The Future of Medicine is Bright: Personalized Medicine, Predictive Analytics and Big Data

0
303
The Opening of the Exhibits of the Annual Meeting of the American Society of Hematology draws a large crowd on Saturday, December 1, 2018.

Modern medicine is to change dramatically.

Over the past 200 years medicine has seen extraordinary developments and advances. From microbiology to the sequencing of the human genome, the advent of CRISPR–Cas genome editing to potentially treat disease and advance drug discovery and development, as well as a better understanding of underlying biology of cancer and hematological disease, and the availability of novel therapeutic agents such as Antibody-drug Conjugates (ADCs), PD-L1 inhibitors and CAR-T, have all contributed to advances in medicine and have contributed to improved life expectancy and better health.

And the treatment promises – and in may cases the ability to treat – is transforming medicine, especially in the area of oncology and hematology, yielding more cures and long-term remissions than ever before!

These advances are supported by novel way to diagnoses disease. Some of these approached are based on revolutions in advanced technology, others may be more mundane.

New approaches
Three studies presented this year during the 60th annual meeting of the American Society of Hematology (ASH) in San Diego, highlight how recent technological developments are rapidly translating into clinically relevant advances for hard-to-treat blood disorders.

“These cutting-edge studies are examples of the rapid progress we are seeing in medical research thanks to new technology and data sharing,” noted Joseph Mikhael, MD, of the Translational Genomics Research Institute (TGen), City of Hope Cancer Center in Phoenix, Arizona.

“Even just two years ago, studies like these were not possible. They are emblematic of what ASH is about — enhanced collaboration between scientists, improved scientific methods, and facilitated translation of that science into better patient outcomes in a way that a single institution could not do alone,” Mikael added.

Photo 1.0 Joseph Mikhael, MD, Professor in the Applied Cancer Research and Drug Discovery Division at the Translational Genomics Research Institute (TGen), speaks during about the Future in Personalized Medicine at the American Society of Hematology 60th Annual Meeting at the San Diego Center, Sunday December 2, 2018.

Genetic and Clinical information
These studies focus on ways doctors can use genetic and clinical information to gain patient-specific insights. In one study, scientists applied machine learning techniques to improve the tools doctors use to determine the prognosis of patients with myelodysplastic syndromes. Another study uses rapid genetic screening to match patients diagnosed with acute myeloid leukemia (AML) with targeted therapies. A third study suggests focusing on the health of the microbiome to help improve outcomes for patients undergoing hematopoietic cell transplantation.

Machine Learning Improves Prognosis Accuracy
In one study researchers used machine learning — a technique for automating the creation of computer models — to develop a new system to predict how long patients with myelodysplastic syndromes are likely to live. In tests, the system outperformed the current gold standard prognostic tool, suggesting the new model could offer patients and doctors a better and more personalized tool to understand a patient’s risk and inform treatment.

Myelodysplastic syndromes are a type of bone marrow cancer in which the bone marrow fails to manufacture enough healthy blood cells, leading to anemia, bleeding, or infection. Patients diagnosed with myelodysplastic syndromes show a wide range of symptoms and may live for only a few months or for decades. About one-third of patients develop acute myeloid leukemia (AML), a more aggressive type of blood cancer.

Predicting a patient’s risk of dying or developing AML is crucial, both to help patients understand their disease and to help doctors determine a course of treatment. High-risk patients are generally treated with a stem cell transplant, which can cure the disease but carries significant risks, while other, less risky, treatments are recommended for patients with a better prognosis. The best course of treatment for patients at intermediate risk can be unclear because individual clinical trials define risk thresholds in different ways.

Photo 2.0: Aziz Hazha, MD, of the Cleveland Clinic speaks during the annual meeting of the American Society of Hematology about the Future of Personalized Medicine. Sunday December 2, 2018.

“All treatment guidelines are driven by risk, which means that if we get the risk wrong, we get the treatment wrong,” said lead study author Aziz Nazha, MD, of the Cleveland Clinic.

A lack of understand the actual risk may lead to over- or under-treatment.

“Improving and personalizing our prognostic models can help to delineate patients who are at higher versus lower risk — which is particularly challenging for those who fall into the intermediate range — and match them with the appropriate treatment,” Nazha added.

Revised International Prognostic Scoring System
Currently, doctors use the Revised International Prognostic Scoring System (IPSS-R) to assess risk for patients with myelodysplastic syndromes.

