August 6, 2026
THRUSDAY, 6 AUGUST 2026
18:30–20:00 IST • 15:00–16:30 CEST • 09:00–10:30 EDT
18:30–20:00 IST • 15:00–16:30 CEST • 09:00–10:30 EDT
16:30–18:00 IST • 13:00–14:30 CEST • 07:00–08:30 EDT
The sampling session will present AIMM’s proposed design for collecting a training dataset of approximately 6,000 children across five districts in Maharashtra. The AIMM team will outline the study-site selection, recruitment strategy, eligibility criteria, nutritional-status targets, subgroup considerations, measurement protocols, and quality-assurance procedures, while DefineSolutions will present the operational requirements and practical constraints associated with field implementation. Particular attention will be given to whether the planned sample can support meaningful analysis across relevant age, sex, nutritional-status, geographic, and socioeconomic subgroups.
The sampling session will present AIMM’s proposed design for collecting a training dataset of approximately 6,000 children across five districts in Maharashtra. The AIMM team will outline the study-site selection, recruitment strategy, eligibility criteria, nutritional-status targets, subgroup considerations, measurement protocols, and quality-assurance procedures, while DefineSolutions will present the operational requirements and practical constraints associated with field implementation. Particular attention will be given to whether the planned sample can support meaningful analysis across relevant age, sex, nutritional-status, geographic, and socioeconomic subgroups.
Register
Register
SESSION MEMO
SESSION MEMO
Join webinar
Join webinar
Tell us your questions and suggestions:
Key Questions
Key Questions
Is this design feasible in practice and sufficient to generate the diversity, subgroup sample sizes, measurement quality, and coverage needed to train, validate, and fairly evaluate the AIMM model across relevant populations and settings?
Is this design feasible in practice and sufficient to generate the diversity, subgroup sample sizes, measurement quality, and coverage needed to train, validate, and fairly evaluate the AIMM model across relevant populations and settings?
AIMM addresses the need for faster, lower-cost, and more accurate child nutrition screening, particularly in hard-to-reach, crisis-affected, or otherwise resource-constrained settings. Current nutrition assessments often require trained personnel, physical measurement tools, and repeated field visits, which can limit coverage during emergencies, displacement, or pandemic-related restrictions. AIMM explores whether smartphone-based images can help estimate key indicators of child undernutrition and support low-cost, near-real-time identification of children at risk.
Which population subgroups should be deliberately represented or oversampled to permit reliable fairness assessments, and what minimum sample sizes are required for meaningful subgroup comparisons?
Which population subgroups should be deliberately represented or oversampled to permit reliable fairness assessments, and what minimum sample sizes are required for meaningful subgroup comparisons?
AIMM is designed for settings where reliable nutrition data are urgently needed but difficult to collect. This includes conflict-affected areas, remote communities, humanitarian emergencies, public health crises, and other situations where access to children and households is limited. By enabling smartphone-based, community-level monitoring, AIMM can help generate timely information when standard measurement systems are disrupted, overstretched, or unavailable.
How should AIMM establish and quality-assure the reference measurements used for model training and validation, given that MUAC, length/height, and weight are themselves subject to measurement error?
How should AIMM establish and quality-assure the reference measurements used for model training and validation, given that MUAC, length/height, and weight are themselves subject to measurement error?
AIMM is being developed and tested in Maharashtra, India. In the first phase, the study will sample approximately 7,000 children across five districts — Dhule, Chandrapur, Nagpur, Jalgaon, and Beed — to train and validate the app. In a second phase, AIMM will be tested in Pune district with 150 households over a period of 12 months.
What biases could affect the training dataset, and how should these risks be monitored, documented, and addressed to support external validity?
What biases could affect the training dataset, and how should these risks be monitored, documented, and addressed to support external validity?
The app is being developed so that caregivers and families can monitor child nutrition using a standard smartphone, with minimal equipment and guidance. Drawing on prior experience with emoji-based questionnaires and culturally appropriate interface designs in Kenya, AIMM will place strong emphasis on intuitive, low-literacy, and locally appropriate user interaction. The app interface will be refined together with rural households and caregivers to ensure that it is easy to understand and use in everyday settings.
