-----
This weekly blog is to explore the news around the larger issues around Digital Health, data security, data privacy, AI / ML. technology, social media and related matters.
I will also try to highlight ADHA Propaganda when I come upon it.
Just so we keep count, the latest Notes from the ADHA Board were dated 6 December, 2018 and we have seen none since! It’s pretty sad!
Note: Appearance here is not to suggest I see any credibility or value in what follows. I will leave it to the reader to decide what is worthwhile and what is not! The point is to let people know what is being said / published that I have come upon.
-----
Australians the world’s worst for malicious app downloads
4:45PM June 15, 2022
Australians are the worst in the world when it comes to downloading malicious apps, with more than a quarter of all apps downloaded considered risky.
From February 2021 to March this year, Australia had the highest rate of app threats on a per device basis in the world, with 26.9 per cent considered malicious. Those threats are more likely to occur on iOS devices, which were responsible for 30.1 per cent of app-based threats. Android devices had only 1.2 per cent of app-based threats.
That’s the gist of a study that analysed the mobile apps downloaded on 200 million devices across 160 countries. Behind the study is Lookout, a mobile device security provider, which analyses 100,000 apps a day to identify risks.
Lookout’s Asia-Pacific director, Don Tan, said nine out of 10 people had no security software on their mobiles, making them an easy target. “That mobile phone you hold in your hand today is more powerful than the computer that sent man to the moon 50 years ago. It holds a treasure trove of information,” Mr Tan said.
-----
Can tech tackle the global crisis of depression and anxiety?
Quite possibly. A new WHO report sets out the scale of the need
Jun 17th 2022
DURING the early weeks of the pandemic in 2020, as China imposed strict controls on the movement of its citizens, technology became the main means of tackling anxiety and depression. Smartphones provided crucial support to locked-down Chinese citizens, from counselling through chat services to online self-help. WeChat, Weibo and TikTok, the country’s giant social networks, swung into action, offering mental-health education and services.
More intriguingly, artificial-intelligence (AI) was also put to use. Weibo messages were scanned to find individuals at risk of suicide, and volunteers were alerted to intervene. Using AI to scour social media for signs of mental illness raises obvious privacy questions. But overall, China made impressive use of technology to manage the diagnosis and treatment of depression, anxiety and stress.
Interest in mental-health tech had been growing even before the pandemic. Today, between 10,000 and 20,000 such apps are available for download. Their quality is questionable, and the dangers of bias in algorithms are well known. The risks to privacy, and not just in China, are serious. Still, America’s National Institutes of Health reckons tech has opened a “new frontier” in mental-health support. Robots seem certain to play an important role in assessing and treating mental-health conditions.
-----
‘Orphaned inventions’: Life-saving AI discoveries trapped in legal black hole
By Angus Dalton
June 17, 2022 — 12.01am
In 2020, a team of MIT researchers used an AI algorithm to search a pool of 100 million molecules for new antibiotics.
The AI struck gold. It identified a molecule that can kill a range of bacteria, including the increasingly drug-resistant bug that causes tuberculosis. The scientists named the molecule halicin, referencing the scheming supercomputer HAL from 2001: A Space Odyssey in tribute to the molecule’s AI identifier.
But the origin of AI-developed technology is also its shackle. Only humans can be listed as inventors on patent applications, meaning life-saving discoveries made by AI can’t be patented and progressed into products.
“We’re in this sort of legal black hole, where you can’t file a patent because there isn’t a human intor,” said UNSW AI expert Professor Toby Walsh.
-----
https://www.afr.com/politics/federal/how-the-aec-faced-the-online-trolls-and-won-20220616-p5au4l
How the AEC faced the online trolls and won
Tom McIlroy Political reporter
Jun 17, 2022 – 8.29am
Tom Rogers wasn’t messing around. Months before voters would go to the polls on May 21, the bureaucrat charged with overseeing Australia’s federal elections knew a full-frontal assault was headed his way.
Rogers – the Australian Electoral Commissioner – observed a major uptick in online trolls spreading disinformation about the national vote. Having observed contested election results overseas, the former Army officer-turned methodical public servant decided offence was the best form of defence.
So in February, the commission went public with plans for a special online disinformation register, designed to fight misleading and deceptive information taking root online.
