Dean Koh

The funds will be used by the Seqster to accelerate the adoption of their interoperability technology for clinical trials, patient engagement and outcomes.  

A new study, conducted by Korean academic hospitals and Lunit, a medical AI company specializing in developing AI solutions for radiology and oncology, demonstrated the benefits of AI-aided breast cancer detection from mammography images. The study was published online on 6 February 2020, in Lancet Digital Health and features large-scale data of over 170,000 mammogram examinations from five institutions across South Korea, USA, and the UK, consisting of Asian and Caucasian female breast images. TOP FINDINGS One of the major findings showed that AI, in comparison to the radiologists, displayed better sensitivity in detecting cancer with mass (90% vs 78%) and distortion or asymmetry (90% vs 50%). The AI was better in the detection of T1 cancers, which is categorized as early-stage invasive cancer. AI detected 91% of T1 cancers and 87% of node-negative cancers, whereas the radiologist reader group detected 74% for both. Another finding was a significant improvement in the performance of radiologists, before and after using AI. According to the study, the AI alone showed 88.8% sensitivity in breast cancer detection, whereas radiologists alone showed 75.3%. When radiologists were aided by AI, the accuracy increased by 9.5% to 84.8%. An important factor in diagnosing mammograms is breast density and dense breast tissues, mostly from the Asian population, make it harder to interpret as dense tissue is more likely to mask cancers in mammograms. According to the study’s findings, the diagnostic performance of AI was less affected by breast density, whereas radiologists' performance was prone to density, showing higher sensitivity for fatty breasts at 79.2% compared to dense breasts at 73.8%. When aided by AI, the radiologists’ sensitivity when interpreting dense breasts increased by 11%. THE LARGER TREND Findings from a study published in Nature indicated that Google’s AI model spotted breast cancer in de-identified screening mammograms with greater accuracy, with fewer false positives and false negatives than experts, HealthCareITNews reported. Lunit recently raised a $26M Series C funding from Korean and Chinese investors, which the company said was its biggest funding round, according to a DealStreetAsia report in January.  ON THE RECORD “It is an unprecedented quantity of data with accurate ground truth--especially the 36,000 cancer cases, which is seven times larger than the usual number of datasets from resembling studies conducted previously,” said Hyo-Eun Kim, the first author of the study and Chief Product Officer at Lunit.  Prof. Eun-Kyung Kim, the corresponding author of the study and a breast radiologist at Yonsei University Severance Hospital, said: “One of the biggest problems in detecting malignant lesions from mammography images is that to reduce false negatives—missed cases—radiologists tend to increase recalls, casting a wider safety net, which brings an increased number of unnecessary biopsies.” “It requires extensive experience to correctly interpret breast images, and our study showed that AI can help find more breast cancer with lesser recalls, also detecting cancers in its early stage of development.” 

Last week, Victoria-based Melbourne Pathology became the latest pathology provider to upload reports to My Health Record (MHR). This allows both patients and clinicians to have convenient and secure access to their pathology reports. Other Victorian labs sharing reports with consumers and clinicians in the MHR include Alfred Health, Monash Health and VCS Pathology. The full list of participating providers is available here.  THE LARGER TREND Last June, the Northern Territory (NT) Department of Health became the first pathology provider to link the online tests results it is sharing via MHR with Lab Tests Online, HealthcareITNews reported. In the same month, South Australia (SA) Pathology also connected to the MHR. Based on the latest statistics from the Australian Digital Health Agency (ADHA) as of December 2019, there are 22.68 million MHRs, of which 12.99 million records have information in them. ON THE RECORD “Investigation results are one of the most common tools doctors use to evaluate your health. In the 2018-2019 financial year alone, Medicare funded over 147 million pathology tests,” said Professor Meredith Makeham, a GP and Chief Medical Adviser, ADHA in a statement.  “It’s easy to quickly lose track of your results, particularly if you don’t have a regular GP or when you are seeing a range of healthcare professionals to manage multiple conditions and tests. MHR allows you to keep your important test results safe in one place, which you and your healthcare providers can access at any time to make more informed decisions about your treatment or care.” Victorian-based general practitioner, Dr Nathan Pinskier, said: “When I need a patient to have a pathology test, I simply send an electronic request and the patient attends the lab with a paper copy. Since the lab already has the electronic request, there’s no human data entry, which greatly reduces the risk of patients receiving the wrong test. Once there’s a report, I receive a copy through my secure messaging software and my patient receives a copy in their MHR, where it can’t be lost and where future healthcare providers can review it to inform their own clinical decision-making.”

