KR102594143B1 - A method and System for sorting group being predicted to have remarkable anticancer treatment response using CA-125 before and after the first neoadjuvant chemotherapy, and for predicting whether interval debulking surgery in the sorted group - Google Patents

Abstract

The present invention relates to a method and system for selecting a group predicted to have an excellent anticancer response prognosis using CA-125 before and after first-line neoadjuvant chemotherapy, and predicting whether to omit interval debulking surgery for the selected group. .

Description

A method and system for selecting clusters predicted to have an excellent anticancer response prognosis using CA-125 before and after first-line neoadjuvant chemotherapy, and predicting whether to omit interval debulking surgery in the selected cluster {A method and System for sorting group being predicted to have remarkable anticancer treatment response using CA-125 before and after the first neoadjuvant chemotherapy, and for predicting whether interval debulking surgery in the sorted group}

The present invention relates to a method and system for selecting a group predicted to have an excellent anticancer response prognosis using CA-125 before and after first-line neoadjuvant chemotherapy, and predicting whether to omit interval debulking surgery for the selected group. .

Recently, in several large-scale clinical trials, PDS/AC, which involves primary debulking surgery (PDS) followed by adjuvant chemotherapy (AC), as the first treatment for advanced ovarian cancer, and neoadjuvant chemotherapy. There is no difference in treatment effect between NACT/IDS (neoadjuvant chemotherapy (NACT)) and interval debulking surgery (IDS), and when neoadjuvant chemotherapy is performed, surgery-related complications are low and life expectancy is low. There is little decline in quality, so clinical application is increasing.

However, there is controversy over the effectiveness of performing interval debulking surgery for patients who responded well after neoadjuvant chemotherapy and achieved complete pathological remission, and the chemotherapy response score for the tissue after surgery is controversial. It is known that a score of 3 has a good prognosis, but the effect of the surgery itself on the prognosis has not been known so far.

Recently, a model for predicting anticancer response and prognosis using the CA-125 Elimination Constant K (KELIM) score has been reported for patients with advanced ovarian cancer. In particular, it is reported to be superior in predicting the prognosis of ovarian cancer compared to other tests based on cross-sectional or longitudinal evaluation of cancer tissue that have been recently studied.

Meanwhile, neoadjuvant chemotherapy is administered multiple times to patients with advanced ovarian cancer. The first neoadjuvant chemotherapy administered is referred to as first neoadjuvant chemotherapy. The present inventors predicted that the prognosis for anticancer response would be excellent using the KELIM score, which is calculated using CA-125 levels before and after the first neoadjuvant chemotherapy. We have developed a method and system to select predicted clusters and further predict whether interval tumor reduction surgery will be omitted in the selected cluster.
(Patent Document 1) Public Patent Publication No. 10-2021-0137828 (2011.11.18.)
(Patent Document 2) Public Patent Publication No. 10-2019-0009166 (2019.01.28.)

The present invention was created to solve the above problems.

Specifically, by using only the information measured before and after the first neoadjuvant chemotherapy for patients with advanced ovarian cancer, the patient's chemotherapy prognosis or whether interval tumor reduction surgery should be omitted is determined and provided to help medical staff establish future treatment plans. The purpose is to provide a method and system that can provide effective anti-cancer treatment by providing information that can provide this information and eliminate unnecessary surgeries that are burdensome to the patient's body.

In addition, the purpose is to provide a method and system that can predict and provide progression-free survival rate or overall survival rate by utilizing additional information to the information measured before and after the first neoadjuvant chemotherapy for patients with advanced ovarian cancer.

In addition, a prediction model is created with higher accuracy by using machine learning or deep learning on the learning data using additional information as input to the information measured before and after the first neoadjuvant chemotherapy for advanced ovarian cancer patients and survival rate as output. The purpose is to provide a method and system that can predict patient survival rate.

One embodiment of the present invention to solve the above problem is to provide an input device with 1) the first CA-125 (cancer antigen 125) level measured from the measurement subject at the time of diagnosis of advanced ovarian cancer, 2) The second CA-125 level measured from the measurement subject at a time after the first neoadjuvant chemotherapy was administered to the measurement subject, 3) the first date information at the time of measuring the first CA-125 level, 4) A step of inputting second date information at the time of administering the first neoadjuvant chemotherapy, and 5) third date information at the time of measuring the second CA-125 level, where the processor inputs the first CA-125 level and the first CA-125 level. 2 Calculating a KLEIM score using the CA-125 value and the first to third date information, wherein the processor selects a measurement object for which a KELIM score greater than a preset score has been calculated as the first cluster, A step of classifying a measurement object for which a small KELIM score has been calculated into a second cluster, wherein first information is mapped to the first cluster and second information is mapped to the second cluster, the step and output device comprising: A step of outputting first information or second information in which the measurement target is mapped together into a classified cluster, wherein the first information includes excellent prognosis for neoadjuvant chemotherapy or possibility of skipping interval debulking surgery, The second information provides a method of predicting whether to omit interval cytoreduction surgery for patients with advanced ovarian cancer, including poor prognosis of neoadjuvant chemotherapy or inability to omit interval cytoreduction surgery.

Another embodiment of the present invention includes, in an input device, 1) a first CA-125 (cancer antigen 125) level measured from the measurement subject at the time of diagnosis of advanced ovarian cancer in the measurement subject, 2) a first CA-125 (cancer antigen 125) level for the measurement subject; The second CA-125 level measured from the measurement subject at the time after the administration of neoadjuvant chemotherapy, 3) the first date information at the time of measuring the first CA-125 level, 4) the administration of the first neoadjuvant chemotherapy 2nd date information at the time, and 5) 3rd date information at the time of measuring the second CA-125 level, 6) age of the measurement subject, 7) number of times neoadjuvant chemotherapy was administered to the measurement subject, 8) the advanced ovarian cancer stage of the measurement target, 9) evaluation of response to prior chemotherapy for the measurement target, and 10) whether or not to perform interval tumor reduction surgery on the measurement target, as steps 6) to 10) above. A step in which evaluation scores according to input values are mapped, and a processor calculates a KELIM score using the input values 1) to 5) using a preset method, where the processor calculates a KELIM score using the input values 6) to 10). Calculating a summed evaluation score by summing the evaluation scores mapped according to input values and the evaluation score calculated using the KELIM score, and the processor using the summed evaluation score to determine the measurement target. Provided is a method for predicting the survival rate of patients with advanced ovarian cancer, including calculating the survival rate.

