Let Navya take the complexity out of treatment decision making.
Navya uses computational solutions to empower physicians and provide them with the resources to assist patients that face complex medical decisions. Here are the resources that we offer to help physicians help others.
Physicians can use the power of Navya’s clinical informatics system to find the most applicable treatments for each patient. In addition to our Expert Opinion Service, which physicians can use on behalf of patients to consult their colleagues at tertiary care centers, Navya offers two physician specific tools that allow them to interface with our experience and evidence engines directly.
This page describes how our evidence and experience engines help physicians, and details the two unique tools designed for physicians, ExpertApp and Alpha.
Navya’s Evidence Engine makes it easy for doctors to connect with the information they need for a case, by indexing medical evidence from clinical research articles that can be searched by individual patient data. Because of our focus on oncology solutions, our database offers a highly structured index of papers relevant to treatment assessments. Our database is regularly updated with the latest medical findings, keeping doctors up to date with the treatments relevant to each patient’s case. Due to the power of Navya’s machine learning algorithms, treatment applicability analyses can be performed for each query, to rank the applicability of treatments to a patient’s case. Navya’s Evidence Engine enables a comprehensive and dynamic search for evidence relevant to a particular patient’s case.
Keyword searches for medical information or on PubMed/MEDLINE are time consuming, and don’t provide patient-specific results. Each paper must be read to fully understand its results and their applicability to the patient, if any. Navya’s experience engine saves physicians critical time by connecting them to the information they need to recommend the most applicable treatment.
Navya’s Experience Engine allows the clinical informatics system to make treatment decisions for patients for whom there are no clinical trials. The Experience Engine indexes thousands of previously treated patients’ treatment pathways, decisions, and outcomes. It models decisions based on a patients’ similarity to the cluster of patients that have similar diagnoses and have already received treatment. The Experience Engine allows Navya to make inferences and predict tumor board decisions for patients with complex or unique cases not represented adequately in literature.
The Navya ExpertApp is an internal software application which collects treatment recommendations from a group of medical experts and builds a single consensus opinion. The ExpertApp uses templates to summarize the medical case of a patient in a highly structured format, and presents guideline based treatment options, generated by Navya’s clinical informatics system, for experts to choose from. When combining opinions, the ExpertApp uses preset weights for each expert, based on specialization, experience, and expertise, and uses reconciliation algorithms to build a consensus opinion. Based on the final result of this process, Navya prepares a comprehensive report for the patient, which includes the case summary, opinion of each of the experts, and the consensus treatment recommendation.
The objective of the ExpertApp is to enable quick, asynchronous, virtual collaboration between an interdisciplinary group of experts to quickly arrive at a single treatment recommendation for a patient. Hospitals and physicians can use the Navya ExpertApp to solve referral patient cases that are routinely sent to them.
A physician can enter the patient’s medical case directly into Alpha. At the click of a button, Alpha uses Navya’s Evidence and Experience Engines to search Navya’s database and return an ordered list of treatments. It works by structuring the patient’s case into Navya’s ontology, and matching the patient’s information with diagnostic criteria and trials. The treatments are ranked by quality of trial, strength of endpoints, sample size, effect size, match of the patient with demographic data, among other factors.