What is metastatic colorectal cancer?
The third most common type of cancer is colorectal cancer. mCRC is the metastatic type of colorectal cancer being located at the colon or rectal part of the human body. It appears more often in men than in women, but women often suffer from the more aggressive right-sided type of the cancer. The right-sided type of mCRC goes along with a worse prognosis of survival. Generally, one can distinguish between left- and right-sided colorectal cancer, where left-sided mCRC patients have better prognoses concerning the progression-free survival (PFS). The PFS is a factor that measures how long people survive after the cancer treatment without the tumor progressing again. A lot of mCRC cases are related to higher ages, because age is one of the risk factors. Other risk factors are a bad lifestyle (bad diet habits, alcohol consumption, etc) and less frequently also genetic factors.

Classification of mCRC patients is done by the oncologists on basis of anatomical tumor characteristics like grading and staging. Grading indicates how similar a tumor cell is to a normal cell, whereas staging gives information about the size and the spreading of the tumor. Since not all patients have the same present biomarkers (biologically measurable parameters of biological processes, that are known to have prognostic or diagnostic expressive power) and clinical data (measured values like weight, height, blood pressure, vitamin d value etc.), not all treatments will work equally well for all patients. Thus, a more personalized approach is being aspired, where in addition to grading and staging several other molecular biomarkers and individual clinical data of the patient play a more important role in the treatment decision.

What does REVERT mean?
The abbreviation REVERT origins from the long title “taRgeted thErapy for adVanced colorEctal canceR paTients”. REVERT is an international project funded by the EU, that started in 2020 and is planned to end in 2023. Specialists from Italy, Spain, Sweden, Luxembourg, Romania, and Germany were chosen to participate in the project, involving clinicians, pathologists, biologists, software developers, and also artificial intelligence (AI) specialists. BioVariance is part of the work package being responsible for the development of the AI solutions, thus BioVariance will offer some machine learning solutions for the question of the project.

What is the aim of the project?
The project aims at generating the REVERT database of molecular and clinical data collected from several hundred metastatic colorectal cancer patients that had visited one of the participating hospitals located at the different countries within the EU in the past. The database is then used as a basis for machine learning models to aspire a more personalized therapy approach for treating newly diagnosed patients. In the future, the trained AI model will predict a suitable first-line treatment for each new patient, who has not received any cancer medication yet, supporting the clinicians in their treatment decision. In addition to that, a clinical study will be executed with several new patients that decide to participate and want to be treated according to the AI-based results. This prospective clinical study will be performed with already authorized and commonly used chemotherapies and not with new treatments. The expectation concerning the AI-based results is to provide another more objective decision factor for clinicians, that is free from the subjective decision of the attending doctor at the hospital. Finally, the machine learning (ML) solutions will be combined in an app, that can support clinicians in the future.

What is machine learning and how is it used in the context of the project?
Machine learning algorithms use underlying mathematical models to recognize certain patterns in the patient’s data. The primary dataset of the REVERT database contains several processes of cancer treatments, the known survival outcome and about 150 other molecular and clinical features of hundreds of mCRC patients from the last 10 years. According to the underlying mathematical models, it is possible to derive some new rules from this dataset, that make it possible to predict outcomes for each new patient that was not included in the primary data. Therefore, the primary dataset must be used to (i) train and thereby generating ML models and to (ii) test and evaluate these generated models. In addition, the ML models allow to spot important features, that have a strong influence on the outcome prediction. For the primary dataset the actual outcome is already known, allowing us to see for how many patients the model predicted the correct outcome.

In the REVERT project BioVariance’s ML algorithms are used to create models that can classify whether a certain patient is likely to respond to different chemotherapies, that have been approved for years. During the project, several chemotherapies have already been categorized by the clinicians as being equally well for treating mCRC and that are now considered for the project. The related question for the ML algorithms is to predict the first-line treatment (= initial treatment, that is recommended for a disease, here: chemotherapy) having the highest chance of success for a certain patient.

What is the current status of the project and what is still to come?
At the moment, the machine learning models are already trained and tested on the previously collected dataset. BioVariance’s models and the models of three other REVERT members are used to predict the best first-line treatment for real patients participating in a phase two clinical study that started in March this year. The first few patients that were diagnosed with mCRC and enrolled to the study have already been processed with the ML models and were treated according to the model outcomes.