In one embodiment, the evaluation score according to the input values 6) to 10) and the evaluation score according to the KELIM score are mapped to different evaluation scores depending on whether the calculated KELIM score is greater or less than a preset score. Different evaluation scores are mapped depending on whether the patient is under 60 years old or over 60 years old, different evaluation scores are mapped according to whether the number of neoadjuvant chemotherapy treatments has been 6 or more or less than 6 times, and advanced ovarian cancer. Different evaluation scores are mapped depending on whether the stage is ⅢC or Ⅳ, and when the neoadjuvant chemotherapy response evaluation is Complete Remission (CR), Partial Remission (PR), or advanced disease ( Different evaluation scores may be mapped depending on whether it is Progressive Disease (PD) or Stable Disease (SD), and different evaluation scores may be mapped depending on whether interval tumor reduction surgery is performed.

In one embodiment, the evaluation score according to the input values 6) to 10) and the evaluation score according to the KELIM score are, when the calculated KELIM score is greater than the preset score, the calculated KELIM score is the preset score. A lower evaluation score is mapped if the score is less than the score, if the age is less than 60 years old, a lower evaluation score is mapped than if the age is more than 60 years, and if the number of neoadjuvant chemotherapy treatments is 6 or more, neoadjuvant chemotherapy is performed. A lower evaluation score is mapped than when the number of times is less than 6, when the advanced ovarian cancer stage is ⅢC, a lower evaluation score is mapped than when the advanced ovarian cancer stage is Ⅳ, and when the prior chemotherapy response evaluation is partial response. , an evaluation score that is higher than in the case of complete response and lower than in the case of advanced or safe lesions may be mapped, and if interval tumor reduction surgery was performed, a lower evaluation score may be mapped than in the case where it was not performed.

In one embodiment, the evaluation score according to the input values 6) to 10) and the KELIM score are 7.5 points when a KELIM score smaller than the preset score is calculated based on 100 points, If a KELIM score greater than the preset score is calculated, 0 points, 6) 0 points if the age is less than 60 years, 2.5 points if the age is more than 60 years, 7) 0 points if the number of neoadjuvant chemotherapy treatments is 6 or more, 7.5 points for less than 6 treatments, 8) 0 points for advanced ovarian cancer stage ⅢC, 11.25 points for Ⅳ, 9) 0 points for partial response if response evaluation to prior chemotherapy is Complete Remission (CR) (Partial Remission, PR) 17.5 points, Progressive Disease (PD) or Stable Disease (SD) 100 points, 10) If interval tumor reduction surgery was performed, 0 points, if not performed 11.25 points may each be mapped.

In one embodiment, the survival rate of the measurement target calculated using the summed evaluation score may be progression-free survival.

In one embodiment, the survival rate of the measurement object calculated using the summed evaluation score may be a 6-month progression-free survival rate, a 12-month progression-free survival rate, or a 24-month progression-free survival rate.

In one embodiment, the higher the summed evaluation score, the lower the progression-free survival rate may be predicted.

In one embodiment, the evaluation score according to the input values 6) to 10) and the KELIM score are 2.5 points when a KELIM score smaller than the preset score is calculated based on 100 points, If a KELIM score greater than the preset score is calculated, 0 points, 6) 0 points if the age is less than 60 years, 7.5 points if the age is more than 60 years, 7) 0 points if the number of neoadjuvant chemotherapy treatments is 6 or more times, 6.25 points for less than 6 treatments, 8) 0 points for advanced ovarian cancer stage ⅢC, 8.75 points for Ⅳ, 9) 0 points for partial response if response evaluation to prior chemotherapy is Complete Remission (CR) (30 points for Partial Remission, PR), 100 points for Progressive Disease (PD) or Stable Disease (SD), 10) 0 points if interval tumor reduction surgery was performed, 0 points if not performed. 11.25 points may each be mapped.

In one embodiment, the survival rate of the measurement target calculated using the summed evaluation score may be the overall survival rate.

In one embodiment, the survival rate of the measurement target calculated using the summed evaluation score may be a 24-month overall survival rate.

In one embodiment, the higher the summed evaluation score, the lower the overall survival rate may be predicted.

In another embodiment of the present invention, the processor, 1) a first CA-125 (cancer antigen 125) level measured from a random individual at the time of diagnosis of advanced ovarian cancer, 2) first neoadjuvant chemotherapy for the random individual The second CA-125 level measured from the subject at a time after the administration of therapy, 3) the first date information at the time of measuring the first CA-125 level, 4) the second at the time of administration of the first neoadjuvant chemotherapy date information, and 5) calculating a KELIM score using a preset method using third date information at the time of measuring the second CA-125 value, wherein the processor calculates the calculated KELIM score - the random entity Age - Number of times neoadjuvant chemotherapy was administered to the random subject - Advanced ovarian cancer stage of the random subject - Evaluation of response to neoadjuvant chemotherapy for the random subject - Interval debulking surgery performed on the random subject Whether - a step of generating learning data consisting of pairs of survival rates and the processor, KELIM score, age, number of times neoadjuvant chemotherapy was administered, advanced ovarian cancer stage, neoadjuvant chemotherapy response evaluation, and interval tumor reduction Provides a method for predicting the survival rate of patients with advanced ovarian cancer, including the step of generating a prediction model through machine learning or deep learning using whether surgery was performed as an input element and the survival rate as an output element.

In one embodiment, the survival rate may be progression-free survival rate or overall survival rate.

In one embodiment, in the learning process by the processor, when the calculated KELIM score is greater than the preset score, a lower weight is given than when the calculated KELIM score is less than the preset score, and the age is less than 60 years. In this case, a lower weight is given than if the age is 60 years or older, if the number of neoadjuvant chemotherapy treatments is 6 or more times, a lower weight is given than if the number of neoadjuvant chemotherapy treatments is less than 6 times, and if the advanced ovarian cancer stage is In the case of ⅢC, a lower weight is given than in the case of advanced ovarian cancer stage Ⅳ, and if the response evaluation of prior chemotherapy is a partial response, a higher weight is given than in the case of a complete response and a lower weight is given than in the case of an advanced lesion or a safe lesion. , if interval tumor reduction surgery was performed, a lower weight may be assigned than if it was not performed.

In addition, one embodiment of the present invention provides a survival rate prediction system for patients with advanced ovarian cancer, which performs the above-described method.

Additionally, in one embodiment of the present invention, a computer program stored on a computer-readable recording medium is provided to execute the above-described method.

The present invention as described above has the following effects.

First, by using only the information measured before and after the first neoadjuvant chemotherapy for patients with advanced ovarian cancer, the patient's chemotherapy prognosis or whether to omit interval tumor reduction surgery is judged and provided to help medical staff establish future treatment plans. It has the advantage of providing effective anti-cancer treatment by providing useful information and eliminating unnecessary surgeries that are burdensome to the patient's body.

Second, it is possible to predict the progression-free survival rate or overall survival rate by utilizing additional information in addition to the information measured before and after the first neoadjuvant chemotherapy for patients with advanced ovarian cancer.

Third, by generating a prediction model with higher accuracy by using machine learning or deep learning on the learning data with additional information as an input element and survival rate as an output element in addition to the information measured before and after the first neoadjuvant chemotherapy for patients with advanced ovarian cancer, It is possible to predict patient survival rates.

