Are Younger People Really Addicted to Their Smartphones? Interview with:

Brittany I. Davidson MA Doctoral Researcher in Information Systems University of Bath

Ms. Davidson

Brittany I. Davidson MA
Doctoral Researcher in Information Systems
University of Bath What is the background for this study? What are the main findings?

Response: Typically, research interested in the impact of technology, or more specifically, smartphones on people and society, use surveys to measure people’s usage. Almost always, these studies claim potential harms from using smartphones, like depression, anxiety, or poorer sleep. However, these studies simply ask people about  their behaviour rather than actually measuring it.

In our study, we took 10 widely used surveys to  measure screen time, which typically asks how often people use their smartphone or how problematic their usage is. We compared this to people’s objective smartphone usage from Apple Screen time (e.g., minutes spend on iPhone, number of times they picked up their phone, and the number of notifications received).

We found that there is a large discrepancy between what people self-report and what they actually do with their iPhone. This is highly problematic as the sweeping statements that claim smartphones (or technology more generally) have a negative impact on mental health are not  based on solid and robust evidence at this time, which leaves much to be desired in terms of what we really know about the  impacts of technology use on people.

Continue reading

BrainHQ Computerized Training Program Improved Cognitive Parameters after Mild TBI Interview with:

Dr.. Mahncke

Dr. Mahncke

Dr. Henry W. Mahncke PhD
Research neuroscientist
CEO of Posit Science Corporation What makes this study newsworthy? 

Response: Mild Traumatic Brain Injury (mTBI) is a complex condition to treat. Patients can report many symptoms (e.g., cognitive deficits, depression, anxiety, stress, fatigue, pain, sleep difficulties, disorientation, emotional issues). Prior to this study, conducted at five military and veterans’ medical centers, there has been no highly-scalable intervention to treat the cognitive deficits associated with mTBI. This study showed that a plasticity-based, computerized, brain-training app can drive statistically and clinically significant gains in overall cognitive performance. Given the number of service members and vets with persistent cognitive deficits from TBIs, that’s a big deal. Continue reading

Telemedicine Expansion to Rural Areas Limited by Lack of Broadband Infrastructure Interview with:

Coleman Drake, PhDAssistant Professor, Health Policy and ManagementPitt Public HealthUniversity of Pittsburgh Graduate School of Public Health

Dr. Drake

Coleman Drake, PhD
Assistant Professor, Health Policy and Management
Pitt Public Health
University of Pittsburgh Graduate School of Public Health What is the background for this study? What are the main findings?

 Response: Telemedicine is frequently proposed as a solution to improve access to care in rural areas where driving to the nearest physician can take up to several hours. However, there needs to be sufficient broadband infrastructure for patients to actually use telemedicine. We found that broadband infrastructure is often insufficient to support telemedicine in the most rural areas, particularly in areas where there is inadequate access to primary care physicians and psychiatrists. 

Continue reading

Laser Microscope Can See and Treat Skin Without Cutting Into It Interview with:
Haishan Zeng, PhDDistinguished ScientistImaging Unit - Integrative Oncology DepartmentBC Cancer Research CentreProfessor of Dermatology, Pathology, and Physics, University of British ColumbiaVancouver, BC, Canada Haishan Zeng, PhD

Distinguished Scientist
Imaging Unit – Integrative Oncology Department
BC Cancer Research Centre
Professor of Dermatology, Pathology, and Physics, University of British Columbia
Vancouver, BC, Canada What is the background for this study? What are the main findings?

Response: We developed a fast multiphoton microscope system that enables clinical imaging of the skin at the level of cellular resolution. With this system, we can see microstructures inside of the skin without cutting into it. We subsequently conceived the idea of directly treating the microstructures that are responsible for disease. We increased the laser power to generate intense localized heat to destroy the targeted structure. In this study, we demonstrated the feasibility of this new treatment by targeting and closing single blood vessels using our new microscope. 

Continue reading

Machine Learning Can Analyze Entire Transcriptome To Improve Diagnosis of Difficult Cancers Interview with:

Steven J.M. Jones, Professor, FRSC, FCAHSCo-Director & Head, BioinformaticsGenome Sciences CentreBritish Columbia Cancer Research CentreVancouver, British Columbia, Canada

Dr. Jones

Steven J.M. Jones, Professor, FRSC, FCAHS
Co-Director & Head, Bioinformatics
Genome Sciences Centre
British Columbia Cancer Research Centre
Vancouver, British Columbia, Canada and

Jasleen Grewal, BSc.Genome Sciences CentreBritish Columbia Cancer Research CentreVancouver, British Columbia, CanadaJasleen Grewal, BSc.
Genome Sciences Centre
British Columbia Cancer Research Centre
Vancouver, British Columbia, Canada What is the background for this study?