The main focus lays on the continuous improvement of the ML algorithms to get the best predictions possible. In the near future the ML models will be included into the REVERT app interface. This allows clinicians to directly enter patient’s data into the REVERT app and get a prediction for the most suitable first-line treatment on a patient-based level.

This approach is an important step into the direction of personalized medicine, since the huge amount of each patient’s data is intensively analyzed and leads to the best treatment for that patient individually, whereas in the current decision process patients get more or less grouped into stages or grades and are then treated in the same way. Finally, the clinical study will show whether the more personalized approach will be able to improve the survival of the patients.

Der Beitrag BioVariance is a member of the EU-funded REVERT Project erschien zuerst auf BioVariance - data-driven diagnostics.

The facts

„Colorectal carcinoma“ means several malignant tumor types in the colon or rectum. Malignant tumors rarely occur in other intestinal areas like small intestine or caecum. ^[1]

Colorectal cancer (CRC) had a low incidence rate in 1950. However, it became a predominant cancer type and now accounts for about 10% of cancer-related mortality in western countries.^[1,2] CRC is the second most common cancer type in men and women in Germany. It ranks third behind lung and breast cancer worldwide. In Germany, about 26.000 women and 32.300 men developed CRC in 2016, while 11.400 women and 13.400 men died from it. More than half of the patients developing CRC had an age of 70 years and above. Only 10 % of the new cases occur before the age of 55. ^[2] The lifetime risk of developing CRC is about 6 %, with chronic inflammatory bowel diseases and other important factors like unhealthy diet or lack of exercise raising the cancer risk. Inheritable genetic mutations cause 3-5 % of all CRC cases, especially colon cancer. Affected people have a very high risk of developing cancer in the early age of 20-40 years. ^[1]

In the year 2018, the World Health Organization counted about 1,8 Mio new CRC cases and 880.000 deaths. ^[3,4] More than 50 % of the new cases were registered in Asia (see Fig. 1). The global incidence rate is estimated to increase up to 3 Mio until 2040. ^[3]

As described above, men are stronger affected by CRCs than women. ^[2,3,6] Additionally, cancer cases strongly increased in the developed countries due to the ageing population in the recent years (see Fig. 2). ^[3]

Sex differences

Although women have a lower incidence of CRC than men, right-sided CRCs occur more frequently in women compared to men, whereas left-sided CRCs have an equal frequency between both sexes. Several evidences demonstrate that the rate of right-sided CRC cases is strikingly higher in women than in men (61.7% vs 38.3%), while only slightly more left-sided CRC cases are observed in women than men (52.1% vs 47.8%). The reason for this sex difference is still not proven and of concern for women, due to the association of right-sided CRCs with the poorest clinical outcomes among all CRC patients. ^[5]

Studies revealed that metabolite rates in the glycolysis pathway, pentose phosphate pathway, carnitine shuttle metabolism, asparagine synthesis, methionine metabolism and the polyamine synthesis pathway showed sex-related differences when measured in tumor samples compared to normal samples. Tumors from women and men also used different metabolic intermediates between the sexes for energy production to support cell growth. ^[5] Thus, modern CRC therapy approaches should ideally consider not only common molecular information, but also details of sex-specific mechanisms.

Further studies also indicate that the gut microbiota is partly correlated with the tumor development as well as emerging drug resistance. ^[4,6]

The upgrade of personalized colorectal cancer treatment

Personalizing cancer treatment is still challenging. No expert believes in finding a magic cure against CRC nowadays. However, therapeutic approaches based on patient’s genetic variations provide the most promising chances for patients. Numerous genetic mutations are already associated with risk of CRC. ^[7] But the manual search for gene variants and appropriate drugs in cancer therapy is very labour intensive and time consuming, while the number of new medical insights gained from scientific research continuously increases. Further, economic acting must be brought into accordance with patient welfare.

Therefore, BioVariance has now developed the web-based platform OncoVariant to identify the most suitable medication for patients suffering from colorectal, breast or prostate cancer. State-of-the-art automatization and parallelization techniques are combined for comparing patient’s gene variants with profound knowledge from worldwide databases regarding treatment options. The final report contains information about patient’s variants and appropriate clinical evidence as well as information on the proposed drugs and their interactions. The examination of numerous high-quality databases ensures the high value of the proposed therapy options. Thus, OncoVariant enables personalized cancer therapy while minimizing time and effort on behalf of attending physicians. ^[8] Finding the perfect treatment for each patient is now as easy as never before.