“However, the IPSS-R underestimates or overestimates risk in up to one-third of patients,” Nazha said.

To improve prognostic tools, Nazha and his team developed a sophisticated machine learning algorithm that uses genomic and clinical data to determine a patient’s prognosis. They trained the system using patient data from Cleveland Clinic and Munich Leukemia Laboratory (1,471 patients total) and validated it in a separate collection of patient data from Moffitt Cancer Center (831 patients).

Figure 1.0: Snapshots from the web application that represents survival probabilities for 3 different patients (A, B and C) with different clinical and mutational variables.

In head-to-head comparisons using patient medical records, the new model correctly predicted a patient’s likelihood of surviving for a given length of time relative to another patient 74% of the time, compared to 67% of the time for IPSS-R. The model correctly predicted a patient’s likelihood of developing AML relative to another patient 81% of the time, compared to 73% of the time for IPSS-R.

Like any decision-support tool, the model is intended to inform human clinicians, not to replace or compete with them, Nazha noted.

To further improve the model, the researchers are gathering feedback from clinicians and working to incorporate more outcomes, such as health related quality of life (hrQoL), into the model. They are also developing ways for the model to update the assessment of risk in response to changing conditions, such as when new test results are available or treatments are completed.

“This project started out of a frustration voiced by many of my patients who want to know what their own risk is and how their prognosis might differ from that of other patients,” Nazha explained.”

“We wanted to build a personalized prediction tool that can give insights about a specific outcome for a specific patient,” Nazha concluded.

The new model gives survival probabilities at different time points that are unique for a given patient. Incorporating clinical and mutational data outperformed a mutations only model even when cytogenetics and age were added.

Rapid Genetic Screening in Acute Myeloid Leukemia
In another study researchers investigated the feasible for doctors to determine which molecular subtype of acute myeloid leukemia (AML) a patient has before beginning treatment and to use this information to pick an approach that best matches the individual. The results of this study confirm that using patient-specific information to guide treatment decisions, an approach known as precision medicine, is possible even for patients with blood cancers that must be treated urgently.

Because acute myeloid leukemia (AML) is a rapidly progressing cancer it is considered an oncologic emergency. That is why treatment is typically started on the day of diagnosis. Physicians have been reluctant to wait the two to three weeks that it typically takes for genomic analysis. Delaying induction chemotherapy until molecular testing results return, may benefit some patients but can harm others. This leaves doctors with little time to learn which AML subtype the patient has, so in current practice, all patients are given the same treatment regimen.

Treatment with immediate initiation of therapy is thought to be crucial to minimizing disease-related morbidity and mortality. And, in many cases this approach has been beneficial. In an ideal, younger, patient with a core binding factor cytogenetic abnormality, who is given standard anthracycline- and cytarabine-based induction chemotherapy, complete remission (CR) rates approach 85%, with long-term disease-free survival (DFS) rates of 60% or greater. [3]

But in most, less ideal, patients, for example older patients or who have other cytogenetic abnormalities or secondary AML, outcome after standard therapy is much worse, with CR rates less than 50%, treatment-related mortality rates that approach 25%, and minimal long-term DFS.

However, in this study, researchers demonstrate the ability to determine AML subtype based on genetic analysis of blood samples in seven days or less. The findings suggest rapid genetic screening could soon be an integral part of AML diagnostics, helping doctors match each patient with the therapy best suited for his or her specific disease.

Photo 3.0. Amy Burd, Ph.D, Vice President for Research Strategy at The Leukemia & Lymphoma Society speaks during the Annual Meeting at the San Diego Center, Sunday December 2, 2018.

Precision medicine
The results represent the first findings from the Beat AML study, a multi-arm, multi-site collaborative trial designed to test precision medicine approaches for improving the generally poor prognosis among patients with AML. In recent years there have been renewed efforts to improve the standard treatment for AML, which has not significantly advanced in about four decades. Many experimental new therapies target specific AML subtypes, so the ability to determine a patient’s AML subtype is crucial to realizing the full benefits of these therapies, said lead study author Amy Burd, Ph.D, vice president for research strategy at The Leukemia & Lymphoma Society (LLS).