Response: Cancer diagnosis requires manual analysis of tissue appearance, histology, and protein expression. However, there are certain types of cancers, known as cancers of unknown primary, that are difficult to diagnose based purely on their appearance and a small set of proteins. In our precision medicine oncogenomics program, we needed an accurate approach to confirm diagnosis of biopsied samples and determine candidate tumour types for where the primary site of the cancer was uncertain.  We developed a machine learning approach, trained on the gene expression data of over 10,688 individual tumours and healthy tissues, that has been able to achieve this task with high accuracy.

Genome sequencing offers a high-resolution view of the biological landscape of cancers. RNA-Seq in particular quantifies how much each gene is expressed in a given sample. In this study, we used the entire transcriptome, spanning 17,688 genes in the human genome, to train a machine learning method for cancer diagnosis. The resultant method, SCOPE, takes in the entire transcriptome and outputs an interpretable confidence score from across a set of 40 different cancer types and 26 healthy tissues.  Continue reading

NYU Researchers Develop Siri-Like Application to Identify PTSD by Speech Analysis Interview with:

Charles R. Marmar, MDThe Lucius N. Littauer Professor Chair of the Department of PsychiatryNYU Langone School of Medicine

Dr. Marmar

Charles R. Marmar, MD
The Lucius N. Littauer Professor
Chair of the Department of Psychiatry
NYU Langone School of Medicine What is the background for this study? What are the main findings? 

Response: Several studies in recent years have attempted to identify biological markers that distinguish individuals with PTSD, with candidate markers including changes in brain cell networks, genetics, neurochemistry, immune functioning, and psychophysiology. Despite such advances, the use of biomarkers for diagnosing PTSD remained elusive going into the current study, and no physical marker was applied in the clinic.

Our study is the first to compare speech in an age and gender matched sample of a military population with and without PTSD, in which PTSD was assessed by a clinician, and in which all patients did not have a major depressive disorder. Because measuring voice qualities in non-invasive, inexpensive and might be done over the phone, many labs have sought to design speech-based diagnostic tools 

Continue reading

AI Poised to Revolutionize Radiation Therapy for Cancer Interview with:

Raymond H Mak, MDRadiation OncologyBrigham and Women's Hospital

Dr. Mak

Raymond H Mak, MD
Radiation Oncology
Brigham and Women’s Hospital What is the background for this study? 

  • Lung cancer remains the most common cancer, and leading cause of cancer mortality, in the world and ~40-50% of lung cancer patients will need radiation therapy as part of their care
  • The accuracy and precision of lung tumor targeting by radiation oncologists can directly impact outcomes, since this key targeting task is critical for successful therapeutic radiation delivery.
  • An incorrectly delineated tumor may lead to inadequate dose at tumor margins during radiation therapy, which in turn decreases the likelihood of tumor control.
  • Multiple studies have shown significant inter-observer variation in tumor target design, even among expert radiation oncologists
  • Expertise in targeting lung tumors for radiation therapy may not be available to under-resourced health care settings
  • Some more information on the problem of lung cancer and the radiation therapy targeting task here:

Continue reading

Most Diabetes Apps Do Not Provide Real Time Decision Support (yet) Interview with:

Associate Professor Josip CarMD, PhD, DIC, MSc, FFPH, FRCP (Edin)​Associate Professor of Health Services Outcomes Research,​Director, Health Services Outcomes Research Programme and DirectorCentre for Population Health SciencesPrincipal Investigator, Population Health & Living Laboratory

Prof. Car

Associate Professor Josip Car
MD, PhD, DIC, MSc, FFPH, FRCP (Edin)​
Associate Professor of Health Services Outcomes Research,​
Director, Health Services Outcomes Research Programme and Director
Centre for Population Health Sciences
Principal Investigator, Population Health & Living Laboratory What is the background for this study?

Response: In 2018, almost 8% of people with diabetes who owned a smartphone used a diabetes app to support self-management. Currently, most apps are not regulated by the US Food and Drug Administration (FDA). We downloaded and assessed 371 diabetes self-management apps, to see if they provided evidence-based decision support and patient education.  Continue reading

Augmented Reality Glasses to Improve Socialization Skills in Children with ASD Interview with:

Dennis P. Wall, PhDAssociate ProfessorDepartments of Pediatrics, Psychiatry (by courtesy) and Biomedical Data ScienceStanford University

Dr. Wall

Dennis P. Wall, PhD
Associate Professor
Departments of Pediatrics, Psychiatry (by courtesy) and Biomedical Data Science
Stanford University What did we already know about the potential for apps and wearables to help kids with autism improve their social skills, and how do the current study findings add to our understanding? What’s new/surprising here and why does it matter for children and families? 