1 is a block diagram for explaining an aspect of a system according to an embodiment of the present invention.
Figure 2 is a schematic block diagram for explaining a system according to the first embodiment of the present invention.
FIG. 3 is a schematic diagram for explaining input elements used in FIG. 2.
Figure 4 is a schematic diagram to explain clusters classified according to the KELIM score calculated by the processor.
Figure 5 is a schematic block diagram for explaining systems according to the second and third embodiments of the present invention.
Figure 6 is a diagram showing an example of a nomogram for predicting progression-free survival in the system of Figure 5.
Figure 7 is a diagram showing an example of a nomogram for predicting overall survival rate in the system of Figure 5.
Figure 8 is a graph showing the progression-free survival rate and overall survival rate according to the clusters classified in Figure 4, (A) the progression-free survival rate in the first cluster, (B) the progression-free survival rate in the second cluster, and (C) the second cluster. This is a graph showing the overall survival rate in cluster 1 and (D) the overall survival rate in cluster 2. Here, CT only refers to the group in which only neoadjuvant chemotherapy was performed without interval debulking surgery, and NACT/IDS refers to the group in which neoadjuvant chemotherapy and interval debulking surgery were performed.
Figure 9 is a graph showing the survival rate according to whether optimal tumor reduction surgery was performed and whether interval tumor reduction surgery was performed, (A) progression-free survival rate in the first group, (B) progression-free survival rate in the second group, (C) ) This is a graph showing the overall survival rate in the first cluster, (D) the overall survival rate in the second cluster.

Hereinafter, the present invention will be described in detail with reference to the attached drawings.

Hereinafter, the term "advanced ovarian cancer" refers to epithelial ovarian cancer showing intra-abdominal dissemination (stage: stage III) or extra-peritoneal dissemination (stage: stage IV), and the histological type is high-grade serous ovarian cancer. (high-grade serous carcinoma).

Hereinafter, the term “adjuvant chemotherapy” refers to chemotherapy administered before interval cytoreductive surgery to remove ovarian cancer tumors in patients with advanced ovarian cancer. The neoadjuvant chemotherapy administered for the first time after diagnosis is called the first neoadjuvant chemotherapy, the neoadjuvant chemotherapy administered after the first neoadjuvant chemotherapy is called the second neoadjuvant chemotherapy, and the nth stage in chronological order (n is 3). Integer above) is called neoadjuvant chemotherapy.

Hereinafter, the term “date information” refers to information at a standard time and includes information on the date, year, month, and day. For example, in the case of October 31, 2022, the information of “2022-10-31” is a concept that can be included here.

Hereinafter, the term “age” refers to the age of the subject, and in the case of an individual aged 55, information of “55” is a concept that can be included here.

Hereinafter, the term “advanced ovarian cancer stage” includes stage I, stage II, stage III, and stage IV, and is a concept in which detailed stages are divided for each stage. For example, stage III can be further subdivided into stages IIIA, IIIB, and IIIC.

Hereinafter, the term "preemptive chemotherapy response evaluation" is a concept that scales the response evaluation after chemotherapy, and the response evaluation includes complete remission (CR), partial remission (PR), and advanced lesions. It may correspond to either Progressive Disease (PD) or Stable Disease (SD).

Hereinafter, the term “whether interval tumor reduction surgery is performed” is a concept that refers to whether interval tumor reduction surgery was performed or not performed on patients with advanced ovarian cancer.

Hereinafter, the term “progression-free survival” refers to the probability that a patient is alive with advanced ovarian cancer during or after treatment for advanced ovarian cancer, but that the advanced ovarian cancer does not get worse. In the present invention, the 6-month progression-free survival rate is the probability that advanced ovarian cancer will not worsen until 6 months after diagnosis, and the 12-month progression-free survival rate is the probability that advanced ovarian cancer will not worsen until 12 months after diagnosis. Probability, 24-month progression-free survival rate indicates the probability that advanced ovarian cancer will not worsen until 24 months after diagnosis.

Hereinafter, the term “overall survival” refers to the probability of surviving for a certain period of time after diagnosis of advanced ovarian cancer. In the present invention, the 24-month overall survival rate represents the probability of a patient with advanced ovarian cancer surviving until 24 months after diagnosis.

Hereinafter, with reference to the attached drawings, a cluster predicted to have an excellent anticancer response prognosis is selected using CA-125 before and after the first neoadjuvant chemotherapy according to an embodiment of the present invention, and interval tumor reduction of the selected cluster is performed. The method and system for predicting whether to omit alcohol will be described in detail.

Referring to Figure 1, the system according to an embodiment of the present invention includes a communication device 10, an input device 20, a memory 30, a processor 40, an output device 50, a control device 60, and a power source. It includes a supply device (70) and an interface device (80).

The communication device 10 is configured for communication with an external device, and data may be transmitted and received with the external device through the communication device 10.

The input device 20 may receive commands or data to be used by a component of the system (e.g., a processor) from outside the system (e.g., a user). The input device 20 may include, for example, a microphone, mouse, keyboard, keys (e.g., buttons), or a digital pen (e.g., stylus pen).

The memory 30 can store various data used in the system. Data stored in the memory 30 include, for example, a prediction model generated by the processor 40, which will be described later, an evaluation score mapped to each numerical range of the input element input to the input device 20, and the basis for survival rate prediction. It may be a standard summed evaluation score, learning data to be used for learning, etc., but is not particularly limited thereto, and input data or output data for software and related commands may also be stored in the memory 30.

Additionally, the memory 30 can store both information input to the system and information generated by the system.

The processor 40 may perform a data processing or calculation function, and as at least part of the data processing or calculation function, may store instructions or data received from other components in a volatile memory, and store the instructions or data stored in the volatile memory. can be processed, and the resulting data can be stored in non-volatile memory. Additionally, the processor 40 may further include a hardware structure specialized for processing artificial intelligence models.

The output device 50 can output information processed or calculated in the system to the outside, and may include a display and speaker.

The control device 60 may control one or more other components (e.g., hardware or software components) of the system connected to the processor, for example by executing software. The control device 60 controls the communication device 10, input device 20, memory 30, processor 40, output device 50, power supply device 70, and interface device 80 of the system. can do.

Power supply 70 supplies power to the system. The power supply device 70 may receive power from an external power source and supply power to the system.

The interface device 80 can display information output from the output device 50 through an interface.

At this time, the interface device 80 is not limited to a specific type or form.

A method according to an embodiment of the present invention based on the above system components will be described in detail.

First, the method according to the first embodiment of the present invention will be described in detail with reference to FIGS. 2 to 4.

