## The Challenge
The Informatics Section of the Department of Pathology and Immunology of Washington University School of Medicine and the Data Analytics Steering Committee of the American Association for Clinical Chemistry welcome you to the ***Predicting PTHrP Results Competition***. 

Through this competition, we hope to engage our community of laboratory medicine practitioners in a fun and friendly environment where we can practice our skills, learn from each other, and get a sense of the variety in how we approach problems in the data-driven side of our field. 

The competition will run from May 8 to July 1, when submissions must be finalized. On July 5, the winner will be announced. A representative of the winning team will be invited to present their solution at the AACC Informatics Division Annual Meeting during the [AACC Annual Scientific Meeting & Clinical Lab Expo](https://meeting.aacc.org/) on July 25, 2022, in Chicago.

## The Background
Measurement of parathyroid hormone-related peptide (PTHrP) can help to establish a diagnosis of humoral hypercalcemia of malignancy. However, PTHrP testing is often ordered on patients with a low pretest probability of this condition. This poor laboratory utilization practice drives up healthcare costs, diverts scarce resources, and can cause anxiety, unwarranted cancer work-ups, and treatment delays in the event of a false positive. 

At Washington University in St. Louis, we use a manual, rules-based approach in which the lab medicine resident reviews PTH and calcium results to try to identify inappropriate orders where the probability of an abnormal PTHrP value is low. This process is labor-intensive and the ordering physician is often unwilling to cancel the order when contacted by the lab medicine resident.

In this friendly competition, we challenge you to develop an algorithm that predicts the PTHrP result (normal vs abnormal) using laboratory data available at the time of order to test our hypothesis that many of the PTHrP tests we send out fail to provide any novel information. The potential utility of this predictive algorithm would be to help convince the ordering physicians to improve utilization or to provide more timely clinical information while we wait for the result to return from the reference laboratory. 

![](https://i.imgur.com/zLscDSs.png)