Biomarkers in Combination with Other Prognostic and Predictive Factors –Individualized Multivariate Statistical Models for Risk and Probability Estimation in Oncology.Implementation into software BIANTA and CRACTES with Some Casuistics.

. Biomarkers in Combination with Other Prognostic and Predictive Factors –Individualized Multivariate Statistical Models for Risk and Probability Estimation in Oncology.Implementation into software BIANTA and CRACTES with Some Casuistics. Biomed J Sci & Tech Res 28(4)- 2020. BJSTR. MS.ID.004676.

to choose appropriate preventive and therapeutic interventions for each patient. A case-control study in the Czech Republic with a similar design to that of the US Breast Cancer Detection and Demonstration Project (BCDDP) [1].
The main objective of this study was to evaluate the validity of the Gail model in the Czech female population, and to develop a local model using the same statistical approach as the Gail model.
Number of 14566 questionnaires containing case history data from both healthy women (control group) and women with breast cancer were collected. Case-control age-matched pairs (n = 4598) have subsequently been matched and analyzed. The original Gail model was also not able to properly describe age-specific baseline risk of breast cancer development in the Czech population. In response the authors developed two variants of modified/locally adjusted models [2]. Now model for 5-years or lifetime risk of developing of breast cancer is developed for a healthy female. This breast cancer risk development model created by author is available at web page http://calc.koc.cz/pro_lekare/vypocet_rizika_nadoru_prsu.html Most biomarkers have increased serum concentrations in multiple tumor diagnoses, or markers may be increased also for many non- and future possibilities to update or extend any of them without disabling the others. Usage of Java technology enables the software to run on every platform and therefore targets wider audience.

Software BIANTA
Software BIANTA is used to help in the interpretation of tumor markers in cases where there is a strong suspicion of cancer, event. Clinical validation of BIANTA software showed that of the cases initially diagnosed as C80 "malignant neoplasm without known location", BIANTA was able to determine the correct diagnosis at one of the first 3 places in 95% in validation data of 93 real C80 causes from the Masaryk´s Memorial Cancer Institute Brno. When compared with 6 physicians from Faculty hospital Pilsen who did not know these patients and had the same input information as the program BIANTA, only one physician was better than BIANTA software. One casuistic of BIANTA is presented at the Table 1.  This was overlooked in previously done imaging methods. The patient was cured and surviving until now.

Software CRACTES
Software CRACTES is the decision support software for tumor markers interpretation during the cancer patient´s follow-up and for the therapy evaluation. The main task which the programme helps to sort out, is early diagnostics of the recurrence of tumor illness and its most probable location. The examination of markers may be a warning signal, but thanks to not specific reactions it also may be a false alarm; this reminds of an association with a jay bird which signals an enemy but has to be taken with a pinch of salt to a certain extent. After reaching the clinical status of full remission the patient is usually invited to be checked up in 1-4 months´ intervals (according to time elapsed since the treatment of primary tumor).
It is desirable to identify the metastatic process earlier than it is manifested clinically. The system helps to answer the following  Table 2.  on every platform and therefore targets a wider audience [4]. It is created as a cloud-based application (see http://almadiagnostics. com).

Conclusion
These decision support software BIANTA and CRACTES which are based on non-linear multivariate approach taking into account time dynamic of the repeatedly measured tumor markers could help to clinician as it is provided by clinical validations presented above.
These validations showed that the software BIANTA and CRACTES are better compare to "normal clinician" (with no or medium experiences with tumor markers) and about the same as real clinical experts working long time in interpreting of tumor markers.
Both these software is being successfully used at a number of hospitals and laboratories in the Czech Republic. BIANTA Software will guide clinician to 3-4 most probable locations of a tumor. This will affect other examinations, especially to which locations to focus by imaging methods. This is a clear example of personalized medicine. CRACTES software personalizes intervals during follow up of cancer patients and also recommends (if risk of recurrence is increased) additive examinations (laboratory and/or imaging methods). Module of CRACTES software for predicting response of anticancer therapy was also developed for ovarian cancer [5].
Authors are planning to integrate population epidemiological data from other countries to make the program applicable and usable outside of the Czech Republic.