Constructing treatment episodes from concomitant medication logs: a prospective observational study

Kuramoto, Lisa; Sobolev, Boris; Brasher, Penelope M. A.; Tang, Michael; Cragg, Jacquelyn J.

doi:10.1136/bmjopen-2019-034305

Cited by 4 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…9 The choice of exposure measure is one of many aspects of rigorous study planning. Other aspects include choosing the exposure and outcome, how to construct treatment episodes 35 and statistical approaches. 11 For a time-varying exposure, a censoring approach stops follow-up at the end of the first treatment episode.…”

Section: Discussionmentioning

confidence: 99%

A systematic, concept‐based method of developing the exposure measure for drug safety and effectiveness studies

Kuramoto

Sobolev

Rösner

et al. 2021

Pharmacoepidemiology and Drug

Self Cite

View full text Add to dashboard Cite

Purpose: In drug safety and effectiveness studies based on secondary data, the choice of an appropriate exposure measure for a given outcome can be challenging.Different measures of exposure can yield different estimates of treatment effect and safety. There is a knowledge gap with respect to developing and refining measures of drug exposure, to ensure that the exposure measure addresses the study question and is suitable for statistical analysis.Methods: We present a transparent, step-by-step approach to the development of drug exposure measures involving secondary data. This approach would be of interest to students and investigators with initial training in pharmacoepidemiology. We illustrate the approach using a study about Parkinson's disease.Results: We described the exposure specifications according to the study question.Next, we refined the exposure measure by linking it to knowledge about four major concepts in drug safety and effectiveness studies: drug use patterns, duration, timing, and dose. We then used this knowledge to guide the ultimate choice of exposure measure: time-varying, cumulative 6-month exposure to tamsulosin (a drug used to treat prostate hyperplasia). Conclusions:The proposed approach links exposure specifications to four major concepts in drug safety and effectiveness studies. Formulating subject-matter knowledge about these major concepts provides an avenue to develop the rationale and specifications for the exposure measure.

show abstract

Section: Discussionmentioning

confidence: 99%

A systematic, concept‐based method of developing the exposure measure for drug safety and effectiveness studies

Kuramoto

Sobolev

Rösner

et al. 2021

Pharmacoepidemiology and Drug

Self Cite

View full text Add to dashboard Cite

show abstract

“…For example, "LEVODOP," "LEVODAP," and "L-DOPA" were replaced by levodopa. The mean value was considered for cases where the same type of medication was used simultaneously with variable doses 29 .…”

Section: Methodsmentioning

confidence: 99%

A Decision Support System Based on Recurrent Neural Networks to Predict Medication Dosage for Patients with Parkinson's Disease

Riasi,

Delrobaei,

Salari

2023

Preprint

View full text Add to dashboard Cite

Using deep learning has demonstrated significant potential in making informed decisions based on clinical evidence. In this study, we deal with optimizing medication and quantitatively present the role of deep learning in predicting the medication dosage for patients with Parkinson's disease (PD). The proposed method is based on recurrent neural networks (RNNs) and tries to predict the dosage of five critical medication types for PD, including levodopa, dopamine agonists, monoamine oxidase-B inhibitors, catechol-O-methyltransferase inhibitors, and amantadine. Recurrent neural networks have memory blocks that retain crucial information from previous patient visits. This feature is helpful for patients with PD, as the neurologist can refer to the patient's previous state and the prescribed medication to make informed decisions. We employed data from the Parkinson's Progression Markers Initiative. The dataset included information on the Unified Parkinson's Disease Rating Scale, Activities of Daily Living, Hoehn and Yahr scale, demographic details, and medication use logs for each patient. We evaluated several models, such as multi-layer perceptron (MLP), Simple-RNN, long short-term memory (LSTM), and gated recurrent units (GRU). Our analysis found that recurrent neural networks (LSTM and GRU) performed the best. More specifically, when using LSTM, we were able to predict levodopa and dopamine agonist dosage with a mean squared error of 0.009 and 0.003, mean absolute error of 0.062 and 0.030, root mean square error of 0.099 and 0.053, and R-squared of 0.514 and 0.711, respectively.

show abstract

“…Treatment episodes were defined as the events from the start to the end of the administration of a medication [43][44][45][46][47][48]. We constructed concomitant treatment episodes as the intervals of time when two different drug prescriptions were contemporaneously active.…”

Section: Construction Of Concomitant Treatment Episodesmentioning

confidence: 99%

Drug dosage modifications in 24 million in-patient prescriptions covering eight years: A Danish population-wide study of polypharmacy

Leal Rodríguez,

Haue,

Mazzoni

et al. 2023

PLOS Digit Health

View full text Add to dashboard Cite

Polypharmacy has generally been assessed by raw counts of different drugs administered concomitantly to the same patients; not with respect to the likelihood of dosage-adjustments. To address this aspect of polypharmacy, the objective of the present study was to identify co-medications associated with more frequent dosage adjustments. The data foundation was electronic health records from 3.2 million inpatient admissions at Danish hospitals (2008–2016). The likelihood of dosage-adjustments when two drugs were administered concomitantly were computed using Bayesian logistic regressions. We identified 3,993 co-medication pairs that associate significantly with dosage changes when administered together. Of these pairs, 2,412 (60%) did associate with readmission, mortality or longer stays, while 308 (8%) associated with reduced kidney function. In comparison to co-medications pairs that were previously classified as drug-drug interactions, pairs not classified as drug-drug interactions had higher odds ratios of dosage modifications than drug pairs with an established interaction. Drug pairs not corresponding to known drug-drug interactions while still being associated significantly with dosage changes were prescribed to fewer patients and mentioned more rarely together in the literature. We hypothesize that some of these pairs could be associated with yet to be discovered interactions as they may be harder to identify in smaller-scale studies.

show abstract

Constructing treatment episodes from concomitant medication logs: a prospective observational study

Cited by 4 publications

References 19 publications

A systematic, concept‐based method of developing the exposure measure for drug safety and effectiveness studies

A systematic, concept‐based method of developing the exposure measure for drug safety and effectiveness studies

A Decision Support System Based on Recurrent Neural Networks to Predict Medication Dosage for Patients with Parkinson's Disease

Drug dosage modifications in 24 million in-patient prescriptions covering eight years: A Danish population-wide study of polypharmacy

Contact Info

Product

Resources

About