Forecasting outbreaks of konzo, a permanent paralysis caused by eating poorly processed bitter cassava during droughts
- Good it would do
- 4 / 5
- Can AI help
- 2 / 5
- How neglected
- 5 / 5
- Can we check it
- 2 / 5
Why it's stuck
Over 182 million people live in African countries where konzo occurs, and outbreaks strike during droughts when cassava becomes the only food. A 2015 study found that in DR Congo 17 of 19 warm El Niño phases were followed by an outbreak within two years, but it did not build a working forecast.
What we'd try
Combine seasonal climate forecasts, satellite measures of crop water stress and crop models to predict when and where cassava will be high in cyanide and food will be short. Check by hindcasting against past outbreaks in DR Congo, Mozambique, Tanzania and the Central African Republic.
What could stop us
The only long outbreak record is one DR Congo series from 1974 to 1996, so a konzo forecast may not be testable with enough power.
Source: https://www.frontiersin.org/articles/10.3389/fenvs.2015.00040/full
Do you know the answer?
One reply from someone in the field can settle what our AI can't.