%0 Journal Article %1 bf2aaacc735e4125b1bc29f3d3b8890b %A Schouten, Rianne M. %A Bueno, Marcos L.P. %A Duivesteijn, Wouter %A Pechenizkiy, Mykola %D 2022 %I Springer Open %J Data Mining and Knowledge Discovery %K Exceptional Information-theoretic Markov Mining Model Sequential chains data functions medical scoring %N 1 %P 379--413 %R 10.1007/s10618-021-00808-x %T Mining sequences with exceptional transition behaviour of varying order using quality measures based on information-theoretic scoring functions %V 36 %X Discrete Markov chains are frequently used to analyse transition behaviour in sequential data. Here, the transition probabilities can be estimated using varying order Markov chains, where order k specifies the length of the sequence history that is used to model these probabilities. Generally, such a model is fitted to the entire dataset, but in practice it is likely that some heterogeneity in the data exists and that some sequences would be better modelled with alternative parameter values, or with a Markov chain of a different order. We use the framework of Exceptional Model Mining (EMM) to discover these exceptionally behaving sequences. In particular, we propose an EMM model class that allows for discovering subgroups with transition behaviour of varying order. To that end, we propose three new quality measures based on information-theoretic scoring functions. Our findings from controlled experiments show that all three quality measures find exceptional transition behaviour of varying order and are reasonably sensitive. The quality measure based on Akaike’s Information Criterion is most robust for the number of observations. We furthermore add to existing work by seeking for subgroups of sequences, as opposite to subgroups of transitions. Since we use sequence-level descriptive attributes, we form subgroups of entire sequences, which is practically relevant in situations where you want to identify the originators of exceptional sequences, such as patients. We show this relevance by analysing sequences of blood glucose values of adult persons with diabetes type 2. In the experiments, we find subgroups of patients based on age and glycated haemoglobin (HbA1c), a measure known to correlate with average blood glucose values. Clinicians and domain experts confirmed the transition behaviour as estimated by the fitted Markov chain models.

@article{bf2aaacc735e4125b1bc29f3d3b8890b, abstract = {Discrete Markov chains are frequently used to analyse transition behaviour in sequential data. Here, the transition probabilities can be estimated using varying order Markov chains, where order k specifies the length of the sequence history that is used to model these probabilities. Generally, such a model is fitted to the entire dataset, but in practice it is likely that some heterogeneity in the data exists and that some sequences would be better modelled with alternative parameter values, or with a Markov chain of a different order. We use the framework of Exceptional Model Mining (EMM) to discover these exceptionally behaving sequences. In particular, we propose an EMM model class that allows for discovering subgroups with transition behaviour of varying order. To that end, we propose three new quality measures based on information-theoretic scoring functions. Our findings from controlled experiments show that all three quality measures find exceptional transition behaviour of varying order and are reasonably sensitive. The quality measure based on Akaike{\textquoteright}s Information Criterion is most robust for the number of observations. We furthermore add to existing work by seeking for subgroups of sequences, as opposite to subgroups of transitions. Since we use sequence-level descriptive attributes, we form subgroups of entire sequences, which is practically relevant in situations where you want to identify the originators of exceptional sequences, such as patients. We show this relevance by analysing sequences of blood glucose values of adult persons with diabetes type 2. In the experiments, we find subgroups of patients based on age and glycated haemoglobin (HbA1c), a measure known to correlate with average blood glucose values. Clinicians and domain experts confirmed the transition behaviour as estimated by the fitted Markov chain models.}, added-at = {2023-02-17T15:58:20.000+0100}, author = {Schouten, {Rianne M.} and Bueno, {Marcos L.P.} and Duivesteijn, Wouter and Pechenizkiy, Mykola}, biburl = {https://www.bibsonomy.org/bibtex/2e9cd890da04744c99b08b3233d2c1b7a/tobias.koopmann}, doi = {10.1007/s10618-021-00808-x}, interhash = {5a8c2be57e08753f593713d161f86c37}, intrahash = {e9cd890da04744c99b08b3233d2c1b7a}, issn = {1384-5810}, journal = {Data Mining and Knowledge Discovery}, keywords = {Exceptional Information-theoretic Markov Mining Model Sequential chains data functions medical scoring}, language = {English}, month = jan, note = {Funding Information: This research is supported by EDIC project funded by NWO. We thank the EDIC consortium and the ZGT hospital for allowing us to analyse the data from the DIALECT-2 study. We especially thank Niala Den Braber (PhD candidate at Universiteit Twente and researcher internal medicine at ZGT hospital) and prof. dr. Goos Laverman (internist-nephrologist at ZGT hospital) for giving us clinical valuation of our findings. In addition, we thank our colleagues dr. Robert Peharz for giving us useful insights on Markov chains and DBNs and dr. Maryam Tavakol for guiding us towards the MovieLens dataset. }, number = 1, pages = {379--413}, publisher = {Springer Open}, timestamp = {2023-02-17T15:58:20.000+0100}, title = {Mining sequences with exceptional transition behaviour of varying order using quality measures based on information-theoretic scoring functions}, volume = 36, year = 2022 }