Response: We have clinically tested apps/AI for diagnosis (e.g. in a number of studies.

This RCT is a third phase of a phased approach to establish feasibility and engagement through in-lab and at-home codesign with families with children with autism. This stepwise process is quite important to bring a wearable form of therapy running AI into the homes in a way that is clinically effective.

What’s new here, aside from being a first in the field, is the rigorous statistical approach we take with an intent-to-treat style of analysis. This approach ensures that the effect of the changes are adjusted to ensure that any significance observed is due to the treatment.  Thus, with this, it is surprising and encouraging to see an effect on the VABS socialization sub-scale. This supports the hypothesis that the intervention has a true treatment effect and increases the social acuity of the child.

With it being a home format for intervention that can operate with or without a clinical practitioner, it increases options and can help bridge gaps in access to care, such as when on waiting lists or if the care process is inconsistent.   Continue reading

Have Police Body-Worn Cameras Lived Up To Their Expectations? Interview with:

Cynthia Lum, PhDProfessor of CriminologyLaw and SocietyGeorge Mason University

Dr. Lum

Cynthia Lum, PhD
Professor of Criminology
Law and Society
George Mason University What is the background for this study?

Response: Body-worn cameras (BWCs) are one of the most rapidly diffusing technologies in policing today, costing agencies and their municipalities millions of dollars. Recent estimates by the Bureau of Justice statistics indicate that over 60% of local police departments have already acquired BWCs. This adoption has been propelled by highly publicized officer-involved shootings and other death-in-custody events in this decade, as well as more generally by continuing concerns regarding police-citizen relationships, particularly within communities of color.

All of these contexts prompt the need to better understand the impacts and effects of BWCs as they diffuse rapidly into policing. Specifically, do BWCs achieve the expectations that citizens, communities, and the police have of them?

This article provides a narrative review of 70 studies, representing over 110 findings, about what we know from research across six important Body-worn cameras domains:

(1) the impact of BWCs on officer behavior;

(2) officer attitudes about BWCs;

(3) the impact of BWCs on citizen behavior;

(4) citizen and community attitudes about BWCs;

(5) the impact of BWCs on criminal investigations; and (6) the impact of BWCs on law enforcement organizations.

Continue reading

TAVRcathAID Mobile App Facilitates Coronary Access Education After TAVR Interview with:

Annapoorna Kini, MDZena and Michael A Wiener Professor of MedicineDirector of the Cardiac Catheterization LaboratoryMount Sinai Heart at Mount Sinai Hospital

Dr. Kini

Annapoorna Kini, MD
Zena and Michael A Wiener Professor of Medicine
Director of the Cardiac Catheterization Laboratory
Mount Sinai Heart at Mount Sinai Hospital What is the background for this study?  

  • Expanding indication and use of Transcatheter aortic valve replacement (TAVR) poses a unique problem of coronary access after valve implantation.
  • Troubleshooting tools and techniques have been published but are not available at the fingertips of the user at all the times.
  • We tried to address this unique problem with an innovative educational mobile application (app) called “TAVRcathAID”.

Continue reading

Smartphone App Will Be Able to Predict Diabetes Interview with:

Robert Avram MD MScDivision of CardiologyUniversity of California, San Francisco

Dr. Robert Avram

Robert Avram MD MSc
Division of Cardiology
University of California, San Francisco What is the background for this study? Would you briefly describe what is meant by Photoplethysmography?

While analyzing the heart rate data as collected using smartphones apps in the Health-eHeart study, we noticed that diabetic patients had, on average, a higher ‘free-living’ heart rate than non-diabetic patients when adjusted from multiple factors. This pushed us to analyze the signal to see if there were other features that would help differentiate diabetes patients from non-diabetes patients. By identifying these features, we saw a huge opportunity to develop a screening tool for diabetes using deep learning and a smartphone camera and flash, in order to classify patients as having prevalent diabetes/no-diabetes.

Photoplethysmography is the technique of measuring the difference in light absorption by the skin in order to detect blood volume changes in the microvasculature. Most modern mobile devices, including smartphones and many fitness trackers (Apple Wathc, FitBit), have the ability to acquire PPG waveforms, providing a unique opportunity to detect diabetes-related vascular changes at population-scale.  Continue reading

AI-Deep Learning Interpreted Lung Cancer Biopsies As Well As Pathologists Interview with:

Saeed Hassanpour, PhDAssistant ProfessorDepartments of Biomedical Data Science,Computer Science, and EpidemiologyGeisel School of Medicine at DartmouthLebanon, NH 03756

Dr. Hassanpour

Saeed Hassanpour, PhD
Assistant Professor
Departments of Biomedical Data Science,
Computer Science, and Epidemiology
Geisel School of Medicine at Dartmouth
Lebanon, NH 03756 What is the background for this study? What are the main findings?