The method according to the first embodiment calculates the KELIM score using the CA-125 levels measured from the individual, the date information on the first neoadjuvant chemotherapy, and the date information on which the CA-125 levels were measured. Depending on the KELIM score, the prognosis of neoadjuvant chemotherapy is predicted, or whether interval tumor reduction surgery after neoadjuvant chemotherapy is omitted.

The factors used to calculate the KELIM score are as follows.

1) First CA-125 level - CA-125 level measured from the individual before the first neoadjuvant chemotherapy

2) Second CA-125 level - CA-125 level measured from the individual at the time after the first neoadjuvant chemotherapy.

3) First date information - Date information at the time the first CA-125 value was measured

4) Second date information - Date information when the first neoadjuvant chemotherapy was performed

5) Third date information - Date information at the time the second CA-125 value was measured

CA-125 levels, which are confirmed at the time of diagnosis of advanced high-grade intestinal ovarian cancer, are known to decrease on a log-scale as chemotherapy progresses. Therefore, the CA-125 level increasing per unit time (dCA125/dt) at a specific point in the treatment period is calculated from the proliferation rate of the CA-125-expressing tumor (KPROD), tumor growth rate (BETA), and proliferation rate (EFFECT). It can be calculated as the value multiplied by the CA-125 value by the CA-125 elimination rate (see formula below). Therefore, it is possible to predict that the higher the KELIM score, which is the CA-125 clearance rate, the less CA-125 levels increase per unit time, resulting in a better response to anticancer treatment.

First, the elements 1) to 5) are input through the input device 20, and the processor 40 calculates the KELIM score according to a preset method using the input elements 1) to 5).

Meanwhile, a preset KELIM score is stored in the memory 30, and the processor 40 compares the KELIM score calculated through the elements 1) to 5) with the preset score, and divides the object into 2 according to the comparison result. It is classified into one of the three clusters.

If the KELIM score is greater than the preset KELIM score, it is classified into the first cluster, and if it is smaller than the preset KELIM score, it is classified into the second cluster.

Meanwhile, first information is pre-mapped to the first cluster, and second information is pre-mapped to the second cluster. Here, the first information includes “the prognosis of neoadjuvant chemotherapy is predicted to be excellent” or “interval tumor reduction surgery can be omitted,” and the second information includes “the prognosis of neoadjuvant chemotherapy is predicted to be poor” or “interval tumor reduction surgery is predicted to be poor.” Includes “no alcohol omission.”

In other words, in the case of the first cluster where the KELIM score is greater than the preset KELIM score, information that the prognosis of neoadjuvant chemotherapy is predicted to be excellent or information that interval tumor reduction surgery can be omitted is calculated by the processor 40, and the output device It can be output through (50).

In addition, in the case of the second cluster where the KELIM score is smaller than the preset KELIM score, information that the prognosis of neoadjuvant chemotherapy is predicted to be poor or information that interval tumor reduction surgery cannot be omitted is calculated by the processor 40, and the output device 50 ) can be output through.

In an embodiment of the present invention, the preset KELIM score may be a score corresponding to a cut off value of 0.95 in the ROC curve for predicting 12-month progression-free survival rate, but is not particularly limited thereto.

In the case of the method invention according to the first embodiment, it is possible to predict the prognosis of neoadjuvant chemotherapy of an individual diagnosed with advanced ovarian cancer or whether interval tumor reduction surgery can be omitted after neoadjuvant chemotherapy according to the KELIM score calculated by a predetermined method. This can help in establishing a future treatment plan.

Next, the method according to the second embodiment of the present invention will be described in detail with reference to FIG. 5.

While the method according to the first embodiment predicts the prognosis of neoadjuvant chemotherapy or whether interval tumor reduction surgery can be omitted using only the KELIM score, the method according to the second embodiment uses additional information along with the KELIM score to predict the There is a difference in predicting the survival rate.

For survival rate prediction, additional information used in conjunction with the KELIM score (KELIM_1 in Figures 6 and 7) is as follows.

6) Age (Age in Figures 6 and 7) - The absolute age of the subject, if born in 1980, 43 years old as of 2022

7) Number of neoadjuvant chemotherapy treatments (Chemo_cycles in Figures 6 and 7) - Number of neoadjuvant chemotherapy treatments administered to the subject, for example, 5 times, 7 times, etc.

8) Advanced ovarian cancer stage (FIGO_stage in FIGS. 6 and 7) - Advanced ovarian cancer stage held by the individual, for example, stage IIIC or stage IV.

9) Prior chemotherapy response evaluation (Final_response in Figures 6 and 7) - Complete Remission (CR), Partial Remission (PR), Progressive Disease (PD), and Stable Disease, SD) either

10) Whether to perform interval debulking surgery (Interval_devulking_surgery in Figures 6 and 7)

The memory 30 includes a first evaluation score each mapped according to the KELIM score range, a second evaluation score each mapped according to the age range, a third evaluation score each mapped according to the range of the number of times of neoadjuvant chemotherapy, and advanced ovarian cancer. The fourth evaluation score mapped to each stage, the fifth evaluation score mapped to each stage, the fifth evaluation score mapped to the response evaluation of neoadjuvant chemotherapy, and the sixth evaluation score mapped to each stage of tumor reduction are stored.

More specifically, different evaluation scores are mapped and stored depending on whether the calculated KELIM score is larger or smaller than the preset score, and different evaluation scores are mapped and stored depending on whether the user is under 60 years old or over 60 years old. Different evaluation scores are mapped and stored depending on whether the number of prior chemotherapy treatments is 6 or more or less than 6, and different evaluation scores are mapped and stored depending on whether the advanced ovarian cancer stage is ⅢC or Ⅳ. If the response evaluation for prior chemotherapy is Complete Remission (CR), Partial Remission (PR), Progressive Disease (PD), or Stable Disease (SD) Depending on the case, different evaluation scores are mapped and stored, and different evaluation scores are mapped and stored depending on whether interval tumor reduction surgery is performed.

More specifically, when the calculated KELIM score is greater than the preset score, a lower evaluation score is mapped and stored than when the calculated KELIM score is smaller than the preset score, and when the age is less than 60 years, the age is 60. A lower evaluation score is mapped and stored for those aged over 6 years, and for those with more than 6 prior chemotherapy treatments, a lower evaluation score is mapped and stored for those with advanced ovarian cancer. When the cancer stage is ⅢC, a lower evaluation score is mapped and stored than when the advanced ovarian cancer stage is Ⅳ, and when the response evaluation of prior chemotherapy is a partial response, it is higher than when the cancer stage is a complete response, and when it is an advanced or safe lesion, the evaluation score is mapped and stored. A lower evaluation score is mapped and stored than the case, and when interval tumor reduction surgery is performed, a lower evaluation score is mapped and stored than when it is not performed.

