Predictive models for infectious diseases

A system of infection prevention data analysis comprising:

• at least one processor;
• and
• memory configured to communicate with the at least one processor, wherein the memory stores instructions that, in response to execution by the at least one processor, cause the at least one processor to perform operations comprising:
• acquiring environmental risk factor data, wherein the environmental risk factor data corresponds to a particular geographic region;
• acquiring social risk factor data, wherein the social risk factor corresponds to the particular geographic region;
• receiving a first input specifying a particular disease;
• receiving a second input specifying a first lead time in the future;
• receiving a third input specifying a second lead time in the future, wherein the second lead time is less than the first lead time;
• selecting subsets of the environmental risk factor data and the social risk factor data that are associated with the particular disease;
• classifying each subset of the environmental risk factor data and the social risk factor as a layer of clustered data, each layer assigned a measurement scale of values that are common between the different layers;
• assigning an integer value to each layer of clustered data based on the common measurement scale of values;
• applying a prediction algorithm to the environmental and social risk factor data different layers to generate a disease risk model for generating at least a trigger prediction and a transmission prediction for a disease-causing pathogen at the particular geographic region, wherein each of the selected environmental risk factor data and the selected social risk factor data layers are assigned a weight based according to influence of the underlying data on the particular disease;
• wherein the trigger prediction is a prediction of a disease outbreak at the particular geographic region at a first defined time period in the future corresponding to the first lead time;
• wherein the transmission prediction is a prediction of a human-to-human transmission of the disease-causing pathogen at the particular geographic region at a second defined time period in the future corresponding to the second lead time;
• generating the trigger prediction by applying the disease risk model to a forecast of data for a first lead time for the particular geographic region;
• and
• generating the transmission prediction by applying the disease risk model to the transmission prediction for a second lead time for the particular geographic region in the future;
• computing a trigger prediction score and a transmission prediction score for a plurality of pixels of a risk map, wherein the plurality of pixels correspond to the particular geographic region;
• and
• generating the risk map comprising the plurality of pixels, wherein the risk map indicates a likelihood of an outbreak and spread of the particular disease in the particular geographic region in the first and second defined time periods in the future.

A non-transitory, computer-readable medium comprising machine-readable instructions that, when executed by a processor of a computing device, cause the computing device to at least:

• acquire environmental risk factor data, wherein the environmental risk factor data corresponds to a particular geographic region;
• acquire social risk factor data, wherein the social risk factor corresponds to the particular geographic region;
• receive a first input specifying a particular disease;
• receive a second input specifying a first lead time in the future;
• receive a third input specifying a second lead time in the future, wherein the second lead time is less than the first lead time;
• select subsets of the environmental risk factor data and the social risk factor data that are associated with the particular disease;
• classify each subset of the environmental risk factor data and the social risk factor as a layer of clustered data, each layer assigned a measurement scale of values that are common between the different layers;
• assign an integer value to each layer of clustered data based on the common measurement scale of values;
• apply a prediction algorithm to the selected environmental and social risk factor data different layers to generate a disease risk model for generating at least a trigger prediction and a transmission prediction for a disease-causing pathogen at the particular geographic region, wherein each of the selected environmental risk factor data and the selected social risk factor data layers are assigned a weight based according to influence of the underlying data on the particular disease;
• wherein the trigger prediction is a prediction of a disease outbreak at the particular geographic region at a first defined time period in the future corresponding to the first lead time;
• wherein the transmission prediction is a prediction of a human-to-human transmission of the disease-causing pathogen at the particular geographic region at a second defined time period in the future corresponding to the second lead time;
• generate the trigger prediction by applying the disease risk model to a forecast of data for a first lead time for the particular geographic region in the future;
• generate the transmission prediction by applying the disease risk model to the transmission prediction for the second lead time for the particular geographic region in the future;
• compute a trigger prediction score and a transmission prediction score for a plurality of pixels of a risk map, wherein the plurality of pixels correspond to the particular geographic region;
• and
• generate the risk map comprising the plurality of pixels, wherein the risk map indicates a likelihood of an outbreak and spread of the particular disease in the particular geographic region in the first and second defined time periods in the future corresponding to the first lead time.