Treatment patterns in pediatric patients with multiple sclerosis in Germany—a nationwide claim-based analysis

Frahm, Niklas; Peters, Melanie; Bätzing, Jörg; Ellenberger, David; Akmatov, Manas K.; Haas, Judith; Stahmann, Alexander; Zettl, Uwe K.; Holstiege, Jakob

doi:10.1177/17562864211048336

Cited by 8 publications

(4 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to the diagnosis data, we extracted individual information on prescribed and dispensed medications from the pseudonymous data of nationwide outpatient drug prescriptions. The claims data and the prescription data are linked by patient information (compare [ 44 ]).…”

Section: Methodsmentioning

confidence: 99%

Patient Embeddings From Diagnosis Codes for Health Care Prediction Tasks: Pat2Vec Machine Learning Framework

Steiger¹,

Kroll²

2023

JMIR AI

View full text Add to dashboard Cite

Background In health care, diagnosis codes in claims data and electronic health records (EHRs) play an important role in data-driven decision making. Any analysis that uses a patient’s diagnosis codes to predict future outcomes or describe morbidity requires a numerical representation of this diagnosis profile made up of string-based diagnosis codes. These numerical representations are especially important for machine learning models. Most commonly, binary-encoded representations have been used, usually for a subset of diagnoses. In real-world health care applications, several issues arise: patient profiles show high variability even when the underlying diseases are the same, they may have gaps and not contain all available information, and a large number of appropriate diagnoses must be considered. Objective We herein present Pat2Vec, a self-supervised machine learning framework inspired by neural network–based natural language processing that embeds complete diagnosis profiles into a small real-valued numerical vector. Methods Based on German outpatient claims data with diagnosis codes according to the International Statistical Classification of Diseases and Related Health Problems, 10th Revision (ICD-10), we discovered an optimal vectorization embedding model for patient diagnosis profiles with Bayesian optimization for the hyperparameters. The calibration process ensured a robust embedding model for health care–relevant tasks by aggregating the metrics of different regression and classification tasks using different machine learning algorithms (linear and logistic regression as well as gradient-boosted trees). The models were tested against a baseline model that binary encodes the most common diagnoses. The study used diagnosis profiles and supplementary data from more than 10 million patients from 2016 to 2019 and was based on the largest German ambulatory claims data set. To describe subpopulations in health care, we identified clusters (via density-based clustering) and visualized patient vectors in 2D (via dimensionality reduction with uniform manifold approximation). Furthermore, we applied our vectorization model to predict prospective drug prescription costs based on patients’ diagnoses. Results Our final models outperform the baseline model (binary encoding) with equal dimensions. They are more robust to missing data and show large performance gains, particularly in lower dimensions, demonstrating the embedding model’s compression of nonlinear information. In the future, other sources of health care data can be integrated into the current diagnosis-based framework. Other researchers can apply our publicly shared embedding model to their own diagnosis data. Conclusions We envision a wide range of applications for Pat2Vec that will improve health care quality, including personalized prevention and signal detection in patient surveillance as well as health care resource planning based on subcohorts identified by our data-driven machine learning framework.

show abstract

Section: Methodsmentioning

confidence: 99%

Patient Embeddings From Diagnosis Codes for Health Care Prediction Tasks: Pat2Vec Machine Learning Framework

Steiger¹,

Kroll²

2023

JMIR AI

View full text Add to dashboard Cite

show abstract

“…MS onset before 18 years of age is relatively rare [ 73 , 74 ]. The volume of research on pediatric MS is limited compared to adult-onset MS and is often observational [ 74 ].…”

Section: Efficacy In Other Ms Settingsmentioning

confidence: 99%

“…The volume of research on pediatric MS is limited compared to adult-onset MS and is often observational [ 74 ]. Consequently, the DMTs commonly used for adults are often prescribed for pediatric MS because of clinician familiarity and lack of approved pediatric MS therapies [ 12 , 73 ]. IFNs and GA, with well-known efficacy and safety profiles, have been preferred in the pediatric MS population [ 12 , 73 – 76 ].…”

Section: Efficacy In Other Ms Settingsmentioning

confidence: 99%

“…Consequently, the DMTs commonly used for adults are often prescribed for pediatric MS because of clinician familiarity and lack of approved pediatric MS therapies [ 12 , 73 ]. IFNs and GA, with well-known efficacy and safety profiles, have been preferred in the pediatric MS population [ 12 , 73 – 76 ]. A consensus statement from the International Pediatric MS Study Group supports these agents as first-line DMTs [ 77 ].…”

Section: Efficacy In Other Ms Settingsmentioning

confidence: 99%

See 1 more Smart Citation

Twenty Years of Subcutaneous Interferon-Beta-1a for Multiple Sclerosis: Contemporary Perspectives

Freedman,

Coyle,

Hellwig

et al. 2024

Neurol Ther

View full text Add to dashboard Cite

Multiple sclerosis (MS) is a chronic, progressive, inflammatory disorder of the central nervous system. Relapsing–remitting MS (RRMS), the most common form of the disease, is characterized by transient neurological dysfunction with concurrent accumulation of disability. Over the past three decades, disease-modifying therapies (DMTs) capable of reducing the frequency of relapses and slowing disability worsening have been studied and approved for use in patients with RRMS. The first DMTs were interferon-betas (IFN-βs), which were approved in the 1990s. Among them was IFN-β-1a for subcutaneous (sc) injection (Rebif ® ), which was approved for the treatment of MS in Europe and Canada in 1998 and in the USA in 2002. Twenty years of clinical data and experience have supported the efficacy and safety of IFN-β-1a sc in the treatment of RRMS, including pivotal trials, real-world data, and extension studies lasting up to 15 years past initial treatment. Today, IFN-β-1a sc remains an important therapeutic option in clinical use, especially around pregnancy planning and lactation, and may also be considered for aging patients, in which MS activity declines and long-term immunosuppression associated with some alternative therapies is a concern. In addition, IFN-β-1a sc is used as a comparator in many clinical studies and provides a framework for research into the mechanisms by which MS begins and progresses.

show abstract

General Principles of Immunotherapy in Neurological Diseases

Rommer,

Hecker,

Zrzavy

et al. 2024

Neuroimmune Diseases

View full text Add to dashboard Cite

Treatment patterns in pediatric patients with multiple sclerosis in Germany—a nationwide claim-based analysis

Cited by 8 publications

References 32 publications

Patient Embeddings From Diagnosis Codes for Health Care Prediction Tasks: Pat2Vec Machine Learning Framework

Patient Embeddings From Diagnosis Codes for Health Care Prediction Tasks: Pat2Vec Machine Learning Framework

Twenty Years of Subcutaneous Interferon-Beta-1a for Multiple Sclerosis: Contemporary Perspectives

General Principles of Immunotherapy in Neurological Diseases

Contact Info

Product

Resources

About