Response: Lung cancer is the deadliest cancer for both men and women in the western world. The most common form, lung adenocarcinoma, requires pathologist’s visual examination of resection slides to determine grade and treatment. However, this is a hard and tedious task. Using new technologies in artificial intelligence and deep learning, we trained a deep neural network to classify lung adenocarcinoma subtypes on histopathology slides and found that it performed on par with three practicing pathologists. Continue reading

Radiomics Plus Machine Learning Can Optimize Prostate Cancer Classification Interview with:

Gaurav Pandey, Ph.D. Assistant Professor Department of Genetics and Genomic Sciences Icahn Institute of Data Science and Genomic Technology Icahn School of Medicine at Mount Sinai, New York 

Dr. Pandey

Gaurav Pandey, Ph.D.
Assistant Professor
Department of Genetics and Genomic Sciences
Icahn Institute of Data Science and Genomic Technology
Icahn School of Medicine at Mount Sinai, New York What is the background for this study?

 Response: Multiparametric magnetic resonance imaging (mpMRI) has become increasingly important for the clinical assessment of prostate cancer (PCa), most routinely through PI-RADS v2, but its interpretation is generally variable due to its relatively subjective nature.

Radiomics, a methodology that can analyze a large number of features of images that are difficult to study solely by visual assessment, combined with machine learning methods have shown potential for improving the accuracy and objectivity of mpMRI-based prostate cancer assessment. However, previous studies in this direction are generally limited to a small number of classification methods, evaluation using the AUC score only, and a non-rigorous assessment of all possible combinations of radiomics and machine learning methods. Continue reading

Knee Implants: Electrical Energy Harvested From Walking Can Power Sensors Interview with:

Professor Sherry Towfighian PhD Mechanical Engineering Binghamton University  

Prof. Towfighian

Professor Sherry Towfighian PhD
Mechanical Engineering
Binghamton University What is the background for this study? What are the main findings? 

Response: We wanted to avoid using batteries in a load monitor that can be placed in total knee replacement. We looked into energy scavenging technologies and studied the most appropriate one for this application. Energy scavenging is converting wasted energy such as walking to electricity for low power sensors.

Our research study showed walking can provide enough electrical energy (about 6 microwatts) for low power load sensors. These load sensors are important in providing information about the mechanical load throughout different activities. It can be used in the future to create a self -awareness device for the patient to avoid certain activities.  Continue reading

Ultraviolet System Enhances Disinfection of Patient Equipment Interview with:

Donna Armellino RN, DNP, CIC Vice President, Infection Prevention Northwell Health, Infection Prevention Lake Success, N. Y.

Dr. Armellino

Donna Armellino RN, DNP, CIC
Vice President, Infection Prevention
Northwell Health, Infection Prevention
Lake Success, N. Y. What is the background for this study? 

Response: The background for initiating this study was to assess frequently used equipment within the patient care environment following standard manual cleaning and disinfection compared to disinfection with PurpleSun’s shadowless 90-second cycle focused multivector ultraviolet (FMUV) delivery system. Microbes exist within the environment. Cleaning followed by disinfection, regardless of method, is intended to decrease levels of these microbes to minimize exposure and the risk of infection.

To measure the effectiveness of the two methods of disinfection a five-point culturing method was used to assess microbial burden. This method was used to assess patient care equipment cleanliness after manual cleaning/disinfection and following the use of FMUV after an operative case and was used to sample equipment deemed cleaned/disinfected and ready for use outside the operative environment. Microbial burden was reported as colony forming units (CFUs). Comparison of the CFUs before cleaning/disinfection, after cleaning/disinfection, and after the use of FMUV allowed efficacy of the disinfection methods to be compared. 

Continue reading

Machine Learning Program Superior to Humans in Non-Pigmented Skin Lesions Interview with:
Philipp Tschandl, MD PhD, Priv.Doz. Department of Dermatology Medical University of ViennaPhilipp Tschandl, MD PhD, Priv.Doz.
Assistant Professor
Department of Dermatology
Medical University of Vienna What is the background for this study? What are the main findings?

Response: Dermatoscopy is a non-invasive imaging technique, where the surface of the skin is rendered translucent and additional important morphologic features become visible from deeper layers. This is achieved through use of immersion fluid or cross-polarised light – equivalent to the effect when using a pair of goggles to look underwater, or polarised sunglasses to reduce glare on glass surfaces. After the first description of “Dermatoskopie” almost 100 years ago by a German dermatologist (Johann Saphier), this technique has evolved to a successful, low-cost, state-of-the-art technique for clinical skin cancer detection in the last decades.

