Model Description:
A Bayesian network for Anemic women is shown below. We consider the benefits of Janani Suraksha Yojana and its impact on the number of anemic women during pregnancy. Dependency relationships between the nodes are established from government reports and published literature.
Nodes / Attribute:
The above model is based on the following nodes. The color scheme used represents the type of node/attribute. (Purple – Independent node; Orange – Dependent node; Red – Target node)
| Node / Attribute | Description | Data Source |
| Estimated Total Pregnancies_1341 | Estimated number of pregnant women | KAG 2020-21 |
| Number of Beneficiaries Availed Janani Suraksha Yojana (JSY)_1338 | Number of women enrolled under the scheme | KAG 2020-21 |
| Number of pregnant women registered for antenatal care (ANC)_1342 | Number of pregnant women registered for antenatal care (ANC) | KAG 2020-21 |
| Number of women registered for ANC within 1st trimester_1343 | Number of women registered for ANC within 1st trimester | KAG 2020-21 |
| Number of pregnant women who received 4 or more antenatal care check-ups_1344 | Number of women have gone through four or more ANC check-ups | KAG 2020-21 |
| No. of pregnant women tested for Hemoglobin 4 or more times_1346 | Number of women tested four or more times for Hemoglobin | KAG 2020-21 |
| Number of Pregnant women treated anemia (Hb<7)_1347 | Number of Pregnant women treated with anemia | KAG 2020-21 |
| Number of PW having severe anemia (Hb<7)_1348 (Target Variable) | Number of PW having severe anemia | KAG 2020-21 |
Intervention Modeling
It sets the network variables to specific levels, to track the changes in the target variable in the network. For instance: If we fix the value of the variable ‘Number of Beneficiaries Availed Janani Suraksha Yojana (JSY)_1338’ to ‘high’, then we would study the impact of this intervention on the target variable i.e., “Number of PW having severe anemia″ of the network across varieties of Taluks in Karnataka and see if that reduces the anemic pregnant women, thus ensuring the success of the scheme.
| Intervention Code | Intervening Node | Description | Ease of Intervention [1-most difficult, 5-easy] | Total Models Impacted | Models Impacted | Domains Impacted | Data Stories impacted upon intervention |
I1 | Number of Beneficiaries availed Janani Suraksha Yojana _1338 | Increasing the number of beneficiaries that avail the JSY scheme in order to assess its impact in reducing anemia amongst pregnant women. Beneficiaries can be increased by spending more resources on deploying more ASHA workers and spreading awareness amongst the general public. | 3 | 4 | 1. Maternal Deaths 2. Child Malnutrition 3. Child Stunting 4. Child Wasting | Health | |
| I2 | Number of pregnant women registered for antenatal care (ANC)_1342 | Increasing the number of pregnant women registering for ANC to determine how important of a factor it should play in the JSY scheme and how much this impacts in reducing severe Anemia. This can be implemented by making ANC registration the focal point of the JSY scheme. | 4 | 1 | 1. Maternal Deaths | Health | |
| I3 | Number of women registered for ANC within 1st trimester_1343 | Increasing the number of women registering for ANC within the 1st trimester to determine how important of a role registering for ANCs early plays in reducing severe Anemia and this too can be implemented via the JSY scheme and making early registration for ANCs a priority by the ASHA workers. | 4 | 1 | Maternal Deaths | Health | |
| I4 | Number of pregnant women who received 4 or more antenatal care check-ups_1344 | Increasing the number of women receiving at least 4 ANC checkups to determine the impact of frequent ANC checkups in reducing severe Anemia and this too can be implemented via the JSY scheme and strict vigilance by the ASHA workers on the women that have registered under the scheme. | 2 | 1 | Maternal Deaths | Health |
DISCLAIMER: AI predictive models are meant to support and augment expert decision-making, and not a replacement for the same. It is important for AI model predictions to be vetted by domain experts before committing to action