# Temporal Validation Changes the Apparent Public-Health Utility of Under-Five Mortality Prediction in Bangladesh: A Four-Round DHS Machine-Learning Study

arXiv: https://arxiv.org/abs/2602.03957 · HTML: https://mlsanity.com/paper/2602.03957/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 41 references that are in the map.
- First posted on arXiv 3 Feb 2026.

## Builds on (most cited first, 5 of 5)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [Tabular Data: Deep Learning is Not All You Need](https://mlsanity.com/paper/2106.03253/) (2021)
- [Why do tree-based models still outperform deep learning on tabular data?](https://mlsanity.com/paper/2207.08815/) (2022)
- [Estimating the Prediction Performance of Spatial Models via Spatial k-Fold Cross Validation](https://mlsanity.com/paper/2005.14263/) (2020)

## Abstract (arXiv)

Background: Under-five mortality in Bangladesh remains uneven despite national progress. DHS-based prediction models may guide targeted follow-up, but only if validation reflects future use. We examined how validation design changes apparent prediction performance. Methods: Four BDHS rounds (2011-2022; 33,962 children; 1,290 deaths) were analysed with a 26-feature pipeline and three model classes under four validation regimes, including cross-survey temporal validation (train 2011+2014, calibrate 2017, test 2022). A 32-unit ELU multilayer perceptron was selected via genetic-algorithm neural architecture search. AUROC used 2,000 bootstrap resamples; screening utility used sensitivity, PPV, and number needed to screen (NNS) at fixed capacity. Results: Validation regime altered public-health interpretation more than model class. NAS MLP AUROC ranged from 0.669 (2022-only random) to 0.775 (pooled random), with temporal AUROC 0.730. At the top-10% temporal threshold, NAS identified 152/355 deaths in 2022 (sensitivity 42.8%, PPV 13.2%, NNS 7.6). NNS across designs ranged from 5.6 to 11.0. Conclusions: Validation-regime choice changed screening workload and apparent policy value more than architecture. Temporal validation supports defensible estimates of follow-up and referral demand; DHS child-mortality studies should report sensitivity, PPV, and NNS before programmatic use.