Assigning diagnosis codes using medication history

Hansen, Emil Riis; Sagi, Tomer; Hose, Katja; Lip, Gregory Y.H.; Larsen, Torben Bjerregaard; Skjøth, Flemming

doi:10.1016/j.artmed.2022.102307

Cited by 10 publications

(19 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A distinctive aspect of medication data as input for building a CAC system is that medication could be expected to convey little to no information about some diagnoses, such as, for example, diagnosis codes belonging to the 3-digits node V50-V59 Persons Encountering Health Services For Specific Procedures And Aftercare . This has led some authors to design algorithms only on cherry-picked subsets of codes filtered both by code frequency and researchers’ prior beliefs about the information content of input data regarding ICD codes [20] (see Section II-A4). Such filtering can be justified assuming that 1) the input data conveys no information about some diagnostics and/or 2) that data is too scarce to allow any learning and/or 3) that the inclusion of such codes in the model deteriorates predictions for the selected cherry-picked codes.…”

Section: Resultsmentioning

confidence: 99%

“…The resulting number of unique codes and number of codes per ICU stay for the cherry-picked code set are respectively shown in Table I and Table S2. Note that despite our efforts to replicate their code filtering we ended up retaining significantly more codes than reported in Hansen et al [20].…”

Section: Methodsmentioning

confidence: 99%

“…Our findings suggest that NNs benefit from learning from the whole hierarchy; however, neither HMC nor class imbalance correction methods improved results upon the simple multitask learning NNs. Finally, our study serves as a valuable replication of predicting ICD-9 codes based on medication information [20] using the MIMIC-III dataset [3], achieving superior classification and ranking results, as well as promoting broader applicability through the use of the OMOP-CDM data-standard.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Creating a computer assisted ICD coding system: performance metric choice and use of the ICD hierarchy

Marcou,

Berti-Equille,

Novelli

2024

Preprint

View full text Add to dashboard Cite

Objective: Machine learning methods hold the promise of leveraging available data and generating higher quality data while alleviating the data collection burden on healthcare professionals. International Classification of Diseases (ICD) diagnoses data, collected globally for billing and epidemiological purposes, represents a valuable source of structured information. However, ICD coding is a challenging task. While numerous previous studies reported promising results in automatic ICD classification, they often describe input data specific model architectures, that are heterogeneously evaluated with different performance metrics and ICD code subsets. This study aims to explore the evaluation and construction of more effective Computer Assisted Coding (CAC) systems using generic approaches, focusing on the use of ICD hierarchy, medication data and a feed forward neural network architecture. Methods: We conduct comprehensive experiments using the MIMIC-III clinical database, mapped to the OMOP data model. Our evaluations encompass various performance metrics, alongside investigations into multitask, hierarchical, and imbalanced learning for neural networks. Results: We introduce a novel metric, RE@R, tailored to the ICD coding task, which offers interpretable insights for healthcare informatics practitioners, aiding them in assessing the quality of assisted coding systems. Our findings highlight that selectively cherry-picking ICD codes diminish retrieval performance without performance improvement over the selected subset. We show that optimizing for metrics such as NDCG and AUPRC outperforms traditional F1-based metrics in ranking performance. We observe that Neural Network training on different ICD levels simultaneously offers minor benefits for ranking and significant runtime gains. However, our models do not derive benefits from hierarchical or class imbalance correction techniques for ICD code retrieval. Conclusion: This study offers valuable insights for researchers and healthcare practitioners interested in developing and evaluating CAC systems. Using a straightforward sequential neural network model, we confirm that medical prescriptions are a rich data source for CAC systems, providing competitive retrieval capabilities for a fraction of the computational load compared to text-based models. Our study underscores the importance of metric selection and challenges existing practices related to ICD code sub-setting for model training and evaluation.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Creating a computer assisted ICD coding system: performance metric choice and use of the ICD hierarchy

Marcou,

Berti-Equille,

Novelli

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Other medical procedures are therapeutic and intend to treat or cure the patient. To standardize how medical procedures are described, medical facilities code procedure concepts using accepted medical taxonomies often used in ML applications [8], such as the Anatomical Therapeutic Classification (ATC) [17] for medication administration and the International Classification of Diseases and Related Health Problems (ICD) [5] for condition diagnosis. Hence, a patient hospitalization can be described as the sequence of concept tokens detailing medical procedures pertaining to a patient coded using medical concepts from accepted medical taxonomies.…”

Section: Hospitalizations As Event Sequencesmentioning

confidence: 99%

“…We conclude with Section 6. This work is an extended version of Hansen et al [7] published at AIME 2023.…”

Section: Introductionmentioning

confidence: 99%

Hospitalization Length of Stay Prediction using Patient Event Sequences

Hansen¹,

Nielsen²,

Mulvad³

et al. 2023

Preprint

View full text Add to dashboard Cite

Predicting patients' hospital length of stay (LOS) is essential for improving resource allocation and supporting decision-making in healthcare organizations. This paper proposes a novel approach for predicting LOS by modeling patient information as sequences of events. Specifically, we present a transformer-based model, termed Medic-BERT (M-BERT), for LOS prediction using the unique features describing patients' medical event sequences. We performed empirical experiments on a cohort of more than 45k emergency care patients from a large Danish hospital. Experimental results show that M-BERT can achieve high accuracy on a variety of LOS problems and outperforms traditional nonsequence-based machine learning approaches.

show abstract

Rising to the challenge of defining and operationalising multimorbidity in a UK hospital setting: the ADMISSION research collaborative

Cooper,

Bunn,

Richardson

et al. 2024

Eur Geriatr Med

View full text Add to dashboard Cite

Purpose Greater transparency and consistency when defining multimorbidity in different settings is needed. We aimed to: (1) adapt published principles that can guide the selection of long-term conditions for inclusion in research studies of multimorbidity in hospitals; (2) apply these principles and identify a list of long-term conditions; (3) operationalise this list by mapping it to International Classification of Diseases 10th revision (ICD-10) codes. Methods Review by independent assessors and ratification by an interdisciplinary programme management group. Results Agreement was reached that when defining multimorbidity in hospitals for research purposes all conditions must meet the following four criteria: (1) medical diagnosis; (2) typically present for ≥ 12 months; (3) at least one of currently active; permanent in effect; requiring current treatment, care or therapy; requiring surveillance; remitting-relapsing and requiring ongoing treatment or care, and; (4) lead to at least one of: significantly increased risk of death; significantly reduced quality of life; frailty or physical disability; significantly worsened mental health; significantly increased treatment burden (indicated by an increased risk of hospital admission or increased length of hospital stay). Application of these principles to two existing lists of conditions led to the selection of 60 conditions that can be used when defining multimorbidity for research focused on hospitalised patients. ICD-10 codes were identified for each of these conditions to ensure consistency in their operationalisation. Conclusions This work contributes to achieving the goal of greater transparency and consistency in the approach to the study of multimorbidity, with a specific focus on the UK hospital setting.

show abstract

Assigning diagnosis codes using medication history

Cited by 10 publications

References 13 publications

Creating a computer assisted ICD coding system: performance metric choice and use of the ICD hierarchy

Creating a computer assisted ICD coding system: performance metric choice and use of the ICD hierarchy

Hospitalization Length of Stay Prediction using Patient Event Sequences

Rising to the challenge of defining and operationalising multimorbidity in a UK hospital setting: the ADMISSION research collaborative

Contact Info

Product

Resources

About