Assistant Professor, Pathology and Molecular Medicine

Associate Member, Biochemistry and Biomedical Sciences

Division: Anatomical Pathology

RESEARCH INTERESTS: Research Areas: Artificial Intelligence Machine Learning Research Interests: Machine Learning Myeloid neoplasia

Dr. Campbell is a hematopathologist with clinical experience in blood and bone marrow morphology, transfusion medicine, special coagulation, red cell disorders, digital pathology and laboratory management.

905-525-9140 ext. 20605

campbecj@mcmaster.ca

---

Campbell Research Program: redefining diagnostic medicine with machine learning

We are in an era where the availability and scale of data is unprecedented. It is beyond the capability of humans to meaningfully analyze such enormous datasets using traditional approaches. This is particularly relevant to healthcare, where increasingly large and complex patient datasets are set to redefine the practice of medicine. The future of diagnostic medicine will entail extracting information from these datasets using a type of artificial intelligence (AI) called machine learning, which is software that learns from data to make predictions about the world. Consequently, the specialty known as pathology will evolve from that of a diagnostic consultant to one of an information specialist.

The fundamental paradigm of pathology is that information about a disease state can be gained by looking at the microscopic features of human tissue. However, the methods used to analyze human tissue specimens (glass slides and light microscope) remain archaic. Assuming that the human brain coupled with a microscope is the best measurement tool for extracting visual information from tissues may no longer be valid. Fortunately, the inevitable transition to digital pathology is set to yield large digital image datasets that can be analyzed by machine learning algorithms to extract and organize biological information in ways not possible by humans. When this information is linked to information from other large clinical and real-word datasets also analyzed using machine learning tools, it is anticipated that new paradigms will emerge that will fundamentally change the practice of diagnostic medicine. 

We believe careful application of machine learning algorithms in diagnostic medicine using non-biased and objective approaches will yield new insights into human health and disease, and lead to better patient care. With this in mind, our research program is structured around the following broad applications of machine learning:

1. Automate workflows in diagnostic medicine.

2. Develop new representations of the information in pathology tissue specimens and reports. 

3. Link this information with information from other large healthcare datasets to redefine paradigms in health and disease. 

Our research program is jointly conducted in collaboration with Dr. Hamid Tizhoosh and KIMIA Lab at the University of Waterloo and Huron Digital Pathology. 

Assistant Professor, Pathology and Molecular Medicine

Associate Member, Biochemistry and Biomedical Sciences

Division: Anatomical Pathology

RESEARCH INTERESTS: Research Areas: Artificial Intelligence Machine Learning Research Interests: Machine Learning Myeloid neoplasia

Dr. Campbell is a hematopathologist with clinical experience in blood and bone marrow morphology, transfusion medicine, special coagulation, red cell disorders, digital pathology and laboratory management.

905-525-9140 ext. 20605

campbecj@mcmaster.ca

---

Campbell Research Program: redefining diagnostic medicine with machine learning

We are in an era where the availability and scale of data is unprecedented. It is beyond the capability of humans to meaningfully analyze such enormous datasets using traditional approaches. This is particularly relevant to healthcare, where increasingly large and complex patient datasets are set to redefine the practice of medicine. The future of diagnostic medicine will entail extracting information from these datasets using a type of artificial intelligence (AI) called machine learning, which is software that learns from data to make predictions about the world. Consequently, the specialty known as pathology will evolve from that of a diagnostic consultant to one of an information specialist.

The fundamental paradigm of pathology is that information about a disease state can be gained by looking at the microscopic features of human tissue. However, the methods used to analyze human tissue specimens (glass slides and light microscope) remain archaic. Assuming that the human brain coupled with a microscope is the best measurement tool for extracting visual information from tissues may no longer be valid. Fortunately, the inevitable transition to digital pathology is set to yield large digital image datasets that can be analyzed by machine learning algorithms to extract and organize biological information in ways not possible by humans. When this information is linked to information from other large clinical and real-word datasets also analyzed using machine learning tools, it is anticipated that new paradigms will emerge that will fundamentally change the practice of diagnostic medicine. 

We believe careful application of machine learning algorithms in diagnostic medicine using non-biased and objective approaches will yield new insights into human health and disease, and lead to better patient care. With this in mind, our research program is structured around the following broad applications of machine learning:

1. Automate workflows in diagnostic medicine.

2. Develop new representations of the information in pathology tissue specimens and reports. 

3. Link this information with information from other large healthcare datasets to redefine paradigms in health and disease. 

Our research program is jointly conducted in collaboration with Dr. Hamid Tizhoosh and KIMIA Lab at the University of Waterloo and Huron Digital Pathology. 