August 6, 2026
THRUSDAY, 6 AUGUST 2026
18:30–20:00 IST • 15:00–16:30 CEST • 09:00–10:30 EDT
18:30–20:00 IST • 15:00–16:30 CEST • 09:00–10:30 EDT
16:30–18:00 IST • 13:00–14:30 CEST • 07:00–08:30 EDT
The sampling session will present AIMM’s proposed design for collecting a training dataset of approximately 6,000 children across five districts in Maharashtra. The AIMM team will outline the study-site selection, recruitment strategy, eligibility criteria, nutritional-status targets, subgroup considerations, measurement protocols, and quality-assurance procedures, while DefineSolutions will present the operational requirements and practical constraints associated with field implementation. Particular attention will be given to whether the planned sample can support meaningful analysis across relevant age, sex, nutritional-status, geographic, and socioeconomic subgroups.
The sampling session will present AIMM’s proposed design for collecting a training dataset of approximately 6,000 children across five districts in Maharashtra. The AIMM team will outline the study-site selection, recruitment strategy, eligibility criteria, nutritional-status targets, subgroup considerations, measurement protocols, and quality-assurance procedures, while DefineSolutions will present the operational requirements and practical constraints associated with field implementation. Particular attention will be given to whether the planned sample can support meaningful analysis across relevant age, sex, nutritional-status, geographic, and socioeconomic subgroups.
Register
Register
SESSION MEMO
SESSION MEMO
Join webinar
Join webinar
Tell us your questions and suggestions:
Key Questions
Key Questions
Is this design feasible in practice and sufficient to generate the diversity, subgroup sample sizes, measurement quality, and coverage needed to train, validate, and fairly evaluate the AIMM model across relevant populations and settings?
Is this design feasible in practice and sufficient to generate the diversity, subgroup sample sizes, measurement quality, and coverage needed to train, validate, and fairly evaluate the AIMM model across relevant populations and settings?
AIMM addresses the need for faster, lower-cost, and more accurate child nutrition screening, particularly in hard-to-reach, crisis-affected, or otherwise resource-constrained settings. Current nutrition assessments often require trained personnel, physical measurement tools, and repeated field visits, which can limit coverage during emergencies, displacement, or pandemic-related restrictions. AIMM explores whether smartphone-based images can help estimate key indicators of child undernutrition and support low-cost, near-real-time identification of children at risk.
Which population subgroups should be deliberately represented or oversampled to permit reliable fairness assessments, and what minimum sample sizes are required for meaningful subgroup comparisons?
Which population subgroups should be deliberately represented or oversampled to permit reliable fairness assessments, and what minimum sample sizes are required for meaningful subgroup comparisons?
AIMM is designed for settings where reliable nutrition data are urgently needed but difficult to collect. This includes conflict-affected areas, remote communities, humanitarian emergencies, public health crises, and other situations where access to children and households is limited. By enabling smartphone-based, community-level monitoring, AIMM can help generate timely information when standard measurement systems are disrupted, overstretched, or unavailable.
How should AIMM establish and quality-assure the reference measurements used for model training and validation, given that MUAC, length/height, and weight are themselves subject to measurement error?
How should AIMM establish and quality-assure the reference measurements used for model training and validation, given that MUAC, length/height, and weight are themselves subject to measurement error?
AIMM is being developed and tested in Maharashtra, India. In the first phase, the study will sample approximately 7,000 children across five districts — Dhule, Chandrapur, Nagpur, Jalgaon, and Beed — to train and validate the app. In a second phase, AIMM will be tested in Pune district with 150 households over a period of 12 months.
What biases could affect the training dataset, and how should these risks be monitored, documented, and addressed to support external validity?
What biases could affect the training dataset, and how should these risks be monitored, documented, and addressed to support external validity?
The app is being developed so that caregivers and families can monitor child nutrition using a standard smartphone, with minimal equipment and guidance. Drawing on prior experience with emoji-based questionnaires and culturally appropriate interface designs in Kenya, AIMM will place strong emphasis on intuitive, low-literacy, and locally appropriate user interaction. The app interface will be refined together with rural households and caregivers to ensure that it is easy to understand and use in everyday settings.
