Study: AI accurately predicts childhood disease from health records

Xia Huimin and Guangzhou Women and Children’s Medical Center researchers used AI to read 1.36 million pediatric health records, and diagnosed disease as accurately as doctors, according to a recent study.

Common childhood diseases were detected after processing symptoms, medical history and other clinical data from this massive sample.  The goal is the diagnosis of complex or rare diseases by providing more diagnostic predictions, and to assist triage patients.

Join ApplySci at the 11th Wearable Tech + Digital Health + Neurotech Boston conference on November 14th at Harvard Medical School

Nano-robots remove bacteria, toxins from blood

UCSD’s Joe Wang and Liangfang Zhang have developed tiny ultrasound-powered robots that can swim through blood, removing harmful bacteria and toxins.

Gold nanowires were coated with platelet and red blood cell membranes,  allowing the nanorobots to perform the tasks of two different cells at once—platelets, which bind pathogens, and red blood cells, which absorb and neutralize toxins. The gold body responds to ultrasound, giving the nanorobots the ability to swim rapidly without chemical fuel, helping them mix with blood bacteria and toxins and speed detoxification.

The robots are about 25 times smaller than the width of a human hair and can travel 35 micrometers per second in blood. They were tested on MRSA contaminated blood samples, which three times less bacteria and toxins than untreated samples after five minutes.

Click to view UCSD video

Join ApplySci at the 9th Wearable Tech + Digital Health + Neurotech Boston conference on September 24, 2018 at the MIT Media Lab.  Speakers include:  Rudy Tanzi – Mary Lou Jepsen – George ChurchRoz PicardNathan IntratorKeith JohnsonJuan EnriquezJohn MattisonRoozbeh GhaffariPoppy Crum – Phillip Alvelda Marom Bikson


Single blood draw detects 1250 pathogens from cell-free DNA

Karius‘s  next-generation sequencing detects fragments of 1250 microbes from a single blood draw.  Identifying microbial cell-free DNA from bacteria, viruses, fungi and protozoa can facilitate the rapid diagnosis of infectious disease.  Current diagnostics only detect a narrow range of pathogens, and may require invasive biopsies.

This fast and comprehensive analysis could enable more effective, targeted treatment, and the ability to monitor infection in high-risk patients, which will save lives.

Join ApplySci at Wearable Tech + Digital Health + NeuroTech Boston on September 19, 2017 at the MIT Media Lab – featuring  Joi Ito – Ed Boyden – Roz Picard – George Church – Nathan Intrator –  Tom Insel – John Rogers – Jamshid Ghajar – Phillip Alvelda – Michael Weintraub – Nancy Brown – Steve Kraus – Bill Geary – Mary Lou Jepsen – Daniela Rus

Registration rates increase Friday, August 11th.


CRISPR platform targets RNA and DNA to detect cancer, Zika

Broad and Wyss scientists have used an RNA-targeting CRISPR enzyme to detect  the presence of as little as a single target molecule. SHERLOCK (Specific High Sensitivity Enzymatic Reporter UnLOCKing) could one day be used to respond to viral and bacterial outbreaks, monitor antibiotic resistance, and detect cancer.

Demonstrated applications included:

  • Detecting the presence of Zika virus in patient blood or urine samples within hours;
  • Distinguishing between the genetic sequences of African and American strains of Zika virus;
  • Discriminating specific types of bacteria, such as E. coli;
  • Detecting antibiotic resistance genes;
  • Identifying cancerous mutations in simulated cell-free DNA fragments; and
  • Rapidly reading human genetic information, such as risk of heart disease, from a saliva sample.

The tool can be paper-based, not requiring refrigeration, and suited for fast deployment at field hospitals or rural clinics.

Join ApplySci at Wearable Tech + Digital Health + NeuroTech Boston – Featuring: Joi Ito, Ed Boyden, Roz Picard, George Church, Tom Insel, John Rogers, Jamshid Ghajar, Phillip Alvelda and Nathan Intrator – September 19, 2017 at the MIT Media Lab

HIV, hepatitis, herpes, cancer detecting nanosensor

Dmitry Fedyanin and Yury Stebunov from the Moscow Institute of Physics and Technology have developed a highly sensitive  biological object detecting nanosensor.

The tiny sensor analyzes the chemical composition of substances and can detect viral disease markers in HIV, hepatitis, and herpes.  It can also help doctors identify tumor markers.

The optical sensor can track changes of  a few kilodaltons in the mass of a cantilever in real time.  The researchers believe that this can help diagnose diseases long before they can be detected by other methods.


Single blood drop test for 1000 current or previous viruses

VirScan allows simultaneous testing for 1,000 virus strains that currently or have previously infected a person, using one drop of blood. The  research, from Howard Hughes Medical Institute,  Brigham and Women’s Hospital, and Harvard,  describes the interplay between immunity and the human virome.

In the study, blood samples from 600 people in Peru, the United States, South Africa and Thailand were tested. The team developed and used a library of peptides representing more than 1,000 viral strains to find evidence of previous viral exposure. Rates of exposure varied by age, geographic location and HIV status, but the team found that a small number of peptides were recognized by the vast majority of people’s immune systems. This pattern, suggesting that the immune systems of many individuals touch upon the same protein portion in a virus, could have implications for understanding immunity.

VirScan may also help researchers find correlations between previous virus exposure and the development of a disease later in life.


Suit, patch allow doctors to safely treat Ebola patients

At SXSW this week, USAID unveiled a biomedical suit and a wearable sensor patch to protect doctors while treating Ebola patients.

The John’s Hopkins developed suit takes two minutes to put on.  It has anti-fogging capabilities and will contain a cooling system, allowing doctors to wear it for longer periods.  Past protective suits took 30 minutes to put on, were hot and uncomfortable, and could only be worn for 45 minutes.

The MultiSense Memory patch described at the conference will enable doctors to remotely monitor patients.  It is flexible , has multiple sensors, and attaches to a patient’s sternum with adhesive.  The device takes baseline heart rate, temp and oxygen saturation readings, and measures all changes.  The prototype uses a USB cable to transmit data, but the patch will use Bluetooth.   It will cost $100 and will have 7 to 10 days of battery life. The average Ebola case runs its course in five days.

Results of USAID’s Grand Challenge to Fight Ebola also include:

  • Aquarius GEP LLC and Innovative BioDefense
    Antiseptic that, when applied to skin, provides up to six hours of pathogen protection and serves as an anti-microbial barrier to viral transmission for health care workers
  • SPR Advanced Technologies, Inc.
    Long-lasting, spray-on barrier that kills and repels microbes with electro-static fields to prevent surface contamination and allow for more breathable PPE materials

Wearable Tech + Digital Healthy NYC 2015 – June 30 @ New York Academy of Sciences.  Early registration rate available until March 27.