The Australian Digital Health Agency (ADHA) today announced the launch of a new professional development program to identify the necessary digital health capabilities for nurses and midwives to further improve the quality, safety and efficiency of care. Nurses and midwives across Australia will now be consulted on the specific digital health skills they need, what is practical and relevant for them and how a draft digital health capability framework could be used in hospitals and health services as a professional development guide for nursing and midwifery in the digital world. Consultation will start on 3 of February 2020 and will run for six weeks. Nurses and midwives are encouraged to provide their feedback by completing a survey or attending feedback sessions through information available on the Health Informatics Society of Australia (HISA) website. The professional development program is being undertaken by HISA in collaboration with the ADHA as part of the National Digital Health Strategy’s commitment to building health workforce capability in digital health.  Once consultation is complete, the final capability framework and resources would be launched at the Nursing Informatics global congress NI 2020 in Brisbane, on 27 – 29 July 2020. WHY IT MATTERS The 2020 focus on nursing and midwifery in the digital age coincides with the World Health Organization’s International Year of the Nurse and Midwife. Critically, it is also important to ensure that the voices of nurses and midwives are heard when looking at the implementation of technology in healthcare organizations.  In an interview with HealthcareITNews last September, Katie Trott, chief nursing information officer at the Royal Free London NHS Foundation Trust said, “Often, there’s an emphasis on doctors, however, the nursing workforce is often much greater than the medical workforce. And so making sure that they’ve got full representation of that is really important, particularly as we have nurses taking on more and more extended roles where they’re seeing patients autonomously.” ON THE RECORD “In the emerging field of digital health, nurses and midwives are at the forefront, combining knowledge, data, and technology to produce best possible outcomes for patients.” “In this new program, nursing and midwifery organizations will be collaborating to create the first national framework to support nurses and midwives in an increasingly digital workplace, with all the challenges and opportunities that provides,” said HISA CEO Dr Louise Schaper in a statement. Angela Ryan, the Agency’s Chief Clinical Information Officer and a Registered Nurse, said: “Nurses and midwives are once again ensuring that they are at the center of their educational and professional development so that they can deliver the best care possible.” “This program will identify the specific skills nurses and midwives need for them to maximize the benefits for their patients from Australia’s digital health system.”

Japanese giant Sumitomo Dainippon Pharma and Oxford-headquartered AI-driven drug discovery company Exscientia yesterday announced that they have created a new compound which is in the process of entering human clinical trials in Japan. This is the first time a new precision engineered drug generated by AI is entering Phase 1 human clinical trials. The trial aims to measure the efficacy of the drug for patients with obsessive-compulsive disorder (OCD).  WHY IT MATTERS According to Exscientia, developing a single drug is around $1.75B and discovery makes up a third of that cost. This entire project was five times faster than typical discovery – it took 12 months, vs. the typical five years, with the candidate compound found within 350 synthesized compounds vs. the typical 2500 compounds.  WHAT HAPPENED The drug, which is named DSP-1181, was created through the joint research by Sumitomo Dainippon Pharma and Exscientia. The former provided its experience and knowledge in monoamine GPCR drug discovery and the latter applied its Centaur Chemist AI platform for drug discovery. THE LARGER TREND MIT's School of Engineering and Takeda Pharmaceuticals Company are also working together to drive innovation and application of AI applications for healthcare and drug development, HealthcareITNews recently reported. Last December, French AI startup Iktos and skin-health focused pharmaceutical company Almirall announced a research collaboration in AI for new drug design.  ON THE RECORD "We are very excited with the results of the joint research that resulted in the development of candidate compounds in a very short time. Exscientia's sophisticated AI drug discovery technologies combined with our company’s deep experience in monoamine GPCR drug discovery, allowed us to work synergistically, delivering a highly successful outcome. We will continue to work hard to make this clinical study a success so that it may deliver new benefits to patients as soon as possible," said Toru Kimura, Board of Directors, Senior Executive Officer and Senior Executive Research Director of Sumitomo Dainippon Pharma in a statement.  Andrew Hopkins, CEO of Exscientia, said: "We believe that this entry of DSP-1181, created using AI, into clinical studies is a key milestone in drug discovery. This project’s rapid success was through strong alignment of the integrated knowledge and experiences in chemistry and pharmacology on monoamine GPCR drug discovery at Sumitomo Dainippon Pharma with our AI technologies. We are proud that our AI drug discovery platform Centaur Chemist has contributed to generate DSP-1181 and look forward to its progression as a treatment for obsessive-compulsive disorder."

