US 12,217,851 B2
Identification of candidate signs indicative of an NTRK oncogenic fusion
Arndt Schmitz, Berlin (DE); Eren Metin Elci, Bensheim (DE); Faidra Stavropoulou, Berlin (DE); Mikhail Kachala, Cologne (DE); Antti Karlsson, Parainen (FI); and Mikko Tukiainen, Kaarina (FI)
Appl. No. 17/595,191
Filed by Bayer Consumer Care AG, Basel (CH)
PCT Filed Apr. 28, 2020, PCT No. PCT/EP2020/061665
§ 371(c)(1), (2) Date Nov. 10, 2021,
PCT Pub. No. WO2020/229152, PCT Pub. Date Nov. 19, 2020.
Claims priority of application No. 19173832 (EP), filed on May 10, 2019.
Prior Publication US 2022/0223261 A1, Jul. 14, 2022
Int. Cl. G06T 7/00 (2017.01); G06N 3/04 (2023.01); G06V 20/69 (2022.01); G16H 10/40 (2018.01); G16H 10/60 (2018.01); G16H 30/40 (2018.01); G16H 50/20 (2018.01)
CPC G16H 30/40 (2018.01) [G06N 3/04 (2013.01); G06T 7/0012 (2013.01); G06V 20/698 (2022.01); G16H 10/40 (2018.01); G16H 10/60 (2018.01); G16H 50/20 (2018.01); G06T 2207/30004 (2013.01)] 3 Claims
OG exemplary drawing
 
1. A computer-implemented method for identifying one or more candidate signs indicative of an NTRK oncogenic fusion within patient data associated with a subject patient, the method comprising:
receiving historical patient data for which one or more candidate signs indicative of an NTRK oncogenic fusion have been verified or excluded, the historical patient data comprising a plurality of histopathological images of tumor tissue;
training a prediction model via machine learning to predict a probability of cancer caused by the NTRK oncogenic fusion for each histological image of the plurality of histopathological images, thereby obtaining a trained prediction model;
receiving patient data of a subject patient suffering from cancer, the patient data comprising at least one histopathological image of tumor tissue of the subject patient;
inputting the patient data into the trained prediction model, the trained prediction model being configured for identifying within the patient data one or more characteristics of an NTRK oncogenic fusion;
receiving as an output from the trained prediction model a probability value, the probability value indicating the probability of the subject patient suffering from cancer caused by an NTRK oncogenic fusion;
comparing the probability value with a predefined threshold value; and
in the event that the probability value is equal to or greater than the threshold value: initiating further investigations for verification of the indication that the subject patient suffers from cancer caused by an NTRK oncogenic fusion.