More preferably, as shown in Figure 6, based on a score out of 100, 7.5 points are mapped when a KELIM score smaller than the preset score is calculated, and 0 points are mapped when a KELIM score greater than the preset score is calculated, , 0 points are mapped if the age is less than 60 years, 2.5 points are mapped if the age is 60 years or older, 0 points are mapped if the number of neoadjuvant chemotherapy treatments is 6 or more times, and 7.5 points are mapped if the number of chemotherapy is less than 6 times, and advanced ovarian cancer is mapped. If the cancer stage is ⅢC, 0 points are mapped, and if it is Ⅳ, 11.25 points are mapped, and if the response evaluation for neoadjuvant chemotherapy is complete remission (CR), 0 points, and if it is partial remission (PR), 17.5 points are mapped. In the case of progressive disease (PD) or stable disease (SD), 100 points are mapped, 0 points are mapped if interval tumor reduction surgery is performed, and 11.25 points are mapped if it is not performed.

The processor 40 calculates a total evaluation score (Total Points in FIGS. 6 and 7) by adding up the evaluation scores mapped to the information input to the input device 20. And, it is configured to predict the survival rate of the individual using the calculated summed evaluation score.

The survival rate predicted in the method according to the second embodiment may be progression-free survival, and specifically, the 6-month progression-free survival rate (6 month Survival in Figure 6) and the 12-month progression-free survival rate (Figure 6). In , it may be 12 month Survival) or 24 month progression-free survival rate (in FIG. 6, 24 month Survival). However, it is not limited to this, and the progression-free survival rate from the time of diagnosis to a specific period can also be calculated.

The higher the calculated combined evaluation score, the lower the progression-free survival rate can be predicted. In other words, the lower the combined evaluation score, the higher the progression-free survival rate can be predicted.

Meanwhile, based on the same summed evaluation score, it can be seen in Figure 6 that the survival rate decreases at 6 months, 12 months, and 24 months.

Next, a method according to a third embodiment of the present invention will be described in detail with reference to FIGS. 5 and 7.

Predicting the survival rate of an individual is the same as the method according to the second embodiment, but in that the second embodiment is a method for predicting the progression-free survival rate, the third embodiment is predicting the overall survival rate. There is a difference, and accordingly, there is a difference in that different evaluation scores are pre-mapped and stored for each input element.

In other words, like the second embodiment, different evaluation scores are mapped and stored depending on whether the calculated KELIM score is larger or smaller than the preset score, and different evaluations are made depending on whether the age is less than 60 years or older than 60 years. Scores are mapped and stored, and different evaluation scores are mapped and stored depending on whether the number of neoadjuvant chemotherapy treatments is 6 or more or less than 6, and different evaluation scores are mapped and stored depending on whether the advanced ovarian cancer stage is ⅢC or Ⅳ. The evaluation score is mapped and stored, and the response evaluation for prior chemotherapy is Complete Remission (CR), Partial Remission (PR), Progressive Disease (PD), or Safe Lesion. Different evaluation scores are mapped and stored depending on the case of (Stable Disease, SD), and different evaluation scores are mapped and stored depending on whether interval tumor reduction surgery is performed.

More specifically, when the calculated KELIM score is greater than the preset score, a lower evaluation score is mapped and stored than when the calculated KELIM score is smaller than the preset score, and when the age is less than 60 years, the age is 60. A lower evaluation score is mapped and stored for those aged over 6 years, and for those with more than 6 prior chemotherapy treatments, a lower evaluation score is mapped and stored for those with advanced ovarian cancer. When the cancer stage is ⅢC, a lower evaluation score is mapped and stored than when the advanced ovarian cancer stage is Ⅳ, and when the response evaluation of prior chemotherapy is a partial response, it is higher than when the cancer stage is a complete response, and when it is an advanced or safe lesion, the evaluation score is mapped and stored. A lower evaluation score is mapped and stored than the case, and when interval tumor reduction surgery is performed, a lower evaluation score is mapped and stored than when it is not performed.

More preferably, as shown in FIG. 7, based on a score out of 100, 2.5 points are mapped when a KELIM score smaller than the preset score is calculated, and 0 points are mapped when a KELIM score greater than the preset score is calculated. , 0 points are mapped if the age is less than 60 years, 7.5 points are mapped if the age is 60 years or older, 0 points are mapped if the number of neoadjuvant chemotherapy treatments is 6 or more times, and 6.25 points are mapped if the number of neoadjuvant chemotherapy is less than 6 times, and advanced ovarian cancer If the cancer stage is ⅢC, 0 points are mapped, and if the cancer stage is Ⅳ, 8.75 points are mapped, and if the neoadjuvant chemotherapy response evaluation is Complete Remission (CR), 0 points, and if it is Partial Remission (PR), 30 points. In the case of progressive disease (PD) or stable disease (SD), 100 points are mapped, 0 points are mapped if interval tumor reduction surgery is performed, and 11.25 points are mapped if it is not performed.

The processor 40 calculates a combined evaluation score by adding up the evaluation scores mapped to each piece of information input to the input device 20. And, it is configured to predict the survival rate of the individual using the calculated summed evaluation score.

The survival rate predicted in the method according to the third embodiment may be overall survival, and specifically may be the 24-month overall survival rate. However, it is not limited to this, and the overall survival rate from the time of diagnosis to a specific period can also be calculated.

The higher the calculated combined evaluation score, the lower the overall survival rate can be predicted. In other words, the lower the combined evaluation score, the higher the overall survival rate can be predicted.

Next, the method according to the fourth embodiment of the present invention will be described in detail with reference to FIG. 5. The input elements/output elements used in the second and third embodiments are the same, but in the method according to the second and third embodiments, an evaluation score is pre-mapped for each input element, and the entity is evaluated through the sum of these evaluation scores. While the survival rate was predicted, the invention according to the fourth embodiment is different in that it generates a survival rate prediction model through artificial intelligence, machine learning, etc., and predicts the survival rate through the generated prediction model.

To this end, the processor 40 generates learning data consisting of pairs of elements used in the methods according to the second and third embodiments.

That is, the learning data consists of the following pairs: KELIM score - age - number of neoadjuvant chemotherapy - advanced ovarian cancer stage - neoadjuvant chemotherapy response evaluation - whether interval tumor reduction surgery was performed - survival rate, and the processor 40 is a plurality of entities. Learning data obtained from is generated and stored in the memory 30.

Additionally, the processor 40 generates a prediction model configured to predict the survival rate by learning the training data stored in the memory 30.

That is, the processor 40 creates a prediction model by learning input elements - output elements to derive correlations between input elements and output elements. In other words, the artificial neural network model uses KELIM score, age, number of neoadjuvant chemotherapy treatments, advanced ovarian cancer stage, neoadjuvant chemotherapy response evaluation, and whether interval debulking surgery was performed as input elements, and survival rate as output elements. This creates a prediction model through machine learning or deep learning.