The reported findings include data from 365 patients over age 60 with suspected or confirmed AML who enrolled in the study from November 2016-2018. The researchers applied three genetic analysis techniques — cytogenetics, polymerase chain reaction (PCR), and next-generation sequencing — to patient samples to create a genetic profile of each patient’s disease. Sixty-six patients were removed from the study because they turned out to not have AML upon laboratory analysis.

To date, 146 patients have continued on to the study’s second phase, in which they were treated on a clinical trial for experimental AML therapies targeting their disease subtype. The remaining patients did not continue on to the study’s second phase for a variety of reasons, including choosing standard AML therapy after molecular profiling, enrolling in a different trial, or deciding not to pursue therapy. Waiting for a few days to start therapy after receiving a diagnosis also gave patients time to make informed decisions about their therapy, something the former approach did not allow.

“This supports a patient-centric approach,” Burd said.

The study is designed to incorporate new experimental therapies as they are developed. Having started in 2016 with three treatment arms, the study has now grown to include 11 arms testing therapies developed by seven different pharmaceutical companies. Initial results from some of these studies suggest patients benefit from therapies specifically chosen based on their individual disease subtype.

“I think the future of treatment for AML will include point-of-care screening to determine what type of AML the patient has and then make the treatment decision based on that information,” Burd said.

“Being able to do genetic screening rapidly and efficiently is critical to making a decision for that patient within seven days. This study demonstrates that the precision medicine approach is feasible and effective,” she added.

Beat AML, LLC, a division of LLS, a nonprofit organization dedicated to fighting blood cancers, is the sponsor of the trial and holds the IND (investigational new drug) approval from the FDA. ASH is an exclusive partner with LLS in educating physicians about the Beat AML initiative.

Disruptions in the Gut Microbiota
The third study expected to help drastically change medicine reports that the likelihood of complications from a hematopoietic cell transplantation (HCT) is higher if a patient has lower diversity of microbes residing in the gut before beginning the transplantation process. While previous research has shown a similar relationship between outcomes and gut microbial composition shortly after transplantation, this new study suggests that the association starts even before patients begin transplantation.

Photo 4.0 Jonathan Peled, MD, PhD of the Memorial Sloan Kettering Cancer Center, speaks during the annual meeting of the American Society of Hematology on, Sunday December 2, 2018. Photo by © ASH/Scott Morgan 2018

Hematopoietic cell transplantation (HCT) is a procedure in which a patient receives blood-forming stem cells from a genetically similar donor. This approach is often used to treat aggressive blood cancers, but it can be associated with severe complications such as graft-versus-host disease (GVHD), a serious and potentially life-threatening complication that occurs when the donated immune cells attack the patient’s cells as foreign tissue.

Although the study is an observational study and doesn’t show cause and effect, the results suggest that it may be possible to reduce patients’ risk of complications by taking steps to improve the health of their gut microbiota before beginning HCT.

Healthy body function
The billions of bacteria and other microbes that live on and within our bodies play an important role in maintaining healthy bodily functions. The study, conducted in the United States, Europe and Japan, found patients set to undergo HCT had gut microbiota that was 1.7 to 2.5-fold lower in diversity compared to healthy volunteers. The microbial communities in the majority of the patients’ guts went on to be dominated by a single bacterial species.

The study compared stool samples from nearly 1,000 patients undergoing allogeneic HCT to those of healthy volunteers. While microbial composition, which depends to some extent on diet and environment, showed some variation from place to place, the diversity and types of microbes found in the stool of transplant patients in all countries was markedly different from those of the healthy volunteers. Further analysis showed this low diversity was associated with lower calorie intake, the use of broad-spectrum antibiotics, and the use of higher-intensity conditioning drugs to clear cancer cells from the body before transplantation.

Patients with the lowest microbial diversity showed lower overall survival and a higher risk for GVHD.

“Before we approve patients to receive a transplant, we do many tests to make sure all of their organs are in good working order,” said lead study author Jonathan U. Peled, MD, PhD, of Memorial Sloan Kettering Cancer Center.

“In the future, we envision that the health of the gut microbiota — which some have called the ‘forgotten organ’ — may become part of this whole-body evaluation. It might also be possible to intervene and repair the microbiota in the pre-transplantation period.”