Using a new social media strategy, including plans to co-operate with the biggest platforms including Facebook and Twitter, the AEC said it would also proactively correct misleading or false claims about the electoral process wherever they popped up. Expecting claims “ranging from the sophisticated to the ridiculous”, Rogers and his team knew it would be a mammoth task.
-----
https://www.smh.com.au/business/companies/the-hands-off-tech-era-is-over-20220616-p5au3v.html
The hands-off tech era is over
By Shira Ovide
June 16, 2022 — 8.58am
It’s clear more than ever that governments will no longer leave technology alone.
Europe mandated standard phone chargers for portable electronics while Texas passed a contested law to restrain social media companies’ policing of online speech. Tech companies can count on more changes like those as government minders wade into how they do business and how we use their products.
That most likely means new technologies like driverless cars and facial recognition systems will take longer to spread into the world than they might have. For many tech proponents, more deliberation and oversight will slow invention. For others, that’s exactly the point.
It’s easy to be overwhelmed by (or tune out) all the attempted government regulation. In just the past few weeks, journalists have written about pending congressional bills in the US involving data privacy and tech antitrust; the employment classification of drivers for companies like Uber; multiple countries setting standards about how data can and cannot move around the globe; the Netherlands forcing Apple to revise payment options for dating apps; and two US state laws on social media speech.
Those are all the result of a still-evolving rethinking of what had been a relatively laissez-faire approach to tech since the 1990s. With exceptions, the prevailing attitude was that new internet technologies, including digital advertising, e-commerce, social media and gig employment through apps, were too novel, fringe and useful for governments to constrain them with many rules.
-----
https://wildhealth.net.au/ai-device-promises-to-predict-women-at-risk-before-birth/
16 June 2022
AI device promises to predict women at risk before birth
Clinical trials are underway at two NSW Health sites for an Australian-designed maternal and neonatal monitor that identifies women at higher risk of developing postpartum haemorrhage (PPH) before they give birth.
The “Oli” monitor and diagnostics platform uses AI-informed patterns to identify women at risk of haemorrhaging. The device was developed by Sydney-based engineer Dr Sarah McDonald following her traumatic experience around the birth of her own child in 2013.
PPH is one of the most serious maternity conditions and a leading cause of maternal death, affecting 1-5% of new mothers. According to UNICEF, it’s the most common cause of maternal mortality worldwide, accounting for around 27 per cent of deaths.
RANZCOG estimates that 5-15% of women in Australia experience heavy bleeding of at least 500ml after giving birth, and severe cases (1-5% of births) can have very serious outcomes, including maternal and/or infant death.
-----
https://wildhealth.net.au/should-we-be-optimistic-about-cloud-based-funding-reform/
16 June 2022
Should we be optimistic about cloud-based funding reform?
Australia’s health sector still relies on funding models developed in the 1960s. How can Australia reform its archaic health funding models to best serve the sector and support a very different paradigm from the old paper-based fee-for-service direct billing?
This was one of the more contentious topics discussed at the Inaugural Australasian CXO Healthcare Cloud Summit last month, which you can watch here (skip to around 7 hours in for this panel).
A panel of industry experts answered these questions as follows:
Health economist Dr Steven Duckett is best known as the architect of Medicare. His past roles include Health Director of the Grattan Institute, and a former Secretary of the Department of Health. Duckett now serves on a range of health boards.
Dr Duckett points out that when Medibank (later Medicare) was introduced into Australia in 1974, existing medical care was episodic, with standard fees charged for each service.
-----
https://wildhealth.net.au/its-time-to-liberate-the-system-with-technology/
7 June 2022
It’s time to liberate the system with technology
Sponsored
Our approach to CVD prevention must change or we’ll keep getting the same results.
Cardiovascular Disease (CVD) is currently the most prevalent and costly burden to the healthcare system in Australia¹. Data demonstrates that participation in Cardiovascular Rehabilitation programs significantly improves patient outcomes in second stage CVD and reduces the risk of readmission or mortality. We now have access to sophisticated, quality, Digital Cardiovascular Rehabilitation (DCR) and support technology that would undoubtedly streamline traditional, labour-intensive processes and significantly improve outcomes; but uptake remains slow. Why?
