Skip to main content

Treating the individual with the knowledge of all

The promise of a more effective, personalised form of medicine is being handicapped because classical healthcare systems are unable to cope with huge amounts of data generated – so researchers are turning to sophisticated informatics tools. To realise the potential of systems medicine requires the use of geographical data, pollution, medical history, and even information from a patient’s genome.

Delegates to the 2014 Biomax Symposium, held in September at Martinsried near Munich, Bavaria, heard that – by taking advantage of sophisticated informatics tools – doctors and researchers can analyse this complex information to provide better outcomes for patients.

This approach is opening up new avenues for the treatment of chronic obstructive pulmonary disease (COPD), according to Dr Emiel Wouters, from the Medical University at Maastricht. Wouters is also chairman of CIRO+, an international centre of excellence for the diagnosis and treatment of COPD, based in the Netherlands.

Wouters said: ‘25 years of knowledge clearly illustrates that COPD is more than airflow limitation, it is a multi-component disease condition with different respiratory impairments, with systemic effects, with comorbidities and we are all very aware that external environmental factors are very important, for example smoking.’ A condition like COPD manifests differently in different patients with considerable variation based on a number of complex variables such as age, physical activity, smoking, and environmental factors such as air pollution.

Wouters said: ‘The CIRO+ Data Centre allows, for the first time, a better understanding of patient outcomes based on systematic pre- and post-assessment data of more than 3,000 patients over the past six years, with up to 6,000 clinical data points captured for each patient.’

He continued: ‘The impact of being able to exploit clinical knowledge effectively using state of the art technology cannot be overestimated. This applies to both improved patient care and better management of treatment costs.’

In order to develop this new form of personalised medicine researchers and doctors at CIRO+ teamed up with Biomax. They created a data centre that could not only house large amounts of data but also mine that data effectively so that patients could be stratified based on pre-determined variables.

According to Dr Klaus Heumann, CEO of Biomax, the system was configured based on the BioXM and Viscovery technologies for semantic integration and data mining. That means the CIRO+ configuration required no time-consuming software development, but was built and is continuously evolving by configuring the underlying platform through biomedical experts.

Once all the relevant patient data was collected, it allowed researchers to look for the underlying causes and mechanisms behind COPD. As Wouters put it: ‘We are trying to treat the individual with the knowledge of all.’ 

This is a common idea in the field of predictive medicine: by collecting data and using data mining techniques, along with more classical approaches to medicine, researchers can begin to predict the most likely outcome before a patient gets to a critical stage. This allows a doctor to intervene earlier, which in turn leads to better patient outcomes.

Wouters said: ‘Predictive medicine is very important for us in order to offer the optimal treatment to the patient. We believe at this moment that the ecosystem of integrated knowledge system that we have setup is the basis to move further in this systems medicine approach.’

Dr Christophe Pison, from the Clinique Universitaire de Pneumologie, Grenoble, France, presented data from research into the prediction of chronic lung allograft dysfunction (CLAD). The study, focusing on multidisciplinary consortium Systems prediction of CLAD (SysCLAD), was set up with 14 lung transplant centres, four small and medium enterprises, and three academic platforms. It was funded by the European Union under the Seventh Framework Programme.

The aim was to develop a predictive mathematical model to predict if patients are at risk of developing chronic lung allograft dysfunction within three years of their lung transplant.

A theme common to both speakers was that the classical data that a doctor receives is not enough, especially for complicated illnesses with many factors to consider. A doctor may know if a patient smokes, as well as their medical history and some hereditary conditions, but many other factors play a role in these complex conditions.

The team behind SysCLAD ‘put a large emphasis on environmental factors’ said Pison. To this end all information is geo-localised – so a doctor can know if a patient lives in an area of high air pollution, for example. According to the group, the predictive mathematical model will be derived from ‘the complete integration of extensive and diverse experimental datasets (clinicome, environmental data, omics, microbiome, and immunological assays) collected from both donors and recipients.’ This data will then be combined with data on air pollution as well as gene expression analysis of M1 and M2 lung macrophages and many other data points to create a more comprehensive understanding of how CLAD works.

Informatics software can integrate all this data to make predictive medicine a reality. Pison illustrated the shift in emphasis by reference to his own career: ‘All my education was to intervene when the car was broken.’ But now, he explained, medicine looks to maintain and service the car rather than just wait until something has gone wrong.

According to Àlvar Agustí from the Thorax Institute, Barnaclinic+, Barcelona, Spain, this new approach to medicine requires new skills: ‘These kinds of systems medicine, personalised medicine, P4 medicine, whatever you want to call it, cannot be done by a single type of professional. Clinicians alone cannot do this. Biologists alone cannot do this. Bioinformaticians alone cannot do this. Unless there is multidisciplinarity there is no way we can prevail.’

The integration of data also makes demands on the intelligence of the software systems that are being used to process the data in order to make the predictions. Jim Roldan, from Linkcare Health Services, Barcelona, Spain, said: ‘When we talk about big data [in systems medicine], the main reason is because we have added some sources of data such as omics or environmental information’. Roldan went on to say: ‘As you know when you get into this kind of information, the amount of data is enormous.’

Hans-Werner Mewes from the Helmholtz-Center, Munich, Germany, mentioned similar experiences: ‘Over the last years I have been more and more puzzled about how to deal with huge amounts of data and then try to filter out something that was interesting.’

The idea behind all of these systems is to use data and the computational power needed to sort, manage and mine it effectively so that the system can provide knowledge to the users helping them to refine their decision-making. As the systems used for prediction become more complex, it will become more and more challenging to refine the models based on finding the relevant biomarkers and proving the causal link to the disease.

However, Mewes says: ‘One of the biggest problems in modelling is that almost all the networks are unidirectional and they hardly ever give feedback on the control over time.’ He gave an example of over 1,500 biomarkers of which only a handful had proven useful once they had been sufficiently researched. Mewes said: ‘Most were significant indicators, but they have no predictive power. Predictive power is all about causality.’

If computational models for predictive medicine are to transform the treatment of life-threatening conditions, informatics software will need to be at the heart of data integration. Data analytics will also be required if knowledge is to be derived from the ever-increasing amounts of data.

Roldan said: ‘Knowledge, at the end, is somewhere above the level of data and information.

‘It is about making decisions. When you are a doctor and you have few minutes to visit your patient, you need to understand what to ask this patient, what information you need to get from them, what information you have about them already, so that you can take a decision about the next step to take.’

Roldan concluded: ‘There is a trend to be less intuitive and be more effective at matching cost with the effectiveness of the results. In any of these steps Knowledge as a Service (KaaS) allows you to take the right direction or as we say now, gives you the options. What we have learned really is that we cannot give you advice but we can say “according to the knowledge base, these are the possible alternatives”.’



Topics

Read more about:

Laboratory informatics

Media Partners