Refining outcome prediction after traumatic brain injury with machine learning algorithms

Outcome after traumatic brain injury (TBI) is typically assessed using the Glasgow outcome scale extended (GOSE) with levels from 1 (death) to 8 (upper good recovery). Outcome prediction has classically been dichotomized into either dead/alive or favorable/unfavorable outcome. Binary outcome prediction models limit the possibility of detecting subtle yet significant improvements. We set out to explore different machine learning methods with the purpose of mapping their predictions to the full 8 grade scale GOSE following TBI. The models were set up using the variables: age, GCS-motor score, pupillary reaction, and Marshall CT score. For model setup and internal validation, a total of 866 patients could be included. For external validation, a cohort of 369 patients were included from Leuven, Belgium, and a cohort of 573 patients from the US multi-center ProTECT III study. Our findings indicate that proportional odds logistic regression (POLR), random forest regression, and a neural network model achieved accuracy values of 0.3-0.35 when applied to internal data, compared to the random baseline which is 0.125 for eight categories. The models demonstrated satisfactory performance during external validation in the data from Leuven, however, their performance were not satisfactory when applied to the ProTECT III dataset.

Prognostic impact of HER2 biomarker levels in trastuzumab-treated early HER2-positive breast cancer

BACKGROUND

Overexpression of human epidermal growth factor receptor 2 (HER2) caused by HER2 gene amplification is a driver in breast cancer tumorigenesis. We aimed to investigate the prognostic significance of manual scoring and digital image analysis (DIA) algorithm assessment of HER2 copy numbers and HER2/CEP17 ratios, along with ERBB2 mRNA levels among early-stage HER2-positive breast cancer patients treated with trastuzumab.

METHODS

This retrospective study comprised 371 early HER2-positive breast cancer patients treated with adjuvant trastuzumab, with HER2 re-testing performed on whole tumor sections. Digitized tumor tissue slides were manually scored and assessed with uPath HER2 Dual ISH image analysis, breast algorithm. Targeted ERBB2 mRNA levels were assessed by the Xpert® Breast Cancer STRAT4 Assay. HER2 copy number and HER2/CEP17 ratio from in situ hybridization assessment, along with ERBB2 mRNA levels, were explored in relation to recurrence-free survival (RFS).

RESULTS

The analysis showed that patients with tumors with the highest and lowest manually counted HER2 copy number levels had worse RFS than those with intermediate levels (HR = 2.7, CI 1.4-5.3, p = 0.003 and HR = 2.1, CI 1.1-3.9, p = 0.03, respectively). A similar trend was observed for HER2/CEP17 ratio, and the DIA algorithm confirmed the results. Moreover, patients with tumors with the highest and the lowest values of ERBB2 mRNA had a significantly worse prognosis (HR = 2.7, CI 1.4-5.1, p = 0.003 and HR = 2.8, CI 1.4-5.5, p = 0.004, respectively) compared to those with intermediate levels.

CONCLUSIONS

Our findings suggest that the association between any of the three HER2 biomarkers and RFS was nonlinear. Patients with tumors with the highest levels of HER2 gene amplification or ERBB2 mRNA were associated with a worse prognosis than those with intermediate levels, which is of importance to investigate in future clinical trials studying HER2-targeted therapy.

A novel noble metal stent coating reduces in vitro platelet activation and acute in vivo thrombosis formation: a blinded study

Inherent to any stenting procedure is the prescription of dual antiplatelet therapy (DAPT) to reduce the platelet response. Clinical guidelines recommend 6-12 months of DAPT, depending on stent type, clinical picture and patient factors. Our hypothesis is that a nanostructured noble metal coating has the potential to reduce protein deposition and platelet activation. These effects would reduce subsequent thrombo-inflammatory reactions, potentially mitigating the need for an extensive DAPT in the acute phase. Here, a noble metal nanostructure coating on stents is investigated. Twelve pigs underwent endovascular implantation of coated and non-coated stents for paired comparisons in a blinded study design. The non-coated control stent was placed at the contralateral corresponding artery. Volumetric analysis of angiographic data, performed by a treatment blinded assessor, demonstrated a significant thrombus reduction for one of the coatings compared to control. This effect was already seen one hour after implantation. This finding was supported by in vitro data showing a significant reduction of coagulation activation in the coated group. This novel coating shows promise as an implant material addition and could potentially decrease the need for DAPT in the early phases of stent implementation.

Cholinergic regulation of vascular endothelial function by human ChAT+ T cells

Endothelial dysfunction and impaired vasodilation are linked with adverse cardiovascular events. T lymphocytes expressing choline acetyltransferase (ChAT), the enzyme catalyzing biosynthesis of the vasorelaxant acetylcholine (ACh), regulate vasodilation and are integral to the cholinergic antiinflammatory pathway in an inflammatory reflex in mice. Here, we found that human T cell ChAT mRNA expression was induced by T cell activation involving the PI3K signaling cascade. Mechanistically, we identified that ChAT mRNA expression was induced following the attenuation of RE-1 Silencing Transcription factor REST-mediated methylation of the ChAT promoter, and that ChAT mRNA expression levels were up-regulated by GATA3 in human T cells. In functional experiments, T cell-derived ACh increased endothelial nitric oxide-synthase activity, promoted vasorelaxation, and reduced vascular endothelial activation and promoted barrier integrity by a cholinergic mechanism. Further, we observed that survival in a cohort of patients with severe circulatory failure correlated with their relative frequency of ChAT ⁺CD4⁺ T cells in blood. These findings on ChAT⁺ human T cells provide a mechanism for cholinergic immune regulation of vascular endothelial function in human inflammation.