Here, learning is a concept of deriving an optimal correlation between a plurality of data that is the subject of learning by training a plurality of learning data into a preset artificial neural network (ANN) model. Here, the artificial neural network models include Deep Neural Network (DNN), Convolutional Neural Network (CNN), Deep Convolutional Neural Network (DCNN), Recurrent Neural Network (RNN), Restricted Boltzmann Machine (RBM), Deep Belief Network (DBN), It may be a model based on SSD (Single Shot Detector) or MLP (Multi-layer Perceptron), but is not limited to this and various artificial neural network models can be applied to the present invention. In addition, in another aspect of the present invention, correlations between a plurality of data that are the subject of learning can be derived using various statistical techniques (linear regression model, random forest, lasso, ridge, elastic net, MDR, SVM, etc.) .

Similar to the second and third embodiments in the method according to the fourth embodiment of generating a prediction model by learning an artificial neural network, when the calculated KELIM score is greater than the preset score, the calculated KELIM score is greater than the preset score. If the score is less than the score, a lower weight is given, if the age is less than 60 years, a lower weight is given than if the age is more than 60 years, and if the number of neoadjuvant chemotherapy treatments is 6 or more, the number of neoadjuvant chemotherapy treatments is given. A lower weight is given than if the number of treatments is less than 6 times, if the advanced ovarian cancer stage is ⅢC, a lower weight is given than if the advanced ovarian cancer stage is Ⅳ, and if the response evaluation of prior chemotherapy is a partial response, a complete response. A prediction model can be used in which weights are given higher than those of cases, lower than those of advanced lesions or safe lesions, and lower if weights are given to cases where interval tumor reduction surgery was performed than to cases where it was not performed.

The pre-assigned weights can be modified/corrected to minimize the loss value through repeated learning of the training data later, so that a prediction model with optimal performance can be derived.

verification experiment

A validation experiment was conducted to verify whether the KELIM score used in the present invention is a valid indicator for predicting survival rate.

AUC P-value Cut-off sensitivity Specificity 0.692 0.031 0.95 0.714 0.659

Among 279 patients with advanced ovarian cancer who underwent neoadjuvant chemotherapy and showed high-grade serous histotype, data were collected on 194 patients who underwent interval cytoreduction surgery and 61 patients who did not undergo interval cytoreduction surgery. Statistical analysis was performed.

For 279 patients, KELIM scores were calculated using the first CA-125 value, second CA-125 value, first date information, second date information, and third date information.

In addition, an ROC curve was created to predict the 12-month progression-free survival rate after diagnosis of advanced ovarian cancer in 61 patients who did not undergo interval tumor reduction surgery. Based on this, the cut off value (preset score) to predict progression-free survival rate 12 months after diagnosis using the KELIM score was calculated to be 0.95. That is, based on the 0.95 cut off value of the KELIM score, cases greater than 0.95 were defined as the first cluster (high-KELIM), and cases lower than 0.95 were defined as the second cluster (low-KELIM) (see Table 1).

Chemotherapy only
(n = 61) NACT/IDS
(n = 194) P-value Age 61 (27-89) 59 (32-88) 0.098 Stage 0.221 IIIC 27 (44.3%) 69 (35.6%) IV 34 (55.7%) 125 (64.4%) Origin <0.001 Ovary 26 (42.6%) 180 (92.8%) Fallopian tubal 1 (1.6%) 2 (1.3%) Primary peritoneal 2 (3.3%) 12 (6.2%) Female genital tract 32 (52.5%) 0 Total cycles of chemotherapy 6 (3-10) 8 (4-15) 0.002 NACT cycles (number of neoadjuvant chemotherapy treatments) - 3 (2-9) KELIM ^* 0.286 High (>0.95) ^** 25 (41%) 65 (33.5%) Low (<0.95) ^** 36 (59.0%) 129 (66.5%) Pathologic CR - 22 (11.8%) Pathologic tumor <1cm - 63 (23.5%)

There was no difference in age, tumor origin, and total number of neoadjuvant chemotherapy treatments among the 279 patients with or without interval cytoreduction surgery, and among patients who received neoadjuvant chemotherapy without interval cytoreduction surgery, the first cluster (high- KELIM) was confirmed to be 41%, and among patients who underwent neoadjuvant chemotherapy and interval debulking surgery, the first cluster was confirmed to be 33.5% (see Table 2).

High KELIM (>0.95; N=90) Low KELIM
(<0.95; n=165) P-value Surgical outcome 0.035 R0/R1 63 (70%) 108 (65.5%) R2 2 (2.2%) 21 (12.7%) CT only (no surgery) 25 (27.8%) 36 (21.8%) Radiologic response 0.183 CR 83 (80.6%) 126 (71.6%) PR 17 (16.5%) 38 (21.6%) SD/PD 3 (2.9%) 12 (6.8%) Chemotherapy cycles
(median, min-max) 6 (3-13) 6 (3-15) 0.463

When analyzing the surgical and treatment response evaluation of the first cluster (high-KELIM) and the second cluster (low-KELIM), there was no difference in the number of patients who reached RO/R1 with a residual tumor size of less than 1 cm between the two groups. In the clinical evaluation, 80.6% and 71.6% of patients achieved complete response in each group, so no difference between the two groups could be identified. It was confirmed that there was no difference in the number of neoadjuvant chemotherapy treatments between the two groups (see Table 3).

Referring to Figure 8, when the survival rate analysis was performed according to whether or not interval tumor reduction surgery was performed in each cluster, the first and second clusters, in the first cluster, the group that did not undergo interval tumor reduction surgery and the group that underwent neoadjuvant chemotherapy and There was no difference in progression-free survival and overall survival in the group that underwent interval debulking surgery. On the other hand, in the second cluster, it was confirmed that patients who underwent neoadjuvant chemotherapy and interval debulking surgery showed a significantly higher survival rate.

Referring to Figure 9, patients who underwent optimal cytoreduction surgery (RO/R1), patients with residual tumors greater than 2 cm after interval tumor reduction surgery (R2), and patients who did not undergo interval tumor reduction surgery (CT only) When comparing survival rates, in the first group, both the progression-free survival rate and overall survival rate were superior when optimal tumor reduction surgery was performed, but in the second group, there was no difference in survival rate depending on whether or not there was interval tumor reduction surgery or optimal tumor reduction surgery. was able to confirm.

