Life sciences · Preprint

Leveraging contextual events on structure-aware next activity prediction

arXiv · September 8, 2026

Insufficient Information Why this matters to you Expert discussion

The material analysed did not support any firm read.

AI Summary

This is a preprint computer science paper describing a machine learning method (Instance Graphs with Graph Neural Networks) for predicting the next activity in business process workflows. It has no clinical relevance, population, or health outcome and does not constitute medical evidence.

What was studied

Preprint.

Key findings

Incorporating contextual process instances improved prediction performance on real-world event logs

Safety

Safety was not reported in the material analysed. Check the source before drawing any conclusion about harm.

Who this may help

The source did not state who this applies to in practice.

Plain-language summary

This is a computer science methods paper on process prediction algorithms with no clinical application, population, or health outcome; it does not address medical evidence and is outside the scope of clinical intelligence.

Caveats

This is a preprint and has not been peer reviewed.
This is a computer science methods paper with no clinical application, human subjects, or health outcome.
No quantitative results (accuracy, precision, recall, or other metrics) are reported in the abstract.
The source does not describe which real-world event logs were used or their characteristics.

Evidence assessment

Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.

Study design

insufficient

Computer science methods paper; no human subjects or clinical trial design.

Directness

insufficient

No clinical or health-related outcome; addresses process prediction algorithms only.

Consistency

insufficient

Single paper; no comparison to prior clinical evidence base.

Risk of bias

insufficient

Not applicable to algorithm development work without clinical endpoints.

Sample adequacy

insufficient

No human sample; uses event logs from unspecified real-world datasets.

What is missing. This record has no reported figures. That is a gap in the analysis, not a judgement about the study.

Source abstract

Predictive process monitoring aims at forecasting various aspects of running processes. Among the different tasks, next activity prediction represents the most extensively investigated. However, only a limited number of existing approaches explicitly encode contextual information, i.e., the environmental conditions in which the process is executed, typically modeled through event log attributes or aggregated measures. In this paper, an approach based on the concept of Instance Graphs is introduced. To incorporate contextual process instances, several encoding strategies are proposed and evaluated by measuring their impact on prediction performance. For each encoding strategy, a set of prefix-Instance Graphs is generated and subsequently provided as input to a Graph Neural Network for the classification task. The proposed approach is evaluated on multiple real-world event logs, and the experimental results demonstrate that incorporating contextual process instances benefits prediction performance.

Follow from this

Taken from the source record, never inferred. Follow any of these and new work involving them reaches your briefing.

Alessandro MeleClaudia DiamantiniDomenico Potena