References
[1] Nazha A, Komrokji RS, Meggendorfer M, Mukherjee S, Al Ali N, Walter W, Hutter S, Padron E, Madanat YF, et al. A Personalized Prediction Model to Risk Stratify Patients with Myelodysplastic Syndromes. | Oral and Poster Abstracts | Session: 637. Myelodysplastic Syndromes—Clinical Studies: Prognosis and Prediction | Hematology Disease Topics & Pathways: AML, Diseases, MDS, Technology and Procedures, Clinically relevant, Myeloid Malignancies, molecular testing, NGS. Presented during the 60th Annual Meeting of the American Society of Hematology. December 2018. [Abstract]
[2] Burd A, Levine RL, Shoben A, Mims AS, Borate U, Stein EM, Patel PA, et al.Initial Report of the Beat AML Umbrella Study for Previously Untreated AML: Evidence of Feasibility and Early Success in Molecularly Driven Phase 1 and 2 Studies. Program: Oral and Poster Abstracts | Session: 616. Acute Myeloid Leukemia: Novel Therapy, excluding Transplantation: Targeted Therapy | Hematology Disease Topics & Pathways: AML, antibodies, Biological, Diseases, Therapies, Non-Biological, Elderly, Study Population, Clinically relevant, Myeloid Malignancies, pharmacology | Presented during the 60th Annual Meeting of the American Society of Hematology. December 2018.[Abstract]
[3] Sekeres MA, Elson P, Kalaycio ME, Advani AS, Copelan EA, Faderl S, Kantarjian HM, Estey E. Time from diagnosis to treatment initiation predicts survival in younger, but not older, acute myeloid leukemia patients.Blood. 2009 Jan 1;113(1):28-36. doi: 10.1182/blood-2008-05-157065. Epub 2008 Sep 30.[Pubmed][Article]
[4] Peled JU, Gomes ALC, Stein-Thoeringer CK, Slingerland JB, Slingerland AE, Weber D, Markey KA, Smith M, et al. Multicenter Microbiota Analysis Indicates That Pre-HCT Microbiota Injury Is Prevalent across Geography and Predicts Poor Overall Survival. Program: Oral and Poster Abstracts. Session: 721. Clinical Allogeneic Transplantation: Conditioning Regimens, Engraftment, and Acute Transplant Toxicities: Microbiodata, Endothelial Damage, and Opportunistic Infections. Hematology Disease Topics & Pathways:
Biological, Adult, Therapies, Technology and Procedures, Study Population, transplantation, NGS.| Presented during the 60th Annual Meeting of the American Society of Hematology. December 2018. [Abstract]


Last Editorial Review: December 2, 2018

Featured Image: The Opening of the Exhibits of the Annual Meeting of the American Society of Hematology draws a large crowd on Saturday, December 1, 2018. Courtesy: 2018 © American Society of Hematology/Scott Morgan 2018. Used with permission. Photo 1.0: Joseph Mikhae speaks during about the Future in Personalized Medicine at the American Society of Hematology 60th Annual Meeting at the San Diego Center, Sunday December 2, 2018. Courtesy: 2018 © American Society of Hematology/Scott Morgan 2018. Used with permission. Photo 2.0: Aziz Hazha, MD, speaks during the annual meeting of the American Society of Hematology about the Future of Personalized Medicine. Sunday December 2, 2018. Courtesy: 2018 © American Society of Hematology/Scott Morgan 2018. Used with permission. Photo 3.0. Amy Burd speaks during the Annual Meeting at the San Diego Center, Sunday December 2, 2018. Courtesy: 2018 © American Society of Hematology/Scott Morgan 2018. Used with permission. Photo 4.0 Jonathan Peled, MD, PhD speaks during the annual meeting fo the American Society of Hematology on, Sunday December 2, 2018. Courtesy: 2018 © American Society of Hematology/Scott Morgan 2018. Used with permission. Figure 1.0: Snapshots from the web application that represents survival probabilities for 3 different patients (A, B and C) with different clinical and mutational variables. Courtesy: 2018 © American Society of Hematology. Used with permission.

Copyright © 2010 – 2018 Sunvalley Communication, LLC. All rights reserved. Republication or redistribution of Sunvalley Communication content, including by framing or similar means, is expressly prohibited without the prior written consent of Sunvalley Communication. Sunvalley Communication shall not be liable for any errors or delays in the content, or for any actions taken in reliance thereon. Onco’Zine, Oncozine and The Onco’Zine Brief are registered trademarks and trademarks of Sunvalley Communication around the world.

Print Friendly, PDF & Email

LEAVE A REPLY

Please enter your comment!
Please enter your name here