Creation of a tool for the Identification of Neurodevelopmental Disabilities to Improve Global Outcomes (INDIGO) in children aged 0-3 years in Malawi, Pakistan and Uganda – feasibility of implementation and diagnostic accuracy
Bibliographic record
Abstract
Abstract Background Over 50 million children under five have disabilities, the majority residing in resource-limited settings. Many children with neurodevelopmental disabilities (NDDs) remain undetected due to lack of culturally appropriate tools for identification. This study aimed to develop and evaluate the feasibility of the Identification of Neurodevelopmental Disabilities to Improve Global Outcomes (INDIGO) tool to identify NDDs in children aged 0 −3 years. Methods A systematic approach was used to construct the INDIGO tool. First, 114 items of the Malawi Developmental Assessment Tool (MDAT) were mapped onto the International Classification of Functioning, Disability and Health for Children and Youth (ICF-CY). Gaps were identified leading to review of 2,158 items from existing tools. After consensus, 59 additional items (28 existing, 31 newly created) were incorporated, ensuring comprehensive coverage of ICF-CY domains. The preliminary INDIGO tool (203 items) was pilot tested in Uganda, Malawi and Pakistan with a gold standard assessment protocol developed to validate diagnostic accuracy. Feasibility outcomes including recruitment, diagnostic accuracy, cultural applicability and practical implementation were assessed. Items with over 80% diagnostic accuracy were retained for the final INDIGO prototype. Results A total of 425 children (151 Malawi, 145 Pakistan, 129 Uganda) were assessed using both INDIGO and gold standard evaluation. The feasibility study highlighted challenges in recruiting younger children with behavioural or socioemotional conditions and difficulties assessing sensory impairment due to resource constraints. Despite challenges, 99 high performing items were selected for the final INDIGO prototype emphasizing diagnostic accuracy, feasibility and cultural neutrality. Conclusions The INDIGO tool is a novel, rigorously developed instrument designed for early detection of NDDs in children 0-3 years in LMICs. By integrating a broad range of developmental domains, INDIGO addressed key limitations of existing tools. Future large-scale validation and implementation studies are needed to assess its effectiveness in routine child health surveillance programmes. Key Messages What is already known on this topic Most existing developmental screening tools used globally are not culturally adapted for LMICs, require specialized training, and fail to comprehensively assess structural, functional, and environmental factors important for detecting NDDs in early childhood. What this study adds This study presents the development and feasibility testing of the INDIGO tool, a novel screening instrument for identifying moderate to severe NDDs in children under 3 years in resource-limited settings, incorporating items to assess structural anomalies, sensory impairments, and participation, offering a more holistic and contextually relevant approach to NDD detection. The study provides strong initial evidence of diagnostic accuracy across multiple LMIC settings, with high feasibility and acceptability among caregivers and health workers. How this study might affect research, practice or policy Future studies could enable scaled up implementation of tools such as INDIGO integrated into national child health systems for early NDD detection, enhancing referral and intervention in LMICs.
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 | 0.024 | 0.040 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.004 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
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".