analysis of RNA sequencing previously performed on stable and unstable atherosclerotic plaque identified a panel of 47 differentially regulated lncRNAs. We focused on LINC01272, a lncRNA upregulated in unstable plaque previously detected in inflammatory bowel disease, which we termed PELATON (plaque enriched lncRNA in atherosclerotic and inflammatory bowel macrophage regulation). Here, we demonstrate that PELATON is highly monocyte- and macrophage-specific across vascular cell types, and almost entirely nuclear by cellular fractionation (90%-98%). In situ hybridization confirmed enrichment of PELATON in areas of plaque inflammation, colocalizing with macrophages around the shoulders and necrotic core of human plaque sections. Consistent with its nuclear localization, and despite containing a predicted open reading frame, PELATON did not demonstrate any protein-coding potential in vitro. Functionally, knockdown of PELATON significantly reduced phagocytosis, lipid uptake and reactive oxygen species production in high-content analysis, with a significant reduction in phagocytosis independently validated. Furthermore, CD36, a key mediator of phagocytic oxLDL (oxidized low-density lipoprotein) uptake was significantly reduced with PELATON knockdown. CONCLUSIONS: PELATON is a nuclear expressed, monocyte- and macrophage-specific lncRNA, upregulated in unstable atherosclerotic plaque. Knockdown of PELATON affects cellular functions associated with plaque progression.

Urinary angiotensinogen as a biomarker for acute to chronic kidney injury transition - prognostic and mechanistic implications.

Accurate biomarkers that both predict the progression to, and detect the early stages of chronic kidney disease (CKD) are lacking, resulting in difficulty in identifying individuals who could potentially benefit from targeted intervention. In a recent issue [Clinical Science (2018) 132, 2121-2133], Cui et al. examine the ability of urinary angiotensinogen (uAGT) to predict the progression of acute kidney injury (AKI) to CKD. They principally employ a murine ischaemia reperfusion injury model to study this and provide data from a small prospective study of patients with biopsy proven acute tubular necrosis. The authors suggest that uAGT is a dynamic marker of renal injury that could be used to predict the likelihood of structural recovery following AKI. Here we comment on their findings, exploring the clinical utility of uAGT as a biomarker to predict AKI to CKD transition and perhaps more controversially, to discuss whether the early renin-angiotensin system blockade following AKI represents a therapeutic target.

Erratum to: Smartphone apps for orthopaedic sports medicine ­ a smart move?

[This corrects the article DOI: 10.1186/s13102-015-0017-6.].

Smartphone apps for orthopaedic sports medicine - a smart move?

BACKGROUND: With the advent of smartphones together with their downloadable applications (apps), there is increasing opportunities for doctors, including orthopaedic sports surgeons, to integrate such technology into clinical practice. However, the clinical reliability of these medical apps remains questionable. We reviewed available apps themed specifically towards Orthopaedic Sports Medicine and related conditions and assessed the level of medical professional involvement in their design and content, along with a review of these apps. METHOD: The most popular smartphone app stores (Android, Apple, Blackberry, Windows, Samsung, Nokia) were searched for Orthopaedic Sports medicine themed apps, using the search terms; Orthopaedic Sports Medicine, Orthopaedics, Sports medicine, Knee Injury, Shoulder Injury, Anterior Cruciate Ligament Tear, Medial Collateral Ligament Tear, Rotator Cuff Tear, Meniscal Tear, Tennis Elbow. All English language apps related to orthopaedic sports medicine were included. RESULTS: A total of 76 individual Orthopaedic Sports Medicine themed apps were identified. According to app store classifications, there were 45 (59 %) medical themed apps, 28 (37 %) health and fitness themed apps, 1 (1 %) business app, 1 (1 %) reference app and 1 (1 %) sports app. Forty-nine (64 %) apps were available for download free of charge. For those that charged access, the prices ranged from £0.69 to £69.99. Only 51 % of sports medicine apps had customer satisfaction ratings and 39 % had named medical professional involvement in their development or content. CONCLUSIONS: We found the majority of Orthopaedic Sports Medicine apps had no named medical professional involvement, raising concerns over their content and evidence-base. We recommend increased regulation of such apps to improve the accountability of app content.

Treatment, comorbidity and survival in stage III laryngeal cancer.

BACKGROUND: The purpose of this study was for us to identify factors associated with survival and laryngeal function in a contemporary, population-based study of stage III laryngeal carcinoma. METHODS: Patients presenting to a tertiary center with stage III laryngeal carcinoma between 1999 and 2010 were included in the study. Kaplan-Meier and Cox proportional hazards analyses were utilized. RESULTS: Of 137 patients receiving either surgery ± adjuvant therapy (SURG±Adj = 24.1%), chemoradiotherapy (CRT = 32.8%), or radiotherapy alone (RT = 36.5%), 5-year cause-specific survival (5-year CSS) was 81.0% and 2-year local relapse rate was 27.5%. RT had higher recurrence (p < .01), lower 5-year CSS (90.8% vs 87.8% vs 68.9%/SURG±Adj vs CRT vs RT/p = .0026) and lower overall survival (p = .001). Adjusting for excess of severe comorbidity in the RT group, there was no difference in 5-year CSS between treatment modality. CONCLUSION: SURG±Adj and CRT had similar survival. Severe comorbidity was associated with selection bias to RT and reduced 5-year CSS. Comorbidity is a key prognostic variable and should be considered in the interpretation of treatment outcomes.