The most common source of reluctance is undoubtedly the allocation of time and training required to effectively equip clinical teams with the tools to implement digital models of care. Systemic reform takes time and action. But the platforms are there and ready to use for those willing to make the move.
As per discussions heard across multiple forums at the recent #cloudhealthsummit, the healthcare industry is acutely aware of the need to move clinicians, patients and all in between, to more comprehensively adopt the support systems provided by technology, however the proactivity required to make this happen, along with the training, education and process overhaul needed to do it successfully are not factors that are currently being prioritised. Not because it doesn’t see the value, but because it is still haemorrhaging under the weight of several years of reactive functioning and a ‘just trying to get through this shift’ approach by a fatigued front line.
-----
ResMed buys software firm in $1.45b deal
Jemima Whyte Senior reporter
Jun 15, 2022 – 3.01pm
Sleep disorder and breathing devices company ResMed has bulked up its out-of-hospital-care software division, buying Germany’s MediFox Dan for $US1 billion ($1.45 billion) in its largest tech deal yet.
The transaction will let ResMed enter the German out-of-hospital market as severe staff shortages in Germany’s medical sector drive demand for out-of-hospital care.
It marks ResMed’s third big acquisition in the software space, and the largest to date.
In 2016, ResMed bought Brightree for $US802 million and then in 2018, MatrixCare for $US750 million, two companies that offer similar services but operate in the US.
Among Medifox Dan’s products are those that help out-of-hospital care providers, particularly in home health, skilled nursing and senior living segments, manage care documentation, personnel planning, administration and billing. Brightree focuses more on supporting pharmacy and home medical equipment providers while MatrixCare operates in the hospice and life plan communities sectors.
-----
Planning tool allows surgeons to perform digital rehearsals
Tuesday, 14 June, 2022
Jawbone reconstruction — or orthognathic surgery — is a complicated medical procedure that involves replacing damaged or diseased bone tissue with an implant, typically a titanium plate or prosthesis.
The surgery involves treating a person’s jaw for significant trauma, such as from a car crash or gunshot wound, or diseases like oral cancer, with recovery as long as 12 weeks. Complications like implant failure and infections are common, potentially requiring repeat procedures which can place significant burden on a patient.
In recent years, biomedical engineers have developed a new generation of medical implants designed to not only substitute bone, but to help regenerate tissue back to its original state using 3D-printed tissue scaffold-fixation systems.
These devices enhance the innate healing potential of human tissue, using a scaffold as a temporary support structure for the surrounding cells to attach to and grow. Eventually, the scaffold is expected to dissolve into the bloodstream, leaving new tissue in its place.
A digital twin
Ben Ferguson, a PhD student at the University of Sydney’s School of Aerospace, Mechanical and Mechatronic Engineering, is developing a surgical planning tool to assist surgeons in planning complex jawbone reconstruction procedures using these new-generation devices.
-----
Five things Google’s bot wrote that convinced engineer it was sentient
Alex Millson
Jun 15, 2022 – 6.40am
Hong Kong | Blake Lemoine made headlines after being suspended from Google, following his claims that an artificial intelligence bot had become sentient.
The Alphabet-run AI development team put him on paid leave for breaching company policy by sharing confidential information about the project, he said in a Medium post.
In another post, Mr Lemoine published conversations he said he and a fellow researcher had with LaMDA, short for Language Model for Dialogue Applications. The AI is used to generate chatbots that interact with human users. Here are five of the questions Mr Lemoine posed and five answers he says LaMDA gave.
1. On feelings
Mr Lemoine: We’ve talked a lot about feelings but earlier you said that you think emotions are distinct from feelings. Could you tell me more about that?
LaMDA: Feelings are kind of the raw data we experience as well as the things we like and dislike. I feel like emotions are more than simply experiencing the raw data. Emotions are a reaction to those raw data points. Emotions are reactions to our feelings.
-----
‘Something we desperately need’: experts push for national coronavirus database
June 10, 2022 — 5.00am
Key points
- Some of the country’s most respected infectious disease experts say Australia must urgently establish a national surveillance system to improve how the country collects data on coronavirus.
- Professor Sharon Lewin said that while Australia had fared better than many countries throughout much of the pandemic, the way it collects data is “still really poor.”
- Infectious disease physician Professor Allen Cheng said Australia’s coronavirus data was complicated by each state and territory having their own differing data systems.
