Visual analytics in personalized health: A study of the expert analyst – health consumer relationship in a direct-to-consumer service
Bibliographic record
Abstract
In the era of “big data analytics” for healthcare, the personalized medicine promise offers a shift to the provision of care enabled by our technical ability to quantify and assess large volumes of biomedical data. This message however, often seems to strengthen a notion of healthcare from a “biomedical positivism framework”, that is, that diagnosis of disease, medical image analysis, integration of devices, and ultimately, the selection of the appropriate therapy is empowered by volumes of data and algorithmic accuracy, thus improving the patient’s illness. In this research program, we approached expert biomolecular analysts, recorded their sensemaking process, and analyzed the role of data visualization technologies while they performed analysis of multi-omic data for a direct-to-consumer service of personalized health. We uncovered the nature of the analysts turning to their human-interaction skillset to address the health reality of each consumer they worked for. Assertions about the scientific validity and the amount of data, often emphasize the claims of this personalized health approach, but in practice, the analysts turned to attend goals, preferences, to find actionable evidence in the data, and to frame a relatable health summary story for the clients. The role of technology design in scenarios like this one will be fundamental in properly translating and bridging the effort from these emergent providers (the analysts) in communication with the end consumers. Our findings suggest that both parties benefit from analytic capacities to explore and understand the strength of each piece of evidence in the case, including the evidence that is provided by the clients themselves beyond their biological samples. We believe that this work, along with the research methodologies deployed in work-settings, are a contribution to the Visual Analytics community to support the tasks of bio scientists in personalized medicine, as much as an HCI initiative in support of evidence-based models of preventive healthcare with large amounts of data.
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 | 0.030 | 0.075 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.010 | 0.015 |
| Scholarly communication | 0.014 | 0.011 |
| Open science | 0.002 | 0.009 |
| Research integrity | 0.004 | 0.005 |
| Insufficient payload (model declined to judge) | 0.008 | 0.001 |
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".