Assistant Professor, Pathology and Molecular Medicine

Associate Member, Biochemistry and Biomedical Sciences

Division: Anatomical Pathology

RESEARCH INTERESTS: Research Areas: Artificial Intelligence Machine Learning Research Interests: Machine Learning Myeloid neoplasia

Dr. Campbell is a hematopathologist with clinical experience in blood and bone marrow morphology, transfusion medicine, special coagulation, red cell disorders, digital pathology and laboratory management.

905-525-9140 ext. 20605

campbecj@mcmaster.ca

---

Campbell Research Program: redefining diagnostic medicine with machine learning

We are in an era where the availability and scale of data is unprecedented. It is beyond the capability of humans to meaningfully analyze such enormous datasets using traditional approaches. This is particularly relevant to healthcare, where increasingly large and complex patient datasets are set to redefine the practice of medicine. The future of diagnostic medicine will entail extracting information from these datasets using a type of artificial intelligence (AI) called machine learning, which is software that learns from data to make predictions about the world. Consequently, the specialty known as pathology will evolve from that of a diagnostic consultant to one of an information specialist.

The fundamental paradigm of pathology is that information about a disease state can be gained by looking at the microscopic features of human tissue. However, the methods used to analyze human tissue specimens (glass slides and light microscope) remain archaic. Assuming that the human brain coupled with a microscope is the best measurement tool for extracting visual information from tissues may no longer be valid. Fortunately, the inevitable transition to digital pathology is set to yield large digital image datasets that can be analyzed by machine learning algorithms to extract and organize biological information in ways not possible by humans. When this information is linked to information from other large clinical and real-word datasets also analyzed using machine learning tools, it is anticipated that new paradigms will emerge that will fundamentally change the practice of diagnostic medicine. 

We believe careful application of machine learning algorithms in diagnostic medicine using non-biased and objective approaches will yield new insights into human health and disease, and lead to better patient care. With this in mind, our research program is structured around the following broad applications of machine learning:

1. Automate workflows in diagnostic medicine.

2. Develop new representations of the information in pathology tissue specimens and reports. 

3. Link this information with information from other large healthcare datasets to redefine paradigms in health and disease. 

Our research program is jointly conducted in collaboration with Dr. Hamid Tizhoosh and KIMIA Lab at the University of Waterloo and Huron Digital Pathology. 

Assistant Professor, Pathology and Molecular Medicine

Associate Member, Biochemistry and Biomedical Sciences

Division: Anatomical Pathology

RESEARCH INTERESTS: Research Areas: Artificial Intelligence Machine Learning Research Interests: Machine Learning Myeloid neoplasia

Dr. Campbell is a hematopathologist with clinical experience in blood and bone marrow morphology, transfusion medicine, special coagulation, red cell disorders, digital pathology and laboratory management.

905-525-9140 ext. 20605

campbecj@mcmaster.ca

---

Campbell Research Program: redefining diagnostic medicine with machine learning

We are in an era where the availability and scale of data is unprecedented. It is beyond the capability of humans to meaningfully analyze such enormous datasets using traditional approaches. This is particularly relevant to healthcare, where increasingly large and complex patient datasets are set to redefine the practice of medicine. The future of diagnostic medicine will entail extracting information from these datasets using a type of artificial intelligence (AI) called machine learning, which is software that learns from data to make predictions about the world. Consequently, the specialty known as pathology will evolve from that of a diagnostic consultant to one of an information specialist.

The fundamental paradigm of pathology is that information about a disease state can be gained by looking at the microscopic features of human tissue. However, the methods used to analyze human tissue specimens (glass slides and light microscope) remain archaic. Assuming that the human brain coupled with a microscope is the best measurement tool for extracting visual information from tissues may no longer be valid. Fortunately, the inevitable transition to digital pathology is set to yield large digital image datasets that can be analyzed by machine learning algorithms to extract and organize biological information in ways not possible by humans. When this information is linked to information from other large clinical and real-word datasets also analyzed using machine learning tools, it is anticipated that new paradigms will emerge that will fundamentally change the practice of diagnostic medicine. 

We believe careful application of machine learning algorithms in diagnostic medicine using non-biased and objective approaches will yield new insights into human health and disease, and lead to better patient care. With this in mind, our research program is structured around the following broad applications of machine learning:

1. Automate workflows in diagnostic medicine.

2. Develop new representations of the information in pathology tissue specimens and reports. 

3. Link this information with information from other large healthcare datasets to redefine paradigms in health and disease. 

Our research program is jointly conducted in collaboration with Dr. Hamid Tizhoosh and KIMIA Lab at the University of Waterloo and Huron Digital Pathology.