Detecting, analyzing and impacting improvement opportunities related to total cost of care, clinical quality and revenue integrity
Example embodiments of a system, apparatus, computer readable media, and method are disclosed for improving clinical and financial outcomes for a healthcare provider The example embodiments may be used for aggregating data corresponding to care for a group of patients by at least one healthcare provider, generating a statistical model based on the aggregated data, periodically determining a current value for the treatment parameter associated with care of a patient provided by a healthcare provider, and causing treatment to be administered to the patient in response to applying the statistical model to determine that the current value for the treatment parameter is associated with an adverse outcome.
1. An apparatus comprising:
at least one processor; and
at least one memory storing computer executable instructions that, when executed, cause the at least one processor at least to perform:
retrieving a plurality of patient and physician longitudinal administrative records (LARs) that each correspond to a member of a first group of patients and a group of physicians, respectively;
aggregating, from the retrieved LARs, data corresponding to an episode of care that is common for each member of the first group of patients and the group of physicians by multiple healthcare providers;
retrieving a drug and supply formulary matrix for the episode of care, the drug and supply formulary matrix including supply data and acquisition cost data for the episode of care;
allocating the supply data and the acquisition cost data to each patient of the first group of patients for the episode of care;
generating a statistical model based on the aggregated data;
periodically determining a current value for the episode of care for the LARs provided by each of the plurality of healthcare providers; and
causing treatment to be administered for the episode of care to a second group of patients in response to applying the statistical model to determine that the current value for the episode of care is associated with an adverse outcome.
2. The apparatus of claim 1 , wherein the applying of the statistical model determines a probability that the adverse outcome will occur for the current value, wherein the causing of the treatment to be administered is in response to determining that the probability exceeds a threshold.
3. The apparatus of claim 1 , wherein the adverse outcome is an infection or a readmission.
4. The apparatus of claim 1 , wherein the causing of the treatment to be administered to the patient comprises electronically communicating an alert to a device for prompting a clinician to administer the treatment.
5. The apparatus of claim 4 , wherein the alert causes the device to display the current value for the episode of care, a probability of the adverse outcome, and a description of the treatment.
6. The apparatus of claim 4 , wherein the alert causes the device to exit a sleep mode and establish a network connection for receiving data.
7. The apparatus of claim 1 , wherein the causing of the treatment to be administered to the patient comprises controlling a drug delivery pump to automatically dispense a drug to the patient.
8. A computer-implemented method comprising:
retrieving, by an ingestion engine comprising at least one processor and at least one memory, a plurality of patient and physician longitudinal administrative records (LARs) that each correspond to a member of a first group of patients and a group of physicians, respectively;
aggregating, by an analytics engine comprising at least one processor and at least one memory storing computer executable instructions, from the retrieved LARs, data corresponding to an episode of care that is common for each member of the first group of patients and the group of physicians by multiple healthcare providers;
retrieving, by the ingestion engine, a drug and supply formulary matrix for the episode of care, the drug and supply formulary matrix including supply data and acquisition cost data for the episode of care;
allocating, by the ingestion engine, the supply data and the acquisition cost data to each patient of the first group of patients for the episode of care;
generating, by the analytics engine, a statistical model based on the aggregated data;
periodically determining, by the analytics engine, a current value for the episode of care for the LARs provided by each of the plurality of healthcare providers; and
causing, by the analytics engine, treatment to be administered for the episode of care to a second group of patients in response to applying the statistical model to determine that the current value for the episode of care is associated with an adverse outcome.
9. The method of claim 8 , wherein the applying of the statistical model determines a probability that the adverse outcome will occur for the current value, wherein the causing of the treatment to be administered is in response to determining that the probability exceeds a threshold.
10. The method of claim 8 , wherein the adverse outcome is an infection or a readmission.
11. The method of claim 8 , wherein the causing of the treatment to be administered to the patient comprises electronically communicating an alert to a device for prompting a clinician to administer the treatment.
12. The method of claim 11 , wherein the alert causes the device to display the current value for the episode of care, a probability of the adverse outcome, and a description of the treatment.
13. The method of claim 11 , wherein the alert causes the device to exit a sleep mode and establish a network connection for receiving data.
14. The method of claim 8 , wherein the causing of the treatment to be administered to the patient comprises controlling a drug delivery pump to automatically dispense a drug to the patient.
15. A non-transitory computer readable medium storing instructions that, when executed, cause at least one processor to perform at least:
retrieving a plurality of patient and physician longitudinal administrative records (LARs) that each correspond to a member of a first group of patients and a group of physicians, respectively;
aggregating, from the retrieved LARs, data corresponding to an episode of care that is common for each member of the first group of patients and the group of physicians by multiple healthcare providers;
retrieving a drug and supply formulary matrix for the episode of care, the drug and supply formulary matrix including supply data and acquisition cost data for the episode of care;
allocating the supply data and the acquisition cost data to each patient of the first group of patients for the episode of care;
generating a statistical model based on the aggregated data;
periodically determining a current value for the episode of care for the LARs provided by each of the plurality of healthcare providers; and
causing treatment to be administered for the episode of care to a second group of patients in response to applying the statistical model to determine that the current value for the episode of care is associated with an adverse outcome.
16. The computer readable medium of claim 15 , wherein the applying of the statistical model determines a probability that the adverse outcome will occur for the current value, wherein the causing of the treatment to be administered is in response to determining that the probability exceeds a threshold.
17. The computer readable medium of claim 15 , wherein the causing of the treatment to be administered to the patient comprises electronically communicating an alert to a device for prompting a clinician to administer the treatment.
18. The computer readable medium of claim 17 , wherein the alert causes the device to display the current value for the episode of care, a probability of the adverse outcome, and a description of the treatment.
19. The computer readable medium of claim 17 , wherein the alert causes the device to exit a sleep mode and establish a network connection for receiving data.
20. The computer readable medium of claim 15 , wherein the causing of the treatment to be administered to the patient comprises controlling a drug delivery pump to automatically dispense a drug to the patient.