Low KELIM; < 0.95 High KELIM; > 0.95 Progression-free survival Overall survival Progression-free survival Overall survival HR (95% CI) P-value HR (95% CI) P-value HR (95% CI) P-value HR (95% CI) P-value Age > 60 0.856 (0.612-1.198) 0.365 0.909 (0.587-1.407) 0.669 1.479 (0.912-2.397) 0.112 2.293 (1.234-4.262) 0.009 Total chemo cycle > 6 0.584 (0.413-0.827) 0.002 0.536 (0.340-0.846) 0.007 1.205 (0.726-2.0) 0.472 1.030 (0.551-1.924) 0.926 Stage IV 1.107 (0.767-1.596) 0.587 1.01 (0.628-1.625) 0.967 1.864 (1.126-3.085) 0.015 1.203 (0.661-2.188) 0.545 R2 resection 1.540 (0.918-2.585) 0.102 2.094 (1.165-3.764) 0.014 3.83 (0.865-16.955) 0.077 13.82 (2.657-71.887) 0.002 Chemotherapy only 2.642 (1.768-3.949) <0.001 2.293 (1.234-4.262) <0.001 1.431 (0.850-2.410) 0.177 0.851 (0.437-1.655) 0.634

Accordingly, when a multivariate analysis model was performed based on multiple variables such as age, number of neoadjuvant chemotherapy treatments, stage, residual tumor after surgery, and whether interval tumor reduction surgery was performed, interval tumor reduction surgery was performed only in the first cluster. It was confirmed that there was a significantly good prognosis and correlation (see Table 4).

Low KELIM; < 0.95 High KELIM; > 0.95 Progression-free survival Overall survival Progression-free survival Overall survival HR (95% CI) P-value HR (95% CI) P-value HR (95% CI) P-value HR (95% CI) P-value Age > 60 0.865 (0.618-1.211) 0.398 0.905 (0.583-1.404) 0.656 1.73 (1.051-2.848) 0.031 2.512 (1.33-4.744) 0.005 Total chemo cycle > 6 0.564 (0.400-0.796) 0.001 0.688 (0.460-1.10) 0.118 1.329 (0.791-2.232) 0.282 1.245 (0.657-2.364) 0.502 Stage IV 1.070 (0.744-1.538) 0.716 1.159 (0.727-1.845) 0.535 2.422 (1.412-4.155) 0.001 1.611 (0.841-3.087) 0.151 Radiologic CR 0.019 (0.007-0.048) <0.001 0.106 (0.048-0.235) <0.001 0.042 (0.011-0.16) <0.001 0.022 (0.005-0.102) <0.001 Radiologic PR 0.036 (0.015-0.088) <0.001 0.203 (0.088-0.468) <0.001 0.12 (0.03-0.481) 0.003 0.060 (0.012-0.3) 0.001 CT only 1.467 (0.911-2.360) 0.115 1.933 (1.33-4.744) 0.016 1.214 (0.703-2.098) 0.486 0.739 (0.371-1.473) 0.390

In the case of [Table 4], since the tumor response evaluation in patients who did not undergo interval debulking surgery was not reflected, a multivariate analysis was performed as shown in [Table 5], including the radiological treatment response evaluation as a variable. It was confirmed that not performing interval tumor reduction surgery did not lower the survival rate in the first group, and that performing interval tumor reduction surgery significantly improved the survival rate in the second group.

All or at least part of the configuration of the system according to an embodiment of the present invention may be implemented in the form of a hardware module or a software module, or may be implemented in a combination of a hardware module and a software module.

Here, a software module can be understood as, for example, instructions executed by a processor that controls operations within the system, and these instructions may be mounted on memory within the system.

The method according to an embodiment of the present invention described above may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., singly or in combination. Program instructions recorded on the medium may be specially designed and constructed for the present invention or may be known and usable by those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. -Includes optical media (magneto-optical media) and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, etc. Examples of program instructions include machine language code, such as that produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to carry out the operations of the present invention, and vice versa.

Above, the present invention has been described with reference to the embodiments shown in the drawings so that those skilled in the art can easily understand and reproduce the present invention, but these are merely illustrative examples, and various modifications and equivalent alternatives can be made by those skilled in the art from the embodiments of the present application. It will be appreciated that embodiments are possible. Therefore, the scope of protection of this application should be determined by the claims.

10: Communication device
20: input device
30: Memory
40: processor
50: output device
60: control device
70: power supply
80: interface device

Claims (17)

