What Changed at Tempus

Tempus received FDA 510(k) clearance for Tempus ECG PH, software that reads a standard 12 lead electrocardiogram and identifies signs associated with pulmonary hypertension. The device does not require new hardware or a new test, since it runs against ECGs that are already being captured for other reasons. This adds to the cleared cardiovascular algorithm suite Tempus has been assembling, and pulmonary hypertension is a deliberate target because it is characteristically diagnosed late.

Our read

Clearance is the gate that separates a research grade algorithm from something a cardiology service can put into routine practice, and this one runs on data every hospital already has in volume. The deployment question is what happens downstream of a positive flag, because pulmonary hypertension confirmation requires right heart catheterization and a screening tool that raises referral volume without a matching diagnostic pathway creates a bottleneck rather than removing one. Ask for the sensitivity and specificity in the cleared indication and the population it was established in.

Tempus announced the publication of a study in Nature Medicine demonstrating the performance of PRISM2, its multimodal slide-level pathology foundation model developed with Microsoft. The model processes routine hematoxylin and eosin slides to predict biomarker status and patient prognosis without requiring specialized fine-tuning.

Our read

Clinical buyers and oncology researchers can leverage this peer-reviewed evidence to validate the diagnostic and prognostic accuracy of Tempus's pathology foundation models. The ability to extract deep biological insights from standard slides reduces the need for additional complex assays.

Tempus acquired Deep 6 AI in March 2025, adding an AI precision research platform that mines structured and unstructured EMR data to match patients to clinical trials and generate real world evidence. Deep 6 continues to operate under its own name and reports real time EMR feeds across more than 30 health systems and an ecosystem of over 1,000 research facilities. This index records the capability inside the Tempus vendor entry rather than as a separate record, consistent with how other acquired product lines are handled.

Our read

For a health system already running Tempus Next or Hub, this quietly widens what the relationship covers: the same vendor now sits on clinical decision support, prior authorization, and trial recruitment, all reading the same EMR. That consolidation is convenient and worth scrutinizing, since the data access granted for one purpose now serves several. The technically interesting claim is about unstructured data: Deep 6 reports that 92 percent of trial inclusion and exclusion criteria benefit from unstructured sources and that 15 to 20 percent of eligible patients are found through free text alone, which is the actual argument for NLP based matching over coded data queries. Two things to establish: that data ownership remains with the health system rather than transferring with the platform, and that matched cohorts are treated as decision support requiring validation, which the company itself states.