Here you can find more information about the web-based platform OncoVariant.

Contact Person:

Kerstin Hammer

Sources

Der Beitrag Colorectal cancer – The evil within erschien zuerst auf BioVariance - data-driven diagnostics.

Generally, drugs are only allowed to be prescribed when special agencies have tested them on safety, effectiveness and quality and have approved them on corresponding indications. The prescription of drugs without considering these facts is called “off-label use”. ^[1] The relevant aspects for a drug approval are not only the application area and route of administration, but also dosage, moment of intake and the duration of the treatment. Off-label use is not permitted officially, but requires special care. General risks like decreased effectiveness or side effects are harder to conceive due to a lack of study data on effectiveness and safety. ^[1,2] In new-born, off-label use concerns up to 90 % of all patients, while it’s about 50 % in children and about 25 % in adults. ^[3,4] Insurances may take over the accruing costs only in these particular cases: ^[1]

• Severe or life-threatening diseases
• Reasonable assumption that the prescribed drug will induce a therapy success
• Other therapy options are not available

Off-label use in children and adolescents

Off-label use is common especially in paediatrics, because clinical studies regarding drug intake in young patients are often lacking. Children and adolescents differ in body size and functions from each other and from adults. Thus, drugs which are originally approved for adults can cause overdosage or severe side effects in children. ^[2,5] But despite that, ill children have to be treated sufficiently and so the treating physicians are forced to act in this legal grey area. When children are included in clinical studies, there have to be considered special ethical and legal facts. For the participation in a clinical study the consent of the participant (children with an age of 8 years, dependent on development) and his legal representative has to be recorded. In contrast to adult studies, a remuneration is not allowed in studies with children. Further, single indications will probably never get a full approval in rare diseases, because the number of patients in relevant age groups is too low to conduct clinical studies. ^[5] To improve the current situation of healthcare for children and adolescents regarding approved drugs, the European Union implemented the regulation (EC) Nr. 1901/2006 in the year 2007. The aim was to maintain and extend the number of drugs approved for the treatment of young patients under 18 years. ^[6] A Pediatric Commission (PDCO) was established for the valuation of paediatric concepts of drug companies. Since the implementation of the regulation clinical studies were increasingly conducted, about 100 new indications were authorized and more than 270 new drugs were approved for the treatment of children (see Fig. 1). ^[2,7]  

  In the year 2016, most of the off-label prescriptions were recognized for patients between 1 and 13 years. The highest number was listed for patients in the age group 6-13 years. Off-label use in dosage, indication and duration of the treatment were highest among all patients (see Fig. 2). ^[8]  

Advancement through digitalization

With the paediatric off-label use being necessary way too often, several countries implemented special projects dealing with the development of web-based platforms. These platforms are meant to support physicians in treating their young patients. Well-known examples are „Kinderformularium“ from the Netherlands, the „British National Formulary for Children“ from Great Britain, „Kispiportal“ from Switzerland and „Drugbase“ from Germany. ^[9,10,11,12]

• „Kinderformularium“ is an open access paediatric database for physicians and pharmacists. It currently includes information about dosage, application form, side effects, contraindications and corresponding references for more than 730 drugs. ^[9]
• The „British National Formulary for Children“ was established for health professionals by the Royal College of Paediatrics and Child Health (RCPCH) and the Neonatal and Paediatric Pharmacists Group (NPPG). It deals with prescriptions and care for young patients and offers information about more than 900 drugs and 200 treatment options. ^[10]
• „Kispiportal“ is the official database of the Universitäts-Kinderspital in Zurich. After entering patient’s data, the correct dosage of a certain drug is calculated automatically. ^[11]
• „Drugbase“ offered by Wissenschaftliche Verlagsgesellschaft Stuttgart includes several reference works in the fields of medicine and pharmacy, for example the Red List, drug profiles and paediatric dosage charts. ^[12]

These comprehensive and easily accessible databases will improve therapies for young patients by avoiding side effects and unnecessary expenses and also by shortening the duration of the treatments.  

Contact Person: Kerstin Hammer Sources

Der Beitrag Off-Label Use in Paediatrics erschien zuerst auf BioVariance - data-driven diagnostics.