Leveraging data visualization to improve the use of data for global health decision-making
Bibliographic record
Abstract
T he surge of available global health data necessitates developing creative approaches to communicate evidence to decision-makers.This "data revolution" reflects both increased demand for data to assess programs and policies and improved technologies to rapidly collect and disseminate data [1].More available data does not necessarily translate into more evidence-based program and policies in global health.There is limited understanding of how to effectively promote use of data for decision-making [2].Data visualization -the visual representation of data -techniques are increasingly being used in global health.The DHS Program' s STATcompiler (https://www.statcompiler.com/en/) and UNICEF' s Data portal (https://data.unicef.org/)are data exploratory tools that allow users to visualize household survey data collected by these institutions.Dashboards are used by governments in low-and middle-income (LMICs) countries and development partners to present indicators of interest.Dashboards exist for every global health focus area, and sometimes numerous dashboards exist that visualize the same topic.Scorecards, another data visualization technique, are also widely used in global health.For example, the Government of Tanzania has used reproductive, maternal newborn child health (RMNCH) scorecards to track progress towards achieving maternal and child health intervention targets since 2014.This viewpoint describes efforts undertaken by the National Evaluation Platform (NEP) project to strengthen capacity for analysis and communication of RMNCH & nutrition (RMNCH&N) data to inform policy and program planning decisions by governments in four sub-Saharan African countries between 2013-2018.Specifically, this viewpoint aims to describe the evolution of efforts to incorporate data visualization and its impact on communicating actionable key messages to decision makers DATA VISUALIZATION TRAINING FOR NEP COUNTRY TEAMSThe Institute for International Programs at Johns Hopkins University (IIP-JHU) collaborated with government institutions to develop NEPs in Malawi, Mali, Mozambique, and Tanzania.The NEP approach brought together representatives from national statistical offices, government ministries, and public research institutions for training and mentorship activities to systematically identify and answer priority RMNCH&N program and policy questions with diverse data sources [3].Even though participants worked with RMNCH&N data as part of their professional roles, we found that baseline data literacy skills -including identifying and communicating key messages and producing graphs in Excel -were highly variable and generally low [4].An external midterm evaluation across the four NEP countries found that that Leveraging data visualization to improve the use of data for global health decision-making
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 | 0.031 | 0.087 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.003 | 0.005 |
| Bibliometrics | 0.009 | 0.009 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.006 | 0.006 |
| Open science | 0.003 | 0.004 |
| Research integrity | 0.003 | 0.004 |
| Insufficient payload (model declined to judge) | 0.007 | 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".