Convolutional neural networks (“CNN”) are powerful machine learning methods, and frequently applied to medical image data in the recent scientific literature. They are highly accurate for basic image classification tasks in experimental settings, and found to be as good as dermatologists in melanoma recognition on clinical or dermatoscopic images. In this study we trained a CNN to diagnose non-pigmented skin lesions (where melanomas are only a minority) through analysis of digital images, and compared the accuracy to >90 human readers including 62 board-certified dermatologists. This study expands knowledge in the following ways compared to previous work:

– We applied the network for the detection of non-pigmented skin cancer, which is far more common in the (caucasian) population than melanoma.

– We created a prediction model that combines analysis of a dermatoscopic and clinical image (“cCNN”) which is able to further increase diagnostic accuracy.

– We compared accuracy not only to experts, but users with different level of experience Continue reading

Comparison of the Evolut R™TAVR Valve with the Evolut PRO™ Interview with:

Evolut TAVR PlatformDr. Shazia Afzal MD
University Hospital DüsseldorfMedical FacultyDivision of Cardiology, Pulmonology and Vascular Medicine, Düsseldorf, Germany What is the background for this study?

Response: Since its introduction in 2002, transcatheter aortic valve replacement (TAVR) emerged to an increasingly important interventional procedure in the field of structural heart disease. Widespread use in Europe, the USA and Canada lead to continuous technological development and improved patient’s safety, procedural success and clinical outcome.

In 08/2017 one of the market leaders introduced its latest generation valve model -the CoreValve Evolut PROTM– which was especially designed to mitigate paravalvular leakage after valve deployment. We conducted the first prospective study which directly compares the Evolut PROTM with its direct predecessor the Evolut RTM as a head-to-head analysis especially focusing on hemodynamic performance and clinical outcome in a real-world setting. To ensure comparability between groups, we performed propensity score matching with special interest in CT-derived data to guarantee equitable anatomical conditions.

Since both valves are on the market but sold at different prices the pivotal question is whether the Evolut PROTM reaches its target. In a highly budget restricted health care system with limited refunding cost-effectiveness evolves to a substantial discussion point in daily clinical practice. Our results may not be marketing friendly but we think of relevance for the interventional community.  Continue reading

AI: Deep Learning Algorithms Can Detect Critical Head CT Findings Interview with:
Qure-ai.jpgSasank Chilamkurthy

AI Scientist, What is the background for this study?

Response: Head CT scan is one of the most commonly used imaging protocols besides chest x-ray. They are used for patients with symptoms suggesting stroke, rise in intracranial pressure or head trauma. These manifest in findings like intracranial haemorrhage, midline shift or fracture.

Scans with these critical findings need to be read immediately. But radiologists evaluate the scans on first-come-first-serve basis or based on stat/routine markers set by clinicians. If the scans with critical findings are somehow pushed to the top of radiologists’ work list, it could substantially decrease time to diagnosis and therefore decrease mortality and morbidity associated with stroke/head trauma.

Continue reading

Text Messages Improved Colonoscopy Adherence Interview with:

Nadim Mahmud, MD, MS, MPH Hospital of the University of Pennsylvania

Dr. Mahmud

Nadim Mahmud, MD, MS, MPH
Hospital of the University of Pennsylvania What is the background for this study? What are the main findings?

Response: Colonoscopy is an effective screening technique for colorectal cancer (CRC) prevention, but many patients either do not show up or have poor bowel preparation for the procedure. There are many contributors to this issue, including challenges with colonoscopy bowel preparations and communication barriers between healthcare systems and their patients. To address this, we performed a pilot of 21 patients using automated text messages sent over the course of one week prior to scheduled colonoscopy. These messages included instructional, educational, and reminder messages regarding aspects of the colonoscopy preparation process.

We found significantly improved colonoscopy adherence among patients who received the text message program as compared to routine care controls (90% versus 62%). Furthermore, patient satisfaction and likelihood to recommend the text messaging program was high. Similar texting programs are simple to create and manage, and should be considered to improve outpatient colonoscopy adherence. 

Continue reading

Education Using VR Can Encourage Patients To Get Colon Cancer Screening Interview with:

Nathaniel Ernstoff, MD University of Miami

Dr. Ernstoff

Nathaniel Ernstoff, MD
University of Miami What is the background for this study? What are the main findings?

Response: Despite the best efforts of all healthcare providers, colon cancer screening is underutilized with screening rates ranging anywhere from 58-76% based on the state (American Cancer Society 2017). At best we are still failing to screen 25% of the population.  Patients have serious concerns about colorectal cancer (CRC) screening with the most common barriers to screening being fear of colonoscopy and of the bowel preparation, amongst others. These barriers coupled with the lack of understanding of the risks, benefits, and the efficacy of screening contribute to our inadequate screening.