Optimisation of the Synthesis and Cell Labelling Conditions for [89Zr]Zr-oxine and [89Zr]Zr-DFO-NCS: a Direct In Vitro Comparison in Cell Types with Distinct Therapeutic Applications

BACKGROUND

There is a need to better characterise cell-based therapies in preclinical models to help facilitate their translation to humans. Long-term high-resolution tracking of the cells in vivo is often impossible due to unreliable methods. Radiolabelling of cells has the advantage of being able to reveal cellular kinetics in vivo over time. This study aimed to optimise the synthesis of the radiotracers [89Zr]Zr-oxine (8-hydroxyquinoline) and [89Zr]Zr-DFO-NCS (p-SCN-Bn-Deferoxamine) and to perform a direct comparison of the cell labelling efficiency using these radiotracers.

PROCEDURES

Several parameters, such as buffers, pH, labelling time and temperature, were investigated to optimise the synthesis of [89Zr]Zr-oxine and [89Zr]Zr-DFO-NCS in order to reach a radiochemical conversion (RCC) of >95 % without purification. Radio-instant thin-layer chromatography (iTLC) and radio high-performance liquid chromatography (radio-HPLC) were used to determine the RCC. Cells were labelled with [89Zr]Zr-oxine or [89Zr]Zr-DFO-NCS. The cellular retention of 89Zr and the labelling impact was determined by analysing the cellular functions, such as viability, proliferation, phagocytotic ability and phenotypic immunostaining.

RESULTS

The optimised synthesis of [89Zr]Zr-oxine and [89Zr]Zr-DFO-NCS resulted in straightforward protocols not requiring additional purification. [89Zr]Zr-oxine and [89Zr]Zr-DFO-NCS were synthesised with an average RCC of 98.4 % (n = 16) and 98.0 % (n = 13), respectively. Cell labelling efficiencies were 63.9 % (n = 35) and 70.2 % (n = 30), respectively. 89Zr labelling neither significantly affected the cell viability (cell viability loss was in the range of 1-8 % compared to its corresponding non-labelled cells, P value > 0.05) nor the cells' proliferation rate. The phenotype of human decidual stromal cells (hDSC) and phagocytic function of rat bone-marrow-derived macrophages (rMac) was somewhat affected by radiolabelling.

CONCLUSIONS

Our study demonstrates that [89Zr]Zr-oxine and [89Zr]Zr-DFO-NCS are equally effective in cell labelling. However, [89Zr]Zr-oxine was superior to [89Zr]Zr-DFO-NCS with regard to long-term stability, cellular retention, minimal variation between cell types and cell labelling efficiency.

Prognostic potential of automated Ki67 evaluation in breast cancer: different hot spot definitions versus true global score

PURPOSE

The proliferation-associated biomarker Ki67 has potential utility in breast cancer, including aiding decisions based on prognosis, but has unacceptable inter- and intralaboratory variability. The aim of this study was to compare the prognostic potential for Ki67 hot spot scoring and global scoring using different digital image analysis (DIA) platforms.

METHODS

An ER+/HER2- breast cancer cohort (n = 139) with whole slide images of sequential sections stained for hematoxylin-eosin, pancytokeratin and Ki67, was analyzed using two DIA platforms. For hot spot analysis virtual dual staining was applied, aligning pancytokeratin and Ki67 images and 22 hot spot algorithms with different features were designed. For global Ki67 scoring an automated QuPath algorithm was applied on Ki67-stained whole slide images. Clinicopathological data included overall survival (OS) and recurrence-free survival (RFS) along with PAM50 molecular subtypes.

RESULTS

We show significant variations in Ki67 hot spot scoring depending on number of included tumor cells, hot spot size, shape and location. The higher the number of scored tumor cells, the higher the reproducibility of Ki67 proliferation values. Hot spot scoring had greater prognostic potential for RFS in high versus low Ki67 subgroups (hazard ratio (HR) 6.88, CI 2.07-22.87, p = 0.002), compared to global scoring (HR 3.13, CI 1.41-6.96, p = 0.005). Regarding OS, global scoring (HR 7.46, CI 2.46-22.58, p < 0.001) was slightly better than hot spot scoring (HR 6.93, CI 1.61-29.91, p = 0.009). In adjusted multivariate analysis, only global scoring was an independent prognostic marker for both RFS and OS. In addition, global Ki67-based surrogate subtypes reached higher concordance with PAM50 molecular subtype for luminal A and B tumors (66.3% concordance rate, κ = 0.345), than using hot spot scoring (55.8% concordance rate, κ = 0.250).

CONCLUSIONS

We conclude that the automated global Ki67 scoring is feasible and shows clinical validity, which, however, needs to be confirmed in a larger cohort before clinical implementation.