Exploration of Machine Learning Techniques to Examine the Journey to Neuroendocrine Tumor Diagnosis with Real-World Data

Abstract

Aim: Machine learning reveals pathways to neuroendocrine tumor (NET) diagnosis. Patients & methods: Patients with NET and age-/gender-matched non-NET controls were retrospectively selected from MarketScan claims. Predictors (e.g., procedures, symptoms, conditions for which NET is misdiagnosed) were examined during a 5-year pre-period to understand presence of and time to NET diagnosis using conditional inference trees. Results: Among 3460 patients with NET, 70% had a prior misdiagnosis. 10,370 controls were included. Decision trees revealed combinations of factors associated with a high probability of being a patient with NET (e.g., abdominal pain, an endoscopic/biopsy procedure, vomiting) or longer times to diagnosis (e.g., asthma diagnosis with visits to >6 providers). Conclusion: Decision trees provided a unique examination of the journey to NET diagnosis.

Identifying patients with undiagnosed small intestinal neuroendocrine tumours in primary care using statistical and machine learning: model development and validation study

“…First, there was no accounting for the over-representation of NET cases in the case-control sample, which means that the probabilistic estimates will be poorly calibrated. Second, that study only performed an apparent 'validation', and did not assess clinical utility or other key metrics [24]. Therefore, the present study is the first to develop a prediction tool to provide clinical decision support to target identification of SI-NETs in primary care.…”

“…Most clinical prediction modelling studies in NETs have focussed on predicting outcomes after diagnosis. However, one recent study used decision tree methodology on claims data to better understand clinical pathways to NET diagnosis, and also predict risks that a patient may have a NET [24]. However, that report has significant limitations in terms of its possible deployment in the target setting for the present study.…”