Ranking Madhya Pradesh's Districts on Maternal and Child Health: What a Neural Network Confirms
- ▸Ranking all 45 districts of Madhya Pradesh on 32 maternal and child health indicators, this study found Indore has the highest development index and Tikamgarh the lowest — with 12 districts classified 'backward,' 10 'underdeveloped,' 11 'developing,' and 12 'developed.'
- ▸The district rankings were derived from Principal Component Analysis (six components explaining 81.7% of variance) and then independently confirmed by a neural network, which classified districts into the same four categories with 100% accuracy on both training and test data.
- ▸One counterintuitive finding stands out: sex ratio at birth was actually worse in 'developed' districts (886 girls per 1,000 boys) than in 'backward' districts (935) — suggesting economic development alone does not fix, and may even worsen, sex-selection pressures.
Which of Madhya Pradesh's 45 districts are furthest behind on maternal and child health — and can you trust the ranking? This study set out to answer both questions at once. The researchers gathered 32 separate health and welfare indicators for every district, spanning things like infant mortality, birth rate, sex ratio, female literacy, household sanitation, and childhood immunization rates — data drawn from India's official Annual Health Survey. They then used a statistical technique called Principal Component Analysis (PCA) to compress those 32 indicators into a single development score per district, and sorted every district into one of four bands: Developed, Developing, Underdeveloped, or Backward.
Indore came out on top; Tikamgarh came out last. Of the 45 districts, 12 landed in "developed," 11 in "developing," 10 in "underdeveloped," and 12 in "backward" — a roughly even four-way split that the authors read as clear evidence of wide regional disparity within a single state.
To check whether the PCA-based ranking was trustworthy rather than a statistical artefact, the authors fed the same district data into a neural network and asked it to independently predict each district's category. It matched the PCA classification for every single district, in both the training and test samples — a strong cross-check that the four-way grouping reflects a real, learnable pattern in the underlying data rather than noise.
This study is itself an India-focused piece of applied development economics, but its broader relevance lies in the method, not just the Madhya Pradesh numbers: the same PCA-plus-neural-network approach could be replicated using more recent National Family Health Survey (NFHS) or Annual Health Survey data to produce updated, methodologically cross-validated district rankings for any Indian state, feeding directly into the district-level planning mandate created by the 73rd and 74th constitutional amendments. With India still working toward Sustainable Development Goal targets on maternal mortality (SDG 3.1) and under-five mortality (SDG 3.2), and with total public health expenditure only reaching about 1.2% of GDP by 2017-18 against goals of 2.5%, district-level targeting tools like this one are directly relevant to how limited public health resources get allocated across India's states. The sex-ratio paradox this paper surfaces is also a live national policy issue — India's child sex ratio has been a persistent concern nationally, not just in Madhya Pradesh, and this study's finding that 'developed' districts fare worse on this specific measure lines up with similar patterns documented in Punjab, Haryana, and other relatively prosperous states.
Primary Sources
Cite This Article
EconoLens Research Desk. (2026, August 25). Ranking Madhya Pradesh's Districts on Maternal and Child Health: What a Neural Network Confirms. EconoLens. https://www.econolens.co.in/news/madhya-pradesh-districts-maternal-child-health-ranking
The EconoLens Research Desk reviews academic papers in economics and econometrics, translating cutting-edge research into accessible analysis. Full credit is given to original authors in every review.