The Haemophilia Joint Visualizer: development of a personalized, interactive, web‐based tool to help improve adherence to prophylaxis
Bibliographic record
Abstract
Despite prophylaxis being the standard of care for haemophilia in developed countries, with growing adoption worldwide 1, many persons with haemophilia (PWH) perceive their prophylactic schedules as an imposition on day-to-day activities 2 and fail to adhere to prescribed regimens, thus compromising effectiveness of treatment. Self-reported non-adherence has been reported in 40% of prophylaxis users 3. Lack of adherence leads to poor outcomes, both in the short and long term (i.e. bleeding episodes and deteriorating joint function respectively) and is significantly associated with increased bleeding, low physical health status scores, development of target joints and risk of high chronic pain, as well as lower quality of life (QoL) scores and missed work or school days 4, 5. To address the detrimental effects of non-adherence, we describe the development of an educational tool designed to foster communication with healthcare providers (HCPs) about the risk for long-term complications resulting from poor adherence. The Haemophilia Joint Visualizer (HJV) is an interactive, customizable, web-based tool (URL: http://www.hjv.bayer.co.uk) that helps facilitate the HCP-patient dialogue about benefits of prophylaxis in maintaining long-term joint health. The purpose of HJV is to support physicians in discussions of adherence and prophylaxis benefits with patients. The goals of HJV are to: (i) Communicate importance of adherence to prophylaxis; (ii) Demonstrate benefits of prophylaxis and (iii) Serve as a visual educational tool to aid HCPs in discussions with patients about the impact of joint bleeds on long-term joint health, non-adherence to prophylaxis and patient activity based on joint status. The HJV personalizes the patient experience based on input regarding the length of time on prophylaxis, age and adherence. Navigation of the tool consists of a linear navigation structure that requires completion of four main functions: patient profile input, joint damage visualizer, daily lifestyle and activities and summary report of results. Medical illustrations presented in the tool were created as composite images, based on radiographs and MRIs from actual patients, Dorland's Illustrated Medical Dictionary and Arnold-Hilgartner 5-category Classification of Haemophilic Arthropathy 6, 7, that allow visualization of the long-term impact of non-adherence on joint health (Fig. 1). The HJV's web-based interface allows the user to navigate linearly from a landing page to patient profile setup to 1 of 3 steps: Joint Damage Visualizer, Sports and Athletics/Daily Lifestyle and Hobbies and Summary Report. Figure 2 shows an example of navigation through the HJV, including an example landing page, patient profile and Steps 1–3 based on user input. Briefly, the landing page provides an interface from which the tool may be launched. The patient's age group, time on prophylaxis and bleeding frequency are entered for the patient profile. The user is then presented with a ‘joint damage’ interface (Step 1), where degree of joint damage is visualized according to on-demand versus prophylactic therapy. Selection of the prophylactic therapy option allows an additional choice between adherent and non-adherent. In Step 2, the user enters activities in categories of Sports/Athletics or Lifestyle/Hobbies, which facilitates discussions between patient and HCP about safety or feasibility of such activities according to the patient's profile and joint state. In Step 3, a summary of the HCP-patient discussion, along with images and descriptions of each stage of joint damage, is provided. A functionality assessment of the HJV in real world settings showed agreement between HCPs from five HTCs across Canada that the tool provided accurate visual representations of joint health and potential joint damage that can result from uncontrolled bleeding. Other positive attributes included its usefulness as an educational tool, the user-enabled image control for visualizing different stages of joint damage, the customizability of the software and the printable summary at the end of the user experience. Clinical advances over the past several decades have led to significant improvements in the management of haemophilia, leading to increased survival and reduced haemophilia-related morbidity. Prophylaxis prevents bleeding episodes, preserves joint function and improves QoL for PWH. Poor adherence to prophylaxis is associated with compromised efficacy and poor outcomes 4, 5. In a survey of behaviour and attitudes of PWH toward adherence, survey participants who failed to adhere to prophylaxis reported that the top motivator for improving adherence would be having proof that following a routine infusion schedule could prevent joint damage 3. The HJV serves that purpose by allowing a user to visualize potential joint damage, the severity of which is directly related to an individual's adherence to prophylaxis. The printable summary at the end of the user session further facilitates discussion between the patient and HCP on potential complications and how to achieve the best possible joint outcome, given one's lifestyle and activities. While the HJV forecasts potential joint damage due to patient behaviour, the tool should not, however, be interpreted as diagnostic, predictive or prognostic, as individual circumstances may vary. Other determinants of adherence include age, symptoms, beliefs and a patient's relationship with his HCP. Although PWH are motivated to adhere to prophylaxis when they experience symptoms, have a positive belief of necessity of treatment, and a good relationship with their HCP, barriers that impede adherence include infrequent or absence of symptoms, increasing age, time required for infusions, unwillingness, venous access limitations (i.e. in younger children), and difficulty in balancing prophylaxis regimens with family needs, as well as lack of education and awareness of importance of prophylaxis 8. To both motivate adherence and eliminate barriers, education and support of PWH is critically important to empowering them with a better understanding of self-care, management and adherence. Patient education is particularly important, as many individuals with haemophilia have limited knowledge about their own disease and treatment; in a large, prospective multicentre study in Scandinavia (N = 413), 44% of patients did not understand why they needed replacement factor and 5% did not know their own severity level 9. Patients may be empowered through education, including through electronic learning venues. A randomized study from the Netherlands showed that study participants who were randomized to follow an e-learning programme on haemophilia management not only had better theoretical knowledge about haemophilia, treatment options and complications, but also had significantly better practical skills than those who did not enrol in the programme 10. The HJV was developed as a tool that would aid patients in forecasting potential joint damage due to non-adherence and to facilitate discussions between HCPs and patients on the importance of prophylaxis based on personalized information including both medical history and individual activities and lifestyle. Due to the diverse nature of haemophilia, PWH have distinct needs, with variations in degree of factor deficiency, prescribed prophylaxis regimen, activity level, lifestyle, home support, accessibility to haemophilia treatment centres and other comorbidities such as cardiovascular disease. Barriers to adherence vary according to an individual's behaviour and attitude towards adherence, making prediction of joint outcomes complex. The HJV overcomes this complexity by personalizing the user's experience. We consider the HJV a valuable tool for improving adherence through education about the potential long-term impact on joint health. This work was funded by Bayer HealthCare Pharmaceuticals. Medical writing support was provided by Ingrid Koo, Ph.D., from FleishmanHillard. The HJV tool was developed with the assistance of Casey Steffen, MS, from Steffen VFX. Drs. Takedani, Solimeno, Saxena and Mathew were key contributors to the development of the HJV tool. Dr. Kalweit evaluated adherence data used to drive development of the HJV tool. Dr. Takedani was not involved in the collection or analysis of patient data. All authors were involved in drafting the publication and/or revising it critically for important intellectual content, and approving the final draft. HT has received honoraria from Bayer HealthCare for consultation work and has participated on Speaker Bureaus for Bayer, Baxter, Novo Nordisk and Pfizer. LS has received honoraria from Bayer HealthCare, Baxter and Novo Nordisk for consultation work. KS, LK and PM are employees of Bayer HealthCare.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.017 | 0.005 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".