Machine learning models for abstract screening task - A systematic literature review application for health economics and outcome research.

OBJECTIVE: Systematic literature reviews (SLRs) are critical for life-science research. However, the manual selection and retrieval of relevant publications can be a time-consuming process. This study aims to (1) develop two disease-specific annotated corpora, one for human papillomavirus (HPV) associated diseases and the other for pneumococcal-associated pediatric diseases (PAPD), and (2) optimize machine- and deep-learning models to facilitate automation of the SLR abstract screening. METHODS: This study constructed two disease-specific SLR screening corpora for HPV and PAPD, which contained citation metadata and corresponding abstracts. Performance was evaluated using precision, recall, accuracy, and F1-score of multiple combinations of machine- and deep-learning algorithms and features such as keywords and MeSH terms. RESULTS AND CONCLUSIONS: The HPV corpus contained 1697 entries, with 538 relevant and 1159 irrelevant articles. The PAPD corpus included 2865 entries, with 711 relevant and 2154 irrelevant articles. Adding additional features beyond title and abstract improved the performance (measured in Accuracy) of machine learning models by 3% for HPV corpus and 2% for PAPD corpus. Transformer-based deep learning models that consistently outperformed conventional machine learning algorithms, highlighting the strength of domain-specific pre-trained language models for SLR abstract screening. This study provides a foundation for the development of more intelligent SLR systems.

HPV vaccine initiation at 9 or 10 years of age and better series completion by age 13 among privately and publicly insured children in the US.

The US Advisory Committee on Immunization Practice recommends routine human papillomavirus (HPV) vaccination at 11-12 years of age, but states that vaccination may be initiated as early as 9 years. Our primary goal was to assess whether initiating HPV vaccination at 9-10 years of age, compared to 11-12, was associated with a higher rate of series completion by 13 years of age, and to identify factors associated with series completion by age 13. The study used vaccine claims and other data from the IBM MarketScan Commercial Claims and Encounters (privately insured) and IBM MarketScan Multi-State Medicaid (publicly insured) databases. Participants were 9-12 years of age and initiated HPV vaccination between January 2006 and December 2018 (publicly insured) or February 2019 (privately insured). Among 100,117 privately insured individuals, those initiating the HPV vaccination series at 9-10 years of age had a significantly higher series completion rate by 13 years of age than did those initiating at 11-12 years of age (76.2% versus 48.1%; p < .001). The same pattern was observed for 115,863 publicly insured individuals (70.4% versus 40.0%; p < .001). Provider and health care plan type, female sex, race/ethnicity, and wellness checks or non-HPV vaccinations during the baseline period were significantly associated with series completion by 13 years of age. Proactive initiation of HPV vaccination at 9-10 years of age was associated with higher rates of series completion by 13 years of age. These findings can inform provider education and other interventions to encourage timely HPV vaccination series completion.

Patients' Perspective About the Cost of Diabetes Management: An Analysis of Online Health Communities.

OBJECTIVE: To understand the perspectives of persons' living with diabetes about the increasing cost of diabetes management through an analysis of online health communities (OHCs) and the impact of persons' participation in OHCs on their capacity and treatment burden. PATIENTS AND METHODS: A qualitative study of 556 blog posts submitted between January 1, 2007 and December 31, 2017 to 4 diabetes social networking sites was conducted between March 2018 and July 2019. All posts were coded inductively using thematic analysis procedures. Eton's Burden of Treatment Framework and Boehmer's Theory of Patient Capacity directed triangulation of themes with existing theory. RESULTS: Three themes were identified: (1) cost barriers to care: participants describe individual and systemic cost barriers that inhibit prescribed therapy goals; (2) impact of financial cost on health: participants describe the financial effects of care on their physical and emotional health; and (3) saving strategies to overcome cost impact: participants discuss practical strategies that help them achieve therapy goals. Finally, we also identify that the use of OHCs serves to increase persons' capacity with the potential to decrease treatment burden, ultimately improving mental and physical health. CONCLUSION: High cost for diabetes care generated barriers that negatively affected physical health and emotional states. Participant-shared experiences in OHCs increased participants' capacity to manage the burden. Potential solutions include cost-based shared decision-making tools and advocacy for policy change.