In the input device, 1) the first CA-125 (cancer antigen 125) level measured from the measurement subject at the time of diagnosis of advanced ovarian cancer, 2) at the time after the first neoadjuvant chemotherapy was administered to the measurement subject The second CA-125 level measured from the measurement subject, 3) the first date information at the time of measuring the first CA-125 level, 4) the second date information at the time of the first neoadjuvant chemotherapy, and 5 ) Entering third date information at the time of measuring the second CA-125 level;
A processor calculating a KLEIM score using the first CA-125 value, the second CA-125 value, and the first to third date information;
A step in which the processor classifies measurement objects for which a KELIM score greater than a preset score has been calculated into a first cluster, and measurement objects for which a score less than a preset score has been calculated into a second cluster, wherein the first cluster includes a first cluster. information is mapped, and second information is mapped to the second cluster; and
A step of outputting, by an output device, first information or second information mapped together to a cluster in which the measurement target is classified,
The first information includes information that the prognosis of neoadjuvant chemotherapy is excellent and that interval tumor reduction surgery after neoadjuvant chemotherapy can be omitted,
The second information includes information that the prognosis of neoadjuvant chemotherapy is poor and that interval tumor reduction surgery after neoadjuvant chemotherapy cannot be omitted,
A method for predicting whether to omit interval cytoreductive surgery in patients with advanced ovarian cancer.
In the input device, 1) the first CA-125 (cancer antigen 125) level measured from the measurement subject at the time of diagnosis of advanced ovarian cancer, 2) the time after the first neoadjuvant chemotherapy for the measurement subject The second CA-125 level measured from the measurement subject, 3) first date information at the time of measuring the first CA-125 level, 4) second date information at the time of first neoadjuvant chemotherapy, and 5) Third date information at the time of measuring the second CA-125 level, 6) Age of the measurement subject, 7) Number of times neoadjuvant chemotherapy was administered to the measurement subject, 8) Advanced ovarian disease of the measurement subject A step in which the cancer stage, 9) evaluation of response to prior chemotherapy for the measurement target, and 10) whether or not to perform interval tumor reduction surgery for the measurement target are entered, and the evaluation score is based on the input values 6) to 10) above. Steps, each mapped;
Steps 1) to 5) of the processor calculating a KELIM score using a preset method using the input values 1) to 5);
Calculating, by the processor, a total evaluation score by adding evaluation scores mapped according to the input values 6) to 10) and evaluation scores calculated using the KELIM score; and
Comprising, by the processor, calculating a survival rate of the measurement target using the summed evaluation score.
Methods for predicting survival in patients with advanced ovarian cancer.
According to paragraph 2,
The evaluation score according to the input values 6) to 10), and the evaluation score according to the KELIM score are,
Different evaluation scores are mapped depending on whether the calculated KELIM score is larger or smaller than the preset score,
Different assessment scores are mapped depending on whether your age is under 60 or over 60,
Different evaluation scores are mapped depending on whether the number of neoadjuvant chemotherapy treatments is more than 6 times or less than 6 times,
Different evaluation scores are mapped depending on whether the advanced ovarian cancer stage is ⅢC or Ⅳ,
If the response to prior chemotherapy is Complete Remission (CR), Partial Remission (PR), Progressive Disease (PD), or Stable Disease (SD). Different evaluation scores are mapped according to the
Different evaluation scores are mapped depending on whether interval tumor reduction surgery is performed.
Methods for predicting survival in patients with advanced ovarian cancer.
According to paragraph 3,
The evaluation score according to the input values 6) to 10), and the evaluation score according to the KELIM score are,
When the calculated KELIM score is greater than the preset score, a lower evaluation score is mapped than when the calculated KELIM score is smaller than the preset score,
If you are under 60 years of age, a lower evaluation score is mapped than if you are over 60 years of age.
If the number of neoadjuvant chemotherapy treatments is 6 or more times, a lower evaluation score is mapped than if the number of neoadjuvant chemotherapy treatments is less than 6 times,
If the advanced ovarian cancer stage is ⅢC, a lower evaluation score is mapped than if the advanced ovarian cancer stage is Ⅳ,
If the response evaluation to neoadjuvant chemotherapy is a partial response, an evaluation score that is higher than that of a complete response and lower than that of an advanced lesion or a safe lesion is mapped;
When interval debulking surgery was performed, a lower evaluation score was mapped than when it was not performed.
Methods for predicting survival in patients with advanced ovarian cancer.
According to clause 4,
The evaluation score according to the input values 6) to 10) above, and the evaluation score according to the KELIM score are based on 100 points,
If a KELIM score smaller than the preset score is calculated, 7.5 points, if a KELIM score larger than the preset score is calculated, 0 points,
6) 0 points if you are under 60 years of age, 2.5 points if you are over 60 years of age,
7) If the number of neoadjuvant chemotherapy treatments was 6 or more, 0 points, if less than 6 times, 7.5 points,
8) If the advanced ovarian cancer stage is ⅢC, it is 0 points, and if it is Ⅳ, it is 11.25 points.
9) Response evaluation to prior chemotherapy is 0 points for Complete Remission (CR), 17.5 points for Partial Remission (PR), Progressive Disease (PD) or Stable Disease, SD), 100 points;
10) If interval tumor reduction surgery was performed, 0 points were mapped, and if it was not performed, 11.25 points were mapped, respectively.
Methods for predicting survival in patients with advanced ovarian cancer.
According to clause 5,
The survival rate of the measurement target calculated using the summed evaluation score is progression-free survival,
Methods for predicting survival in patients with advanced ovarian cancer.
According to clause 6,
The survival rate of the measurement target calculated using the summed evaluation score is 6-month progression-free survival rate, 12-month progression-free survival rate, or 24-month progression-free survival rate,
Methods for predicting survival in patients with advanced ovarian cancer.
According to clause 6,
The higher the combined evaluation score, the lower the progression-free survival rate is predicted.
Methods for predicting survival in patients with advanced ovarian cancer.
According to paragraph 4,
The evaluation score according to the input values 6) to 10) above, and the evaluation score according to the KELIM score are based on 100 points,
If a KELIM score smaller than the preset score is calculated, 2.5 points, if a KELIM score larger than the preset score is calculated, 0 points,
6) 0 points if you are under 60 years of age, 7.5 points if you are over 60 years of age,
7) If the number of neoadjuvant chemotherapy treatments was 6 or more, 0 points, if less than 6 times, 6.25 points,
8) If the advanced ovarian cancer stage is ⅢC, it is 0 points, and if it is Ⅳ, it is 8.75 points.
9) If the prior chemotherapy response evaluation is Complete Remission (CR), 0 points, Partial Remission (PR), 30 points, Progressive Disease (PD) or Stable Disease, SD), 100 points;
10) If interval tumor reduction surgery was performed, 0 points were mapped, and if it was not performed, 11.25 points were mapped, respectively.
Methods for predicting survival in patients with advanced ovarian cancer.
According to clause 9,
The survival rate of the measurement target calculated using the summed evaluation score is the overall survival rate,
Methods for predicting survival in patients with advanced ovarian cancer.
According to clause 10,
The survival rate of the measurement target calculated using the summed evaluation score is the 24-month overall survival rate,
Methods for predicting survival in patients with advanced ovarian cancer.
According to clause 10,
The higher the combined evaluation score, the lower the overall survival rate is predicted,
Methods for predicting survival in patients with advanced ovarian cancer.
The processor determines: 1) a first CA-125 (cancer antigen 125) level measured from a random individual at the time of diagnosis of advanced ovarian cancer; 2) a time after the first neoadjuvant chemotherapy for the random individual; the second CA-125 level measured from, 3) the first date information at the time of measuring the first CA-125 level, 4) the second date information at the time of the first neoadjuvant chemotherapy, and 5) the above first date information. 2 Calculating the KELIM score using a preset method using the third date information at the time of measuring the CA-125 value;
The processor calculates the KELIM score - the age of the random subject - the number of times neoadjuvant chemotherapy has been administered to the random subject - the advanced ovarian cancer stage of the random subject - the neoadjuvant chemotherapy for the random subject Response evaluation - whether to perform interval tumor reduction surgery for the random subject - generating learning data consisting of pairs of survival rates; and
The processor performs machine learning using the KELIM score, age, number of times neoadjuvant chemotherapy was administered, advanced ovarian cancer stage, neoadjuvant chemotherapy response evaluation, and whether interval tumor reduction surgery was performed as input elements, and the survival rate as an output element. Or generating a prediction model through deep learning; including,
Methods for predicting survival in patients with advanced ovarian cancer.
According to clause 13,
The survival rate is the progression-free survival rate or overall survival rate,
Methods for predicting survival in patients with advanced ovarian cancer.
According to clause 13,
In the learning process by the processor,
When the calculated KELIM score is greater than the preset score, a lower weight is given than when the calculated KELIM score is less than the preset score,
If you are under 60 years of age, a lower weight is given than if you are over 60 years of age.
If the number of neoadjuvant chemotherapy treatments is 6 or more, a lower weight is given than if the number of neoadjuvant chemotherapy treatments is less than 6,
If the advanced ovarian cancer stage is ⅢC, a lower weight is given than if the advanced ovarian cancer stage is Ⅳ,
In the case of a partial response to neoadjuvant chemotherapy, the weight is given higher than that of a complete response and lower than that of an advanced lesion or a safe lesion.
When interval debulking surgery is performed, a lower weight is given than when it is not performed.
Methods for predicting survival in patients with advanced ovarian cancer.
Carrying out the method according to any one of claims 1 to 15,
Survival rate prediction system for patients with advanced ovarian cancer.
Stored on a computer-readable recording medium to execute the method according to any one of claims 1 to 15,
computer program.

Images