This study aims to prove that through education, and most importantly comprehension, patients will choose one of the 6 recommended colorectal cancer screening tests that best fits their preferences. In this study we had 24 patients who previously refused colonoscopy on 3 separate occasions, and had no other CRC screening, undergo a virtual reality (VR) demonstration, created by TheBodyVR, to see if education would improve the uptake of screening. Prior to the virtual reality demonstration, the patients completed a 5-item questionnaire which evaluated their baseline knowledge of CRC risk, polyps and screening as well as determining barriers to prior screening. The patient then viewed the VR demonstration which starts with an overview of colorectal cancer, followed by a tour through a virtual colon explaining and showing the viewer polyps and cancer.

Finally, the demonstration reviews and compares the strengths and weaknesses of all USPSTF-recommended CRC screening tests.  After the study, the patients complete the same questionnaire, and in this study there was a statistically significant improvement in knowledge in all questions.  Ultimately, 23 of 24 patients who previously refused colorectal cancer screening on 3 separate occasions chose to undergo screening after the VR demonstration, and about 50% have performed the screening 60 days out from the study’s completion.

Continue reading

AI Screening for Diabetic Eye Disease May Save Time and Money Interview with:

Prof. Yogesan Kanagasingam, PhD Australian of the Year 2015 (WA Finalist) Research Director, Australian e-Health Research Centre Visiting Scholar,  Harvard University Adjunct Professor, School of Medicine University of Notre Dame

Prof. Kanagasingam

Prof. Yogesan Kanagasingam, PhD
Australian of the Year 2015 (WA Finalist)
Research Director, Australian e-Health Research Centre
Visiting Scholar,  Harvard University
Adjunct Professor, School of Medicine
University of Notre Dame What is the background for this study? What are the main findings?

Response: We wanted to evaluate how an artificial intelligence (AI)–based grading system for diabetic retinopathy will perform in a real-world clinical setting, at a primary care clinic. What should readers take away from your report?

Response: Sensitivity and specificity of the AI system compared with the gold standard of ophthalmologist evaluation is provided.

The results demonstrate both the potential and the challenges of using AI systems to identify diabetic retinopathy in clinical practice. Key challenges include the low incidence rate of disease and the related high false-positive rate as well as poor image quality. What recommendations do you have for future research as a result of this work?

Response: Low incidence rate of disease is an issue. May be a controlled environment, e.g. endocrinology clinic, may overcome this low incidence rate of diseases and high number of patients with diabetes.

Another research direction is how to improve image quality when capturing retinal images from a fundus camera.

How to overcome the issues related to sheen reflection is another research direction. Is there anything else you would like to add?

Response: At present, ophthalmologists or optometrists read all images.

If AI is introduced for image reading then, based the results from this study, ophthalmologists have to check only 8% of the images. This is a huge cost savings to the health system and save lot of time.

The accuracy rate (sensitivity and specificity) from this study is better than human graders.


Kanagasingam Y, Xiao D, Vignarajan J, Preetham A, Tay-Kearney M, Mehrotra A. Evaluation of Artificial Intelligence–Based Grading of Diabetic Retinopathy in Primary Care. JAMA Network Open. 2018;1(5):e182665. doi:10.1001/jamanetworkopen.2018.2665

Oct 6, 2018 @ 12:17 pm

The information on is provided for educational purposes only, and is in no way intended to diagnose, cure, or treat any medical or other condition. Always seek the advice of your physician or other qualified health and ask your doctor any questions you may have regarding a medical condition. In addition to all other limitations and disclaimers in this agreement, service provider and its third party providers disclaim any liability or loss in connection with the content provided on this website.


Biotricity: Deep Data and AI Bring Enhanced Value to Medical Wearables Interview with:

Waqaas Al-Siddiq

Waqaas Al-Siddiq

Waqaas Al-Siddiq
Founder and CEO of Biotricity Inc In light of Apple’s announcement that it will incorporate an EKG monitoring device into Apple watches in the near future, would you discuss your vision of the growing medical wearables market? 

Response: First of all, the public is still largely confused as to what constitutes a medical wearable device. Apple’s new watch, with its EKG monitoring service, is not a medical wearable because it will not produce clinical-grade data needed for diagnosis or treatment. This is not to say that Apple’s watch isn’t helpful. Many people are not even aware that they have a heart problem, but if their Apple watch consistently tells them that they have an irregular heart rhythm, or arrhythmia, they could take that as a sign to go to a physician and get a professional diagnosis. A physician will then prescribe a medical wearable device, such as our Bioflux, to monitor the patient’s heart rhythm. Medical-grade wearable devices produce clinical-grade data that is accurate to within 90-95 percent or higher and are prescribed by physicians to make diagnoses and treatment plans.