Analyzing Patient Secure Messages Using a Fast Health Care Interoperability Resources (FIHR)-Based Data Model: Development and Topic Modeling Study.

BACKGROUND: Patient portals tethered to electronic health records systems have become attractive web platforms since the enacting of the Medicare Access and Children's Health Insurance Program Reauthorization Act and the introduction of the Meaningful Use program in the United States. Patients can conveniently access their health records and seek consultation from providers through secure web portals. With increasing adoption and patient engagement, the volume of patient secure messages has risen substantially, which opens up new research and development opportunities for patient-centered care. OBJECTIVE: This study aims to develop a data model for patient secure messages based on the Fast Healthcare Interoperability Resources (FHIR) standard to identify and extract significant information. METHODS: We initiated the first draft of the data model by analyzing FHIR and manually reviewing 100 sentences randomly sampled from more than 2 million patient-generated secure messages obtained from the online patient portal at the Mayo Clinic Rochester between February 18, 2010, and December 31, 2017. We then annotated additional sets of 100 randomly selected sentences using the Multi-purpose Annotation Environment tool and updated the data model and annotation guideline iteratively until the interannotator agreement was satisfactory. We then created a larger corpus by annotating 1200 randomly selected sentences and calculated the frequency of the identified medical concepts in these sentences. Finally, we performed topic modeling analysis to learn the hidden topics of patient secure messages related to 3 highly mentioned microconcepts, namely, fatigue, prednisone, and patient visit, and to evaluate the proposed data model independently. RESULTS: The proposed data model has a 3-level hierarchical structure of health system concepts, including 3 macroconcepts, 28 mesoconcepts, and 85 microconcepts. Foundation and base macroconcepts comprise 33.99% (841/2474), clinical macroconcepts comprise 64.38% (1593/2474), and financial macroconcepts comprise 1.61% (40/2474) of the annotated corpus. The top 3 mesoconcepts among the 28 mesoconcepts are condition (505/2474, 20.41%), medication (424/2474, 17.13%), and practitioner (243/2474, 9.82%). Topic modeling identified hidden topics of patient secure messages related to fatigue, prednisone, and patient visit. A total of 89.2% (107/120) of the top-ranked topic keywords are actually the health concepts of the data model. CONCLUSIONS: Our data model and annotated corpus enable us to identify and understand important medical concepts in patient secure messages and prepare us for further natural language processing analysis of such free texts. The data model could be potentially used to automatically identify other types of patient narratives, such as those in various social media and patient forums. In the future, we plan to develop a machine learning and natural language processing solution to enable automatic triaging solutions to reduce the workload of clinicians and perform more granular content analysis to understand patients' needs and improve patient-centered care.

Estimating disease burden using Internet data.

Data on disease burden are often used for assessing population health, evaluating the effectiveness of interventions, formulating health policies, and planning future resource allocation. We investigated whether Internet usage and social media data, specifically the search volume on Google, page view count on Wikipedia, and disease mentioning frequency on Twitter, correlated with the disease burden, measured by prevalence and treatment cost, for 1633 diseases over an 11-year period. We also applied least absolute shrinkage and selection operator to predict the burden of diseases. We found that Google search volume is relatively strongly correlated with the burdens for 39 of 1633 diseases, including viral hepatitis, diabetes mellitus, multiple sclerosis, and hemorrhoids. Wikipedia and Twitter data strongly correlated with the burdens of 15 and 7 diseases, respectively. However, an accurate analysis must consider each condition's characteristics, including acute/chronic nature, severity, familiarity to the public, and the presence of stigma.