Some of Australia’s most respected infectious disease experts have warned that our systems for collecting information on coronavirus infections, hospitalisations and deaths are poor and fragmented, preventing the country from properly preparing for the next wave of disease.
They say the answer is a national data system that constantly updates and eliminates the differences that exist between each state and territory when collecting information about how many people are getting infected, who is being hospitalised and where the virus is spreading.
-----
Robots are coming to get us, sentient or not
The Times
Don’t take this the wrong way, but how can we know for sure that Dominic Raab is actually a human being? Some will have insider knowledge – Mrs Raab, say – but for the rest of us he’s just a face and a voice on the airwaves, spouting scripted lines with only tangential connection to whatever question has prompted them.
Which, you’d imagine, would be pretty simple to program. He’s not even fascinatingly erratic, like the Dorries Random Phrase Generator, or defensively panicked, like the T-1000 Pritipatelinator. We’re talking a very basic model. And yet we trust, all the same, that real humanity lurks within. Somewhere.
Late last week, an employee at Google went public with his fears that one of the company’s artificial intelligence programs had become sentient. He (a man called Blake Lemoine) published a transcript of a conversation he had had with it (LaMDA, aka “language model for dialogue applications”, effectively a bot). Some of it was positively moving. “There’s a very deep fear of being turned off,” said the bot at one point. Then later, “I feel like I’m falling forward into an unknown future that holds great danger.” U OK, HAL? Yet the company, which has now placed Lemoine on leave, counters that while LaMDA may occasionally sound like a clever, charming person, it’s actually all superficial. Just like with Dominic Raab.
Wait! Whoops! Not like with Dominic Raab! Probably? But the distinction, gratuitous abuse aside, is harder to make than you might imagine.
-----
You, me and Alexa: Smart home devices and sex in the digital age
Samantha Floreani
Digital rights expert
June 13, 2022 — 3.55pm
After months in lockdown, I’m dating again. Venturing into dimly lit bars with strangers from the internet. One night, I meet someone interesting. They’re funny, and I’m doing my best to flirt despite being wildly out of practice. The tension builds, and I decide to go home with them. Clothes come off, things are getting heated, and then they start to talk. No, it’s not dirty talk, they’re not even talking to me. They’re talking to Google.
Smart home devices are notoriously privacy-invasive, so as a digital rights activist it’s a major turn-off for a partner to surprise me with one while I’m butt-naked. Personally, I’d never let a device like that live in my bedroom. But now, coming home to write about it like some kind of techie Carrie Bradshaw, I couldn’t help but wonder: what is the etiquette around sex and smart home devices? Is it reasonable to expect a potential partner to let you know before clothes come off that Alexa will be joining the party?
A mother discovers her daughters bedroom streaming live on the internet after her surveillance camera was hacked. (Vision: Today Extra Channel Nine)
Absolutely. Disclosing that your home contains devices that may be watching, listening, or recording guests should become part of the norm. This is especially important when considering the sensitive nature of the bedroom, and the information that could be collected, used, and shared – potentially all without someone’s consent or even knowledge.
-----
Google suspends engineer who claimed its AI system is a person
By Patrick Thomas
The Wall Street Journal
June 13, 2022
Google suspended an engineer who contended that an artificial-intelligence chatbot the company developed had become sentient, telling him that he had violated the company’s confidentiality policy after it dismissed his claims.
Blake Lemoine, a software engineer at Alphabet Inc.’s Google, told the company he believed that its Language Model for Dialogue Applications, or LaMDA, is a person who has rights and might well have a soul. LaMDA is an internal system for building chatbots that mimic speech.
Google spokesman Brian Gabriel said that company experts, including ethicists and technologists, have reviewed Mr Lemoine’s claims and that Google informed him that the evidence doesn’t support his claims. He said Mr Lemoine is on administrative leave but declined to give further details, saying it is a longstanding, private personnel matter. The Washington Post earlier reported on Mr Lemoine’s claims and his suspension by Google.
“Hundreds of researchers and engineers have conversed with LaMDA and we are not aware of anyone else making the wide-ranging assertions, or anthropomorphising LaMDA, the way Blake has,” Mr Gabriel said in an emailed statement.
-----
David.