Nearing the first anniversary of the My Health Record (MHR) collection deadline on 31st January 2020, the Australian Digital Health Agency (ADHA) has announced that the total number of MHRs with information has reached 12.99 million, based on the latest statistics from December 2019. The Agency also said that between November and December 2019, there was an 11% increase in the volume of medicine documents uploaded by healthcare providers like GPs and pharmacies, to more than 100 million documents and a 13% increase in clinical documents uploaded by healthcare providers like hospitals, pathologists and radiologists. In December alone, GPs uploaded nearly 3 million documents and their viewing increased 10%. The total number of documents in the MHR system is now 1.7 billion. THE LARGER PICTURE Based on the latest statistics from ADHA as of December 2019, there are 22.68 million MHRs, of which 12.99 million records have information in them. The Agency said last year that one in 10 Australians have opted out of the MHR system, leaving participation rates at 90.1 per cent. Last December, there was a marked increase in the uploading of information to the MHR. Pharmacists uploaded more than 5 million documents, GPs uploaded nearly 3 million documents, hospitals uploaded just over 1.5 million documents and more than 1 million pathology/diagnostic images were uploaded. ON THE RECORD “While it was not expected that all My Health Records would have documents uploaded in the first year as not everyone would see a GP or other connected healthcare provider service in that timeframe, we are now seeing significant increases in uploaded clinical documents and My Health Records with valuable clinical information,” said Professor Meredith Makeham, Chief Medical Adviser, ADHA in a statement. Paul Smith, a pharmacist at Capital Chemist in Huskisson NSW, said: “In the lead up to New Year’s Eve, Huskisson and surrounding towns in NSW had an unusually large number of travelers and locals seemingly stranded without their prescriptions or regular medications. These medications included your run-of-the-mill blood pressure tablets and the like, but there were patients without their insulin, anti-epileptic medications, anti-depressants, preventative asthma inhalers, and numerous others.” “Having access to the My Health Record database certainly helped me a great deal during this unprecedented time, as I was able to ensure a continuity of care in a safe and legal fashion.”  “The main hurdle I faced was assisting patients who had chosen to opt out of the My Health Record system. It is an extremely bad situation to be in when there were no local surgeries open, the roads to the closest public hospital were closed, and the person had nothing to show you that they are normally prescribed.”

These services include digital diagnostic pathology, access to proton therapy information, teaching surgery, an AI-enabled care for in-patients and an autonomous robot for operating rooms.

ADHA has been working with industry and governments over a number of years to achieve interoperable secure messaging across different systems.

Better health information systems that allow every Thai to access their personal health information, including diabetes risk and screening records, could contribute to reducing unmet need.

“This is a big step forward in personalizing cancer treatment and ensuring better patient outcomes,” said Professor Lim Chwee Teck, Mechanobiology Institute, NUS Biomedical Engineering.