Breaking News
February 15, 2019 - Genetic variations in a fourth gene associated with higher ALL risk in Hispanic children
February 15, 2019 - Disruptive behavioral problems in kindergarten linked with lower employment earnings in adulthood
February 15, 2019 - New bioengineered device enhances the production of T-cells
February 15, 2019 - HDL proteome behaves like a tiny Velcro ball that is rolling on surfaces
February 15, 2019 - Puerto Rican children more likely to have poor or decreasing use of asthma inhalers
February 15, 2019 - Quality of patient care does not improve after physician-hospital integration
February 15, 2019 - Synopsys release new software for implant design and patient-specific planning
February 15, 2019 - 6 out of 10 hip replacements last 25 years or longer
February 15, 2019 - Health Tip: What You Should Know About Antibiotics
February 15, 2019 - New research challenges medical consensus that adenoids and tonsils significantly shrink during teenage years
February 15, 2019 - Discovery of weakness in a rare cancer could be exploited with drugs
February 15, 2019 - UVA scientists find potential explanation for mysterious cell death in Alzheimer’s, Parkinson’s
February 15, 2019 - New rules requiring female athletes to lower testosterone levels are based on flawed data
February 15, 2019 - Researchers comprehensively sequence the human immune system
February 15, 2019 - Researchers study animal venoms to identify new medicines for treating diseases
February 15, 2019 - Movement of wrist bones revealed by MRI and computer modeling
February 15, 2019 - Philips introduces new premium digital X-ray room to help shorten patient wait times
February 15, 2019 - Women fare worse than men following aortic heart surgery, study finds
February 15, 2019 - High-protein and low-calorie diet helps older adults lose weight safely, shows study
February 15, 2019 - Drug microdosing effects may not measure up to big expectations
February 15, 2019 - Discharged, Dismissed: ERs Often Miss Chance To Set Overdose Survivors On ‘Better Path’
February 15, 2019 - A digitized lab environment to be showcased at smartLAB 2019
February 15, 2019 - Scientists uncover main mechanisms of fluconazole drug resistance
February 15, 2019 - New study seeks to understand how colibactin causes cancer
February 15, 2019 - Photoacoustic imaging accurately measures the temperature of deep tissues
February 15, 2019 - Large study finds no association between phthalate exposure and breast cancer risk
February 15, 2019 - New research explains presence of ‘natural’ magnetism in human cells
February 15, 2019 - Bio-Rad launches new digital PCR system and kit for monitoring treatment response in CML patients
February 15, 2019 - Scientists shed light on damaging cell effects linked to aging
February 15, 2019 - High intensity exercise may improve health by increasing gut microbiota diversity
February 15, 2019 - Apellis’ APL-2 Receives Orphan Drug Designation from the FDA for the Treatment of Autoimmune Hemolytic Anemia
February 15, 2019 - Couples creating art or playing board games release ‘love hormone’
February 15, 2019 - Glimpsing The Future At Gargantuan Health Tech Showcase
February 15, 2019 - Common herbicide found to increase the risk of lymphoma
February 15, 2019 - Over-abundance of energy to cells could increase cancer risk
February 15, 2019 - Oxford Genetics appoints Jocelyne Bath as new Chief Operating Officer
February 15, 2019 - Castration-resistant metastatic prostate cancer responds to combination of immune checkpoint inhibitors
February 15, 2019 - Large-scale clinical trial begins to study liver transplantation between people with HIV
February 15, 2019 - Cannabis use among adolescents linked with increased risk of depression in adulthood
February 15, 2019 - Fractures, head injuries common in electric scooter accidents, UCLA study finds
February 15, 2019 - Prenatal maternal depression has important consequences for infant temperament, study shows
February 15, 2019 - Stereotactic body radiotherapy effective in treating men with low- or intermediate-risk prostate cancer
February 15, 2019 - Zogenix Submits New Drug Application to U.S. Food & Drug Administration for Fintepla for the Treatment of Dravet Syndrome
February 15, 2019 - Certain birthmarks warrant quick treatment, pediatricians say
February 15, 2019 - New machine learning method predicts if atypical ductal hyperplasia will turn cancerous
February 15, 2019 - Whole-genome sequencing and sharing real-time data could limit spread of foodborne bacteria
February 15, 2019 - FDA warns doctor for illegally marketing unapproved implantable device
February 15, 2019 - New injury documentation tool may provide better evidence for elder abuse cases
February 15, 2019 - Physiological age is a better predictor of survival than chronological age, shows study
February 15, 2019 - New study reveals high success rate for hip and knee replacements
February 15, 2019 - Prenatal exposures to BPA may pose threat to human ovarian function
February 15, 2019 - Suspicious spots on the lungs of children with rhabdomyosarcoma do not behave like metastases
February 15, 2019 - Diet drinks daily could raise stroke risk says study
February 15, 2019 - Many Systematic Reviews Do Not Fully Report Adverse Events
February 15, 2019 - Seven tips to protect your child from burns
February 15, 2019 - Keynote speakers announced for CBD Expo MIDWEST
February 15, 2019 - New DNA methylation GrimAge tool allows you to predict lifespan and healthspan
February 15, 2019 - New AI-driven platform analyze how pathogens infect human cells
February 15, 2019 - Increased activity of EHMT2 gene deficient neurons could cause autism in humans
February 15, 2019 - Recurring UTIs may mask symptoms of bladder or kidney cancer
February 15, 2019 - Researchers conduct extensive comparison of drugs used in treating neuroendocrine tumors
February 15, 2019 - Depression prevention for pregnant women and new mothers – new recommendations
February 15, 2019 - AHA News: Are There Health Benefits From Chocolate?
February 15, 2019 - The involvement of the gut in Parkinson’s disease: hype or hope?
February 15, 2019 - New PET imaging agent may help measure efficacy or failure of hormone therapy for breast cancer
February 15, 2019 - Preventing infections could help combat antimicrobial resistance
February 15, 2019 - Study investigates the role of estrogen in controlling glucose homeostasis
February 15, 2019 - Exposure to chemical in weedkiller Roundup raises risk of some cancers, study finds
February 15, 2019 - Smoking and drinking during pregnancy – stigma drives women to secrecy
February 15, 2019 - Low FODMAP diet reduces stomach issues caused by exercise
February 15, 2019 - Novel approach uses small amounts of tissue to quantify PD-L1 expression levels in tumors
February 15, 2019 - Breast pumps could be transmitting asthma-causing bacteria in babies, finds study
February 15, 2019 - The Pistoia Alliance Launches Next Phase of Blockchain Project to Develop Life Science R&D Use Cases
February 15, 2019 - The search for environmental causes of Parkinson’s disease moves forward
February 15, 2019 - Women scientists inhibited by funding methods that favor men, researchers say
February 14, 2019 - Few primary care physicians lack enough knowledge of cancer treatment options
February 14, 2019 - Prime real estate is determined by previous owner in the squirrel world
February 14, 2019 - Discovery of a ‘master switch’ within the immune system
February 14, 2019 - Health officers with surgical training are a safe alternative for performing C-sections
February 14, 2019 - Researchers discover mechanism on how body’s antimicrobial shield regulates microbiome
New algorithm could accelerate diagnosis of genetic diseases using clinical records

