INTRODUCTION: Medicare Part D provides prescription drug coverage to seniors through a benefit plan with a major deductible inserted in the middle. It is important to study the extent to which this structure affects seniors’ adherence to prescription medications. Therefore, this study had the following objectives: (1) To identify characteristics of beneficiaries reaching and not reaching the coverage gap, (2) To study the entry and exit times from the coverage gap, (3) To study the impact of a complete gap in coverage on beneficiaries’ adherence to prescription medications, (4) To study the impact of a partial gap in coverage on beneficiaries’ adherence to prescription medications METHODS: This was a retrospective quasi-experimental analysis with matched control groups using a nationally representative sample of Part D enrollees from 2008 Centers for Medicare and Medicaid (CMS) datasets. Adherence to each oral medication taken for one or more of the seven pre-defined therapeutic classes before and after reaching the coverage gap was measured using the Medication Possession Ratio (MPR). Appropriate statistical tests for significance were performed for each analysis RESULTS: A quarter of our sample (24.42%) reached the coverage gap in 2008. Most of the beneficiaries reaching the coverage gap did so by end of September. Those reaching the coverage gap and losing all coverage experienced significantly greater reductions in adherence (3% more for beta-blockers to 9% more for oral anti-diabetic agents), compared to those not reaching the coverage gap. A considerable proportion of beneficiaries stopped taking medications in both the groups and the proportion of beneficiaries considered adherent also dropped in both the groups during the coverage gap period. CONCLUSIONS: Medicare Part D beneficiaries face significant barriers to adherence and this is especially highlighted among those reaching the coverage gap. Interventions to improve adherence in this group should target all beneficiaries, especially those with several chronic conditions.

We have seen a rapid increase in the development of deep learning algorithms in recent decades. However, while these algorithms have unlocked new business areas and led to great development in many fields, they are usually limited to Euclidean data. Researchers are increasingly starting to find out that they can better represent the data used in many real-life applications as graphs. Examples include high-risk domains such as finding the side effects when combining medicines using a protein-protein network. In high-risk domains, there is a need for trust and transparency in the results returned by deep learning algorithms. In this work, we explore how we can quantify uncertainty in Graph Neural Network predictions using conventional methods for conformal prediction as well as novel methods exploiting graph connectivity information. We evaluate the methods on both static and dynamic graphs and find that neither of the novel methods offers any clear benefits over the conventional methods. However, we see indications that using the graph connectivity information can lead to more efficient conformal predictors and a lower prediction latency than the conventional methods on large data sets. We propose that future work extend the research on using the connectivity information, specifically the node embeddings, to boost the performance of conformal predictors on graphs. / De senaste årtiondena har vi sett en drastiskt ökad utveckling av djupinlärningsalgoritmer. Även fast dessa algoritmer har skapat nya potentiella affärsområden och har även lett till nya upptäckter i flera andra fält, är dessa algoritmer dessvärre oftast begränsade till Euklidisk data. Samtidigt ser vi att allt fler forskare har upptäckt att data i verklighetstrogna applikationer oftast är bättre representerade i form av grafer. Exempel inkluderar hög-risk domäner som läkemedelsutveckling, där man förutspår bieffekter från mediciner med hjälp av protein-protein nätverk. I hög-risk domäner finns det ett krav på tillit och att resultaten från djupinlärningsalgoritmer är transparenta. I den här tesen utforskar vi hur man kan kvantifiera osäkerheten i resultaten hos Neurala Nätverk för grafer (eng. Graph Neural Networks) med hjälp av konform prediktion (eng. Conformal Prediction). Vi testar både konventionella metoder för konform prediktion, samt originella metoder som utnyttjar strukturell information från grafen. Vi utvärderar metoderna både på statiska och dynamiska grafer, och vi kommer fram till att de originella metoderna varken är bättre eller sämre än de konventionella metoderna. Däremot finner vi indikationer på att användning av den strukturella informationen från grafen kan leda till effektivare prediktorer och till lägre svarstid än de konventionella metoderna när de används på stora grafer. Vi föreslår att framtida arbete i området utforskar vidare hur den strukturella informationen kan användas, och framförallt nod representationerna, kan användas för att öka prestandan i konforma prediktorer för grafer.