We are molecular biologists, data scientists, and digital health engineers, teaching AI to find personalized medicine evidence as we are helping patients and their healthcare team find optimized treatment options. We specialize in personalized medicine, combining and analysing information about the patient’s genome and phenome with his clinical history, mapping it to current scientific and real-world evidence available worldwide, aiming to predict how his body will respond to specific healthcare interventions. We utilize translational bioinformatics algorithms to build knowledge from large corpus of data, thus leveraging technology to augment the cognitive capacity of the healthcare team.

We bring complementary, highly specialised knowledge to the healthcare team, presenting all available treatment options with their rationale, risks, expected outcomes, and practical information, to aid the clinical decision.

EBM’s purpose is to provide healthcare professionals, patients and those close to them with up-to-date and scientifically proven information on the various medical options that are available to them. It uses special methods that have been developed to find the highest quality evidence for the benefits of a specific medical intervention. The main aim is always to find out what kind of care is most suitable for a particular patient – and how to incorporate their individual preferences and circumstances into the treatment decision.

Standard approaches to medicine work and have stood the test of time, but technology and science are always advancing. Sometimes it is best to continue to learn and change to make things better, which is what evidence-based practice supports.

Research + Clinical Expertise + Patient Preference = Evidence-Based Practice (EBP).

Vitae Evidence web application supports the following steps in the application of Evidence-Based Medicine:

1. problem definition: each case is associated to a set of search strategies / PICO questions.
2. search for wanted sources of information: identification of references from selected information sources of type: Scientific publications, Pre-prints, Knowledge Bases, Trial Registries, Medicine Agencies, Medical News Feeds, Previous Cases
3. critical evaluation of the information: Rating of the quality of evidence and relevance to the PICO question being evaluated.
4. application of information of the patient: Inclusion/Exclusion rules based on patient medical history, molecular profile and preferences and practicalities.
5. efficacy evaluation of this application on a patient: Insights report according to Clinical Decision Support and Decision Aids best practices, strength of recommendation for the individual patient.

PICO is a search framework commonly used in the health sciences, and especially in Evidence-Based Medicine, to frame and answer a clinical or health care related question. The PICO framework is also used to develop literature search strategies, for instance in systematic reviews. The acronym stands for:

• Population/Patient/Problem
• Intervention
• Comparator/Control
• Outcome(s) of interest

The "P" contains information extracted from the patient summary, including demographic, condition and comorbidities, already tested biomarkers, and current and past treatments

Patient and clinicians preferences are used to generate searches for specific types of interventions or outcomes.

Vitae Evidence's algorithms annotate large corpus of medical articles, medical news and clinical trials with the Patient population enrolled, the Interventions studied and to what they were Compared, and the Outcomes measured. This makes the references "machine-readable".

Patient summaries, translated into a set of PICO questions, can then be answered by aggregating the results from the references that match these PICO annotations.

Routinely collected health data (real-world data) on a broad range of patients reflect the true diversity of persons with a condition and not only those who volunteer for clinical trials or biobanks. Those data also represent outcomes in real-time, where the patient live, work, eat and play, therefore more likely to represent the truth (compared with data collected at the doctor office, with intervals of several weeks or months, where, in addition to missing data points, the patient’s recollection of events will likely be biased). In addition, as precision medicine is about leveraging patient-specific information to improve treatment strategies, it is challenged by the small patient size (individuals or small groups). Finally, a description of long-term outcomes necessitates longitudinal datasets going over decades, not possible in the context of clinical trials.

Real-world evidence (RWE) provides estimates of absolute event probabilities and costs in patients in actual clinical practice, particularly valuable for informing healthcare policymakers when formulating appropriate treatment pathways, encouraging the optimal allocation of scarce resources, and improving aggregate patient outcomes . There is growing interest globally in using real-world evidence (RWE) for health technology assessment (HTA), and agencies are establishing frameworks to standardize processes and ensure consistency.

Vitae Evidence, by aggregating and analyzing the real-world data collected against scientific evidence from robust studies, turns real-word data (RWD) into real-world evidence (RWE) and by using clinical decision support and patient decision aids best practices, turns it further into real-world actionable insights for clinicians and their patients. Real-world actionable insights are what matters to clinicians and patients. This is Vitae Evidence’s reason for being.

The utilization of AI in Healthcare leads to ethical considerations such as the possible impact of AI systems on people’s rights to privacy, non-discrimination, unbiased decision-making . A system that is continuously learning is also potentially providing different answers throughout its lifecycle. Models for continuously validating and verifying algorithms used in Healthcare is a necessity. The impact of an AI system must be monitored continuously and throughout the system's lifecycle. Coremine Vitae incorporates impact monitoring in its design.

Remote monitoring is going to be more and more present in clinical trials, to reduce trial costs, accelerate clinical trial timelines, reduce study start-up, and advance cures. Virtual Trials and Decentralized trials.

Implementation of Remote Patient Monitoring (RPM, “avstandsoppfølging” in Norwegian ) is also growing through the implementation of national or regional welfare technology hubs, for improved chronic condition management, reduced hospital readmission, reduced burden on healthcare systems, improved patient outcomes and increased patient education.

Coremine Vitae makes use of a Collaboration and Remote Monitoring platform. It is about leveraging the technology of our times to bring healthcare and prevention where people live, work, eat and play. Before, we were limited to the consultation room and punctual consultation time. Now, we can discuss choice of therapy based on continuous real-world data. The program is semi-automated based on the collected data from clinical assessments and patient actions, and alerts the multidisciplinary team as needed. It is about clinical outcomes, healthcare staff time optimization and cost effectiveness.

We built our collaboration and remote monitoring platform on CheckWare, with the following functions:

• Electronic informed consent
• Secure collection of medical records, NGS lab results, priorities, and preferences
• Contextual delivery of educational content
• Patient and Clinician Reported Outcomes and Experiences collected at pre-defined measurement points, data analysis and reporting.
• Case triage
• Secure messaging and closed discussion groups