New algorithm could accelerate diagnosis of genetic diseases using clinical records

image_pdfDownload PDFimage_print

In a continued effort to speed up the diagnostic process of severe genetic diseases, Stanford’s Gill Bejerano, PhD, and his colleagues have developed a new algorithm that can quickly locate important disease-related information within a patient’s medical record.

In a paper recently published in Nature Genetics in Medicine, Bejerano and Cole Deisseroth, a Bio-X undergraduate fellow, along with researchers including Johannes Birgmeier, a graduate student in computer science, developed an algorithm that scans through records of patients and extracts the patient’s key phenotypes, or observable traits.

The team focused particularly on patients with life-threatening genetic diseases such as sickle cell anemia, cystic fibrosis and Huntington’s disease. Manually scanning through patient notes without a computer, a dedicated clinician can process around 200 patient records in a 40-hour work week, the researchers said. This algorithm can do the same job in 10 minutes, further saving busy doctors an additional three to five hours per every downstream disease diagnosis.

“A diagnosis is extremely valuable for the patient, for the family and for the attending clinician,” said Bejerano. But finding the diagnosis within the patient’s genome is very time consuming and, “for that we need computational tools.”

The algorithm is called ClinPhen — a combination of “clinical” and “phenotypes.” After examining a patient’s medical records, the algorithm parses the sentences into short phrases. For example, if the clinical note reads, “The child has short stature and long eyelashes. She has a cleft palate and a small jaw,” the phrases, “The child has short stature”, “and long eyelashes”, “She has a cleft palate”, and “a small jaw” would be selected.

These phrases are converted into codes from an existing phenotype database called the Human Phenotype Ontology, or HPO. The codes are then sorted, with the most- and earliest-mentioned phenotypes at the top of the list. ClinPhen can also identify words, such as “father” and “does not have” and not associate any phenotypes mentioned in that sentence with the patient.

ClinPhen’s accuracy, phenotype filter and speed was validated using six sets of real patient clinical notes from four different medical centers. When compared to other phenotype extraction algorithms, ClinPhen was more precise and 20 times faster, the research showed.

“ClinPhen actually guesses slightly better than a clinician,” Bejerano said. “We can capture clinician intuition and pick the right set of phenotypes to best facilitate the diagnosis.”

The HPO codes produced by ClinPhen will then be fed to Phrank, another algorithm designed by Bejerano and his colleagues that ranks patients’ genes that have rare variants for their ability to explain the phenotypes, or traits, identified by ClinPhen.

Bejerano describes the efforts as a “computational ecosystem”, and said he hopes to see this ecosystem implemented in clinical settings soon.

“The medical establishment is very conservative. And for good reason… You want to protect the patient,” Bejerano said. “[But] I think that slowly, very slowly, there is a shift towards using more of these automated systems. With 60 million patients to be sequenced in the next several years, we simply have no choice.”

Image by Darryl Leja, NHGRI

Tagged with:

About author

Related Articles