August 6, 2026
THRUSDAY, 6 AUGUST 2026
18:30–20:00 IST • 15:00–16:30 CEST • 09:00–10:30 EDT
18:30–20:00 IST • 15:00–16:30 CEST • 09:00–10:30 EDT
16:30–18:00 IST • 13:00–14:30 CEST • 07:00–08:30 EDT
The sampling session will present AIMM’s proposed design for collecting a training dataset of approximately 6,000 children across five districts in Maharashtra. The AIMM team will outline the study-site selection, recruitment strategy, eligibility criteria, nutritional-status targets, subgroup considerations, measurement protocols, and quality-assurance procedures, while DefineSolutions will present the operational requirements and practical constraints associated with field implementation. Particular attention will be given to whether the planned sample can support meaningful analysis across relevant age, sex, nutritional-status, geographic, and socioeconomic subgroups.
The sampling session will present AIMM’s proposed design for collecting a training dataset of approximately 6,000 children across five districts in Maharashtra. The AIMM team will outline the study-site selection, recruitment strategy, eligibility criteria, nutritional-status targets, subgroup considerations, measurement protocols, and quality-assurance procedures, while DefineSolutions will present the operational requirements and practical constraints associated with field implementation. Particular attention will be given to whether the planned sample can support meaningful analysis across relevant age, sex, nutritional-status, geographic, and socioeconomic subgroups.
Register
Register
SESSION MEMO
SESSION MEMO
Join webinar
Join webinar
Tell us your questions and suggestions:
Key Questions
Key Questions
Is this design feasible in practice and sufficient to generate the diversity, subgroup sample sizes, measurement quality, and coverage needed to train, validate, and fairly evaluate the AIMM model across relevant populations and settings?
Is this design feasible in practice and sufficient to generate the diversity, subgroup sample sizes, measurement quality, and coverage needed to train, validate, and fairly evaluate the AIMM model across relevant populations and settings?
AIMM addresses the need for faster, lower-cost, and more accurate child nutrition screening, particularly in hard-to-reach, crisis-affected, or otherwise resource-constrained settings. Current nutrition assessments often require trained personnel, physical measurement tools, and repeated field visits, which can limit coverage during emergencies, displacement, or pandemic-related restrictions. AIMM explores whether smartphone-based images can help estimate key indicators of child undernutrition and support low-cost, near-real-time identification of children at risk.
Which population subgroups should be deliberately represented or oversampled to permit reliable fairness assessments, and what minimum sample sizes are required for meaningful subgroup comparisons?
Which population subgroups should be deliberately represented or oversampled to permit reliable fairness assessments, and what minimum sample sizes are required for meaningful subgroup comparisons?
AIMM is designed for settings where reliable nutrition data are urgently needed but difficult to collect. This includes conflict-affected areas, remote communities, humanitarian emergencies, public health crises, and other situations where access to children and households is limited. By enabling smartphone-based, community-level monitoring, AIMM can help generate timely information when standard measurement systems are disrupted, overstretched, or unavailable.
How should AIMM establish and quality-assure the reference measurements used for model training and validation, given that MUAC, length/height, and weight are themselves subject to measurement error?
How should AIMM establish and quality-assure the reference measurements used for model training and validation, given that MUAC, length/height, and weight are themselves subject to measurement error?
AIMM is being developed and tested in Maharashtra, India. In the first phase, the study will sample approximately 7,000 children across five districts — Dhule, Chandrapur, Nagpur, Jalgaon, and Beed — to train and validate the app. In a second phase, AIMM will be tested in Pune district with 150 households over a period of 12 months.
What biases could affect the training dataset, and how should these risks be monitored, documented, and addressed to support external validity?
What biases could affect the training dataset, and how should these risks be monitored, documented, and addressed to support external validity?
The app is being developed so that caregivers and families can monitor child nutrition using a standard smartphone, with minimal equipment and guidance. Drawing on prior experience with emoji-based questionnaires and culturally appropriate interface designs in Kenya, AIMM will place strong emphasis on intuitive, low-literacy, and locally appropriate user interaction. The app interface will be refined together with rural households and caregivers to ensure that it is easy to understand and use in everyday settings.