That being said, I envision that the medical wearables market will expand considerably with the advent of consumer-based wearables that facilitate health tracking. One of the biggest problems we have today is a lack of awareness. Anywhere between 2.7 and 6.1 million people in the U.S. suffer from atrial fibrillation – a condition that makes the heart beat irregularly – and many aren’t aware that they have the condition. Consumer-based health trackers like the Fitbit and the Apple Watch can help raise awareness and alert consumers to possible health issues, which will encourage them to see a physician for a thorough and professional examination and diagnosis. This, in turn, gives the medical wearable market a boost as more people will be diagnosed with the aid of a medical wearable. Another factor that is playing into this adoption trend is that next-generation medical wearables are increasingly becoming smaller and easier to use for both patients and physicians. So, I think that the future of medical wearables will see them firmly entrenched in mainstream practice and eventually become tools within the home for individuals with chronic issues.  Continue reading

Professor, Microbiology and Molecular Genetics
Dept of Molecular, Cellular, and Developmental Biology
University of California, Santa Barbara, CA What is the background for this study? What are the main findings?

Response: Urinary tract infections (UTIs) cause nearly 10 million doctor visits each year in the United States. Women are much more likely to have a UTI than men, and are particularly harmful to pregnant women and can cause miscarriage. Thus, there is a medical need for rapid, low-cost, on-site testing — particularly in resource-limited settings.

We developed a new app that enables a smartphone to identify (ID) bacteria causing UTIs in just one hour — a fraction of the time and cost of clinical diagnostics.

Continue reading

Experimental Cap Regrows Hair Using Photostimulation Interview with:
photostimulation of hair growthHan Eol Lee Ph.D.
Flexible and Nanobio Device Lab.
Department of Materials Science and Engineering
KAIST What is the background for this study?

Response: Numerous people around the world have suffered from alopecia, which leads to aesthetic issues, low self-esteem, and social anxiety. With the population expansion alopecia patients from middle-age down even to the twenties, a depilation treatment is expected to have social and medical impacts on billions of patients. The causes of alopecia are generally known to be heredity, mental stress, aging, and elevated male hormone. Therapeutic techniques such as thermal, electrical, pharmacological, and optical stimulation have been proposed to treat hair problems. Among them, laser stimulation to hair-lost regions is a promising technique, activating the anagen phase and the proliferation of hair follicles without side effects. However, this laser stimulation technique has drawbacks, such as high power consumption, large size, and restrictive use in daily life (e.g., the difficulty of microscale spatial control and the long time exposure of high-energy laser).  Continue reading

Artificial Intelligence Can Reliably Diagnosis Specific Types of Lung Cancer Interview with:

Aristotelis Tsirigos, Ph.D. Associate Professor of Pathology Director, Applied Bioinformatics Laboratories New York University School of Medicine

Dr. Tsirigos

Aristotelis Tsirigos, Ph.D.
Associate Professor of Pathology
Director, Applied Bioinformatics Laboratories
New York University School of Medicine What is the background for this study? What are the main findings?

Response: Pathologists routinely examine slides made from tumor samples to diagnose cancer types. We studied whether an AI algorithm can achieve the same task with high accuracy. Indeed, we show that such an algorithm can achieve an accuracy of ~97%, slightly better than individual pathologists.

In addition, we demonstrated that AI can be used to predict genes that are mutated in these tumors, a task that pathologists cannot do. Although the accuracy for some genes is as high as 86%, there is still room for improvement. This will come from collecting more training data and also from improvement in the annotations of the slides by expert pathologists.  

Continue reading

Mobile Devices Support Clinical Trials of Chronic Musculoskeletal Pain Interview with:

Richard L Kravitz, MD, MSPH Professor, General Internal Medicine Director, UC Center Sacramento

Dr. Kravitz

Richard L Kravitz, MD, MSPH
Professor, General Internal Medicine
Director, UC Center Sacramento What is the background for this study? What are the main findings? 

Response:  The study was designed to address tso problems. The first is that many patients with chronic pain struggling to find a workable regimen.

The second is more general. Patient sometimes I hesitate to participate in clinical research because they right away do not see the relevance I directly to them selves. And have one trials are away I’m addressing both problems.  Continue reading

Robotic Surgery More Expensive But May Not Have Better Outcomes Than Traditional Surgery Interview with:
A robotically assisted surgical system: WikipediaChris Childers, M.D.

Division of General Surgery
David Geffen School of Medicine at UCLA
10833 Le Conte Ave., CHS 72-247
Los Angeles, CA 90095 What is the background for this study? What are the main findings?

