create tailored data analysis and AI solutions in a clinical environment. The easy-touse research suites for physicians and technicians provide access to state-of-the-art
analysis and AI methods, while the integrated development and analytics environments allow direct data access and real-time feedback between physicians and data
scientists to enhance collaboration.
In the near future, we may see an extension of this IntellisSpace Discovery
solution concept beyond radiology and reaching other clinical domains, leveraging
EMR-based enriched data, allowing physicians to get easy access to a whole system
of insights.
2.11 Toward Precision Medicine?
Perhaps one of the most promising areas of potential for AI and adaptive intelligence
in healthcare is in the field of precision medicine. Since scientists started sequencing
the human genome in the 1990s, doctors have predicted the arrival of precision
medicine, in which the right patients are matched at the right time with the right
therapy to treat their disease.
Such an approach, which is still in its infancy, has particularly far-reaching
implications for cancer—a catch-all term to describe a multitude of diseases that
will affect one out of two men, and one out of three women worldwide in their
lifetime. Scientists are developing an increasingly complex set of options to treat
cancer. These range from interventional therapies—such as surgery, radiation, and
image-guided therapy—through an increasingly broad range of pharmaceutical
therapies, right up to strategies with no or minimal interventions, such as those
involving active surveillance or palliative care.
The optimal treatment choice depends on precise diagnosis. Yet in precision
medicine, this is critically dependent on the ability to analyze staggeringly large data
sets with multiple and diverse parameters—something far beyond any human’s
ability. This is where AI and big data analytics, coupled with clinical insights can
play a crucial role.
To detect the presence of cancer in a patient, they analyze suspicious tissue
samples on a glass slide through a microscope to determine if the tissue is malignant.
Their typing of the tissue is a crucial component in the staging of the tumor, guiding
treatment decisions. With the clinical introduction of digital pathology, it has
become possible to implement more efficient pathology diagnostic workflows.
This can help the pathologist to streamline the diagnostic process, connect a team,
even remotely, to enhance competencies and maximize use of resources, unify
patient data for informed decision-making, and gain new insights by turning data
into knowledge.
Oncology is a complex medical domain, in which multiple disciplines must
collaborate to reach accurate diagnoses and effective treatment plans. Unfortunately,
information is frequently lost in communications between specialties and care
networks, which can lead to critical information being missed. Prediction models
Health Informatics and Co-Innovation: Connecting Patients, Clinical Practice,. . .
121
analysis and AI methods, while the integrated development and analytics environments allow direct data access and real-time feedback between physicians and data
scientists to enhance collaboration.
In the near future, we may see an extension of this IntellisSpace Discovery
solution concept beyond radiology and reaching other clinical domains, leveraging
EMR-based enriched data, allowing physicians to get easy access to a whole system
of insights.
2.11 Toward Precision Medicine?
Perhaps one of the most promising areas of potential for AI and adaptive intelligence
in healthcare is in the field of precision medicine. Since scientists started sequencing
the human genome in the 1990s, doctors have predicted the arrival of precision
medicine, in which the right patients are matched at the right time with the right
therapy to treat their disease.
Such an approach, which is still in its infancy, has particularly far-reaching
implications for cancer—a catch-all term to describe a multitude of diseases that
will affect one out of two men, and one out of three women worldwide in their
lifetime. Scientists are developing an increasingly complex set of options to treat
cancer. These range from interventional therapies—such as surgery, radiation, and
image-guided therapy—through an increasingly broad range of pharmaceutical
therapies, right up to strategies with no or minimal interventions, such as those
involving active surveillance or palliative care.
The optimal treatment choice depends on precise diagnosis. Yet in precision
medicine, this is critically dependent on the ability to analyze staggeringly large data
sets with multiple and diverse parameters—something far beyond any human’s
ability. This is where AI and big data analytics, coupled with clinical insights can
play a crucial role.
To detect the presence of cancer in a patient, they analyze suspicious tissue
samples on a glass slide through a microscope to determine if the tissue is malignant.
Their typing of the tissue is a crucial component in the staging of the tumor, guiding
treatment decisions. With the clinical introduction of digital pathology, it has
become possible to implement more efficient pathology diagnostic workflows.
This can help the pathologist to streamline the diagnostic process, connect a team,
even remotely, to enhance competencies and maximize use of resources, unify
patient data for informed decision-making, and gain new insights by turning data
into knowledge.
Oncology is a complex medical domain, in which multiple disciplines must
collaborate to reach accurate diagnoses and effective treatment plans. Unfortunately,
information is frequently lost in communications between specialties and care
networks, which can lead to critical information being missed. Prediction models
Health Informatics and Co-Innovation: Connecting Patients, Clinical Practice,. . .
121