Development of a lupus nephritis suboptimal response prediction tool using renal histopathological and clinical laboratory variables at the time of diagnosis.

OBJECTIVE: Lupus nephritis (LN) is an immune complex-mediated glomerular and tubulointerstitial disease in patients with SLE. Prediction of outcomes at the onset of LN diagnosis can guide decisions regarding intensity of monitoring and therapy for treatment success. Currently, no machine learning model of outcomes exists. Several outcomes modelling works have used univariate or linear modelling but were limited by the disease heterogeneity. We hypothesised that a combination of renal pathology results and routine clinical laboratory data could be used to develop and to cross-validate a clinically meaningful machine learning early decision support tool that predicts LN outcomes at approximately 1 year. METHODS: To address this hypothesis, patients with LN from a prospective longitudinal registry at the Medical University of South Carolina enrolled between 2003 and 2017 were identified if they had renal biopsies with International Society of Nephrology/Renal Pathology Society pathological classification. Clinical laboratory values at the time of diagnosis and outcome variables at approximately 1 year were recorded. Machine learning models were developed and cross-validated to predict suboptimal response. RESULTS: Five machine learning models predicted suboptimal response status in 10 times cross-validation with receiver operating characteristics area under the curve values >0.78. The most predictive variables were interstitial inflammation, interstitial fibrosis, activity score and chronicity score from renal pathology and urine protein-to-creatinine ratio, white blood cell count and haemoglobin from the clinical laboratories. A web-based tool was created for clinicians to enter these baseline clinical laboratory and histopathology variables to produce a probability score of suboptimal response. CONCLUSION: Given the heterogeneity of disease presentation in LN, it is important that risk prediction models incorporate several data elements. This report provides for the first time a clinical proof-of-concept tool that uses the five most predictive models and simplifies understanding of them through a web-based application.

Quantitative Gross and CT measurements of Cadaveric Cervical Vertebrae (C3 - C6) as Guidelines for the Lateral mass screw fixation.

BACKGROUND: Lateral mass screw fixation is the treatment of choice for posterior cervical stabilization. Long or misdirected screws carry a risk of injury to spinal nerve roots or vertebral artery. This study was aimed to assess the gross anatomic and CT measurements of typical cervical vertebrae for the selection of lateral mass screws. METHODS: Dimensions of the articular pillars were measured on 1) Dry cervical vertebrae with Vernier calipers and 2) Multiplanar reformations of CT scans of the same vertebrae with Viewer software package. The data was statistically evaluated. RESULTS: The transverse diameter of the articular pillars with Vernier calipers varied from 6.0 to 15.4 mm (mean=10.5 mm ± 1.5) and on CT scans ranged from 8.2 - 16.1 mm (mean=11.6 mm ± 1.4). The antero-posterior diameter, an estimate of the screw length by Roy-Camille technique varied from 3.9 to 12.7 mm (mean=8.6 mm ± 1.6) by Vernier calipers and from 6.4 to 13.3 mm (mean=9.1 ± 1.2) on CT scans. The oblique AP diameter, an estimate of screw length by Magerl method varied from 10.8 to 20.3 mm (mean=14.9 mm ± 1.8) by Vernier calipers and from 11.4 to 19.3 mm (mean=14.5 mm ± 1.7) on CT. The CT measurements for height, transverse and AP diameter of the articular pillars were 0.5 - 1.0 mm larger than dimensions by Vernier calipers. No statistically significant difference was observed between the caliper and CT measurements for the oblique AP diameter. CONCLUSION: CT measurements of the articular pillars may slightly overestimate the desired screw length selected by spine surgeons when compared to actual anatomy. Although means of the articular pillars correspond to the screw lengths used, substantial number of observations below 10 mm for Roy-Camille trajectory and below 14 mm for Magerl trajectory requires careful preoperative planning and intra-operative confirmation to avoid long/misdirected lateral mass screws.