Response: The robotic surgical approach has gained significant traction in the U.S. market despite mixed opinions regarding its clinical benefit. A few recent randomized trials have suggested there may be no clinical benefit of the robotic approach for some surgical procedures over the more traditional open or laparoscopic (“minimally-invasive”) approaches.

Previous studies have also suggested the robotic approach is very expensive, but until our study, there was no benchmark for the true costs (to the hospital) of using the robotic platform.

Our study analyzed financial statements from the main supplier of robotic technology. We found that the use of robotic surgery has increased exponentially over the past decade from approximately 136 thousand procedures in 2008 to 877 thousand procedures in 2017. The majority of these procedures were performed in the United States. While most people think of the robotic approach in urologic and perhaps gynecologic surgery, the fastest growing segment has been general surgery, for procedures such as colorectal resections, hernia repairs and gallbladder removals. In total, over 3 billion dollars was spent by hospitals to acquire and use robotic platforms in 2017 with 2.3 billion dollars in the United States. This equates to nearly $3,600 per procedure performed.

Continue reading

Digitization of Pathology Specimens Allows for Improved Workflow and Incorporation of Advanced Techniques Interview with:|
Dr. Wendy L. Frankel, MD. Kurtz Chair and Distinguished Professor and
Dr. Anil Parwani, MD, PhD, MBA, Associate Professor
Wexner Medical Center
The Ohio State University What is the background for this work? How does digital pathology differ from traditional H/E specimens?  Is there is different processing method?  Difference in prep time or costs?

Response: Traditional pathology involves patient tissue coming to the lab and being processed. The end result is a glass slide with a stained tissue that pathologists use under a microscope. The process in digital pathology is the same, up until the point right after when the glass slide is made. In digital pathology, we put the glass slide under a scanner instead of under a microscope. The scanner creates a large file image that can be reviewed remotely by pathologists around the world.

The advantage of digital pathology, and the reason we are doing this at The Ohio State University Comprehensive Cancer Center – Arthur G. James Cancer Hospital and Richard J. Solove Research Institute (OSUCCC – James), is because when the slide is digitized, the image can be rapidly shared with an expert for review, or another institute that the patient may be going to. In addition, I can look at the image and ask the computer to quantitate different types of features that are present in the sample. While this has historically been done manually with a microscope, it’s been a more subjective process that is open to human error.

On top of that, we now have computer programs that allow us to ask very specific questions about the sample. For example, we can ask how many nuclei are in the field, how many of the nuclei show signs of cancer, and the size and color of the nucleus. These programs make the whole diagnostic process more objective and standardized. This is something we just can’t do by looking at a glass slide under a microscope.

Finally, you can also use these images for presentations at clinical conferences or for teaching residents, fellows or other pathologists. You now have the means to create an archive of patient slides and have it instantaneously available.

Continue reading

Waiting Room App Uses Selfies To Show Patients Effects of Sun Damage Interview with:
Startup Screen Dermatology APPDr. med. Titus Brinker
Head of App-Development // Clinician Scientist
Department of Translational Oncology
National Center for Tumor Diseases (NCT)
Department of Dermatology
University Hospital Heidelberg
Heidelberg What is the background for this study? What are the main findings?

Response: ​While everyone in the dermatologic community appears to agree on the importance of UV-protection for skin cancer prevention, busy clinicians often lack time to address it with their patients.

Thus, the aim of this study was to make use of waiting rooms that almost every patient visiting a clinic spends time in and address this topic in this setting by the means of modern technology rather than clinicians time.

We used our free photoaging app “Sunface” which shows the consequences of bad UV protection vs. good UV protection on the users’ own 3D-animated selfie 5 to 25 years in the future and installed it on an iPad. The iPad was then centrally placed into the waiting room of our outpatient clinic on a table and had the Sunface App running permanently. The mirroring of the screen lead to a setting where every patient in the waiting room would see and eventually react to the selfie taken by one individual patient which was altered by the Sunface App.

Thus, the intervention was able to reach a large proportion of patients visiting our clinic: 165 (60.7%) of the 272 patients visiting our waiting room in the seven days the intervention was implemented either tried it themselves (119/72,12%) or watched another patient try the app (46/27,9%) even though our outpatient clinic is well organized and patients have to wait less than 20 minutes on average. Longer waiting times should yield more exposure to the intervention. Of the 119 patients who tried the app, 105 (88.2%) indicated that the intervention motivated them to increase their sun protection (74 of 83 men [89.2%]; 31 of 34 women [91.2%]) and to avoid indoor tanning beds (73 men [87.9%]; 31 women [91.2%]) and that the intervention was perceived as fun (83 men [98.8%]; 34 women [97.1%]).

Continue reading