Multimodal survival prediction in advanced pancreatic cancer using machine learning

Background

Existing risk scores appear insufficient to assess the individual survival risk of patients with advanced pancreatic ductal adenocarcinoma (PDAC) and do not take advantage of the variety of parameters that are collected during clinical care.

Methods

In this retrospective study, we built a random survival forest model from clinical data of 203 patients with advanced PDAC. The parameters were assessed before initiation of systemic treatment and included age, CA19-9, C-reactive protein, metastatic status, neutrophil-to-lymphocyte ratio and total serum protein level. Separate models including imaging and molecular parameters were built for subgroups.

Results

Over the entire cohort, a model based on clinical parameters achieved a c-index of 0.71. Our approach outperformed the American Joint Committee on Cancer (AJCC) staging system and the modified Glasgow Prognostic Score (mGPS) in the identification of high- and low-risk subgroups. Inclusion of the KRAS p.G12D mutational status could further improve the prediction, whereas radiomics data of the primary tumor only showed little benefit. In an external validation cohort of PDAC patients with liver metastases, our model achieved a c-index of 0.67 (mGPS: 0.59).

Conclusions

The combination of multimodal data and machine-learning algorithms holds potential for personalized prognostication in advanced PDAC already at diagnosis.

•

We developed a machine-learning-based prediction model that outperforms the AJCC staging system and mGPS.

•

Applying our model to an external validation cohort demonstrates generalizability.

•

Explainable machine learning enables to understand the decision making of our model and identifies relevant parameters.

•

Combining clinical, imaging and genetic data holds potential for personalized prognostication in advanced PDAC.

ATP dependence of anion uptake by isolated vacuoles: requirement for excess Mg2+

Vacuoles were isolated from barley mesophyll protoplasts. [14C]Malate or 36Cl- were taken up from the surrounding medium. Uptake was only slightly increased in the presence of equimolar levels of ATP and Mg2+ (as magnesium gluconate). In the presence of excess Mg2+ in the medium, ATP-stimulated uptake of malate and chloride increased several-fold. Stimulation by excess Mg2+ was not observed for ATP-stimulated amino acid uptake by isolated vacuoles. Stimulation of uptake by excess Mg2+ was observed at all malate concentrations upto 10 mmol.l-1. The content of Mg2+ needed for half-maximum stimulation was about 3.5 mmol.l-1 in the presence of 1 mmol.l-1 ATP. The increase in Mg2+ concentration had no effect on the tonoplast ATPase activity.

The effect of orally administered cyproterone on the serum production in human subjects

Using the Strauss and Pochi technique it has been confirmed that in human subjects the sebum production is dependent to a great extent on the concentration of androgens available to the tissues. Treatment of normal males with the antiandrogen Cyproterone produced only a transient decrease of sebum production at about the 10th day; Cyproterone induced an increase in testosterone production. As a result of this, Cyproterone was also apparently without effect in hirsute females. In a castrate male, Cyproterone completely inhibited the effect of intramuscularly injected testosterone on the sebaceous glands.