An algorithm to predict which people may experience a mental health crisis has been trialled in the UK and found effective enough for routine use. A version that would track people’s mobile phone calls, messages and location in a bid to improve accuracy is now being considered.

Birmingham and Solihull Mental Health NHS Foundation Trust worked with Alpha, a division of Spanish telecoms firm Telefonica, which owns O2, to see if there was any benefit in automatically flagging the people thought most at risk of experiencing a mental health crisis to NHS staff. The results of the Predictive Analytics project, , suggest there is.

The project ran between November 2018 and May 2019. Alpha developed a machine-learning algorithm fed with historical patient data to predict who could face an imminent crisis. Once a fortnight, staff on four community mental health teams in Birmingham were presented with what the system calculated were the 25 people most at risk of a crisis within the next 28 days.

In some cases, healthcare professionals followed up with individuals by phone or face to face. Overall, the clinicians found the tool useful in about 64 per cent of the cases that were flagged.

An evaluation of the project concluded the tool “could become a part of routine clinical care”. That positive verdict could help the NHS trust and Alpha proceed with a mooted second phase of the research, where people’s mobile network data would also be accessed in a bid to improve the algorithm.

The team is examining whether this information could reduce the number of false positives, although exactly how this would help is unclear. It would involve Alpha having access to “call/message records and location details”, according to minutes of a of Birmingham and Solihull Mental Health NHS Foundation Trust held last October.

The project used five years’ worth of historical patient records and socioeconomic data from the NHS trust. The data was pseudonymised, where names are replaced by strings of letters and numbers.

Mining that data unearthed 22 indicators that the algorithm could use to judge if someone was at risk of an upcoming crisis, although details of those indicators are redacted in documents released by the trust.

Staff were generally positive about the project. “It highlights people that would otherwise, in my opinion, fall through the net and get lost in the system,” one person said in the evaluation.

However, there were issues too. Many of the people flagged by the system were already known to staff as being in a mental health crisis, because such events can last up to 28 days, which raised concerns that clinicians could become “dismissive” of the tool and “less inclined” to follow up people it flagged, said the report.

The consent of patients under the care of the community mental health teams wasn’t sought, as the trust says it was advised by the UK’s Health Research Authority that it wasn’t needed.

“Intervening early helps prevent people from experiencing a mental health crisis and also improves the chances of recovery, so the results of this pilot are interesting,” says Adrian James at the UK’s Royal College of Psychiatrists. “But much more research and evaluation with informed consent is needed as using data in this way is very much in its infancy.”

Allen Frances, a US psychiatrist, is more sceptical. “Predictive tools of all sorts have been available for 50 years, but have limited clinical or public health utility because they are so imprecise – identifying a great many people who don’t get into trouble, missing many who do,” he says.

Sam Smith at MedConfidential, a UK campaign group which requested the documents from the trust, urged the NHS trust to think carefully before allowing Alpha to combine people’s phone data with health records.

A spokesperson for Birmingham and Solihull Mental Health NHS Foundation Trust says: “We envisage the algorithm could be used to enhance our existing care and risk management processes. It would enhance and not replace clinical judgement and decision making.” The trust is still consulting with partners before making a decision on phase two, they added.

In a statement, Alpha said: “The phase one results have demonstrated that the algorithm has high predictive power, and that most clinicians valued the extra insights provided by the algorithm to help inform their decision making. However, the pilot study showed that there is more work to do to improve accuracy, with 7 per cent of clinicians disagreeing with predictions.

“Phase two aims to improve the accuracy of the predictions by adding complementary data to the algorithm, however we have not yet made a final decision on how we would proceed.”

This month, the NHS signed its first deals with Google. Five NHS trusts have agreed contracts with Google Health, after it , nearly a year after .

żěè¶ĚĘÓƵ first revealed the extent of DeepMind’s access to the sensitive data of more than a million National Health Service patients back in 2016, in a deal that the UK’s data watchdog later found breached the law. The partnership has yielded interesting research, including using artificial intelligence to detect eye disease from scans with an .

But is there a material difference now the deals are with the US tech giant rather than DeepMind, and should people who use the NHS be concerned at the change?

Five trusts, including the Royal Free Hospital and Moorfields Eye Hospital, have transferred their contracts over to Google Health. Taunton and Somerset NHS trust is among them, but will not use the company’s Streams app, which helps keep track of patients’ test results. Yeovil District Hospital NHS trust chose instead to end its contract, saying it didn’t find the app necessary.

We don’t know exactly what data sharing is occurring with Google Health, but the included anonymised data such as treatment dates, medical history, diagnoses, ethnic origin and religion.

“Transparency is paramount here. Is Google Health going to be as transparent as DeepMind was?” asks Phil Booth of campaign group MedConfidential. DeepMind took the unusual step of publishing its contracts, but Google Health has not. It says the public can access the documents by asking individual NHS trusts.

Dominic King of Google Health says: “There are very minimal changes to the contracts as they moved over. The updates have been about changes related to the GDPR [EU data law], which wasn’t in force when some of the contracts were done a couple of years ago.”

David Maguire of The King’s Fund think tank questions why the contracts aren’t being published. “It creates an unnecessary uncertainty, which isn’t great for assuaging people’s fears. There’s a legitimate thing about people feeling nervous about how their data is used.”

One change is the data is no longer being stored by a third party contracted by Google. It is now on , which , stored on servers in the UK, and backed up elsewhere in the EU.

Another shift is the abolition of the independent ethics panel that DeepMind established, but that Google Health says doesn’t fit with its international scope. Booth says that although the panel was a “damp squib”, it provided a “level of reassurance” on oversight. King says the firm is heavily scrutinised by its executive board, its partners and regulators.

While patients can opt out of their data being shared with Google, under the NHS’s , hospitals don’t have to be compliant with the opt-out until next year.

Some observers also have concerns over potential cultural changes during the switchover to Google Health.

“Previously the DeepMind Health leadership involved in the actual work in London were well known on the internet scene in the UK as being very ethically minded,” says Tom Loosemore of consultancy Public Digital. “They have now left, because of Google Health taking over.”

However, King says: “The same team that I led in DeepMind Health is the same team that will be working with our partners going forward.”

Whether patients at the five NHS trusts should be worried is ultimately hard to say. “The problem is: how can I know?” says Loosemore. “Would I personally trust Google? No I damn well wouldn’t, I’d want that transparency.”

The UK health regulator has taken the first step towards NHS England lifting a temporary ban on the use of vaginal mesh implants.

The implants are used to treat incontinence and prolapse in women, often after childbirth. Their use was paused last year to allow for a safety review, after women reported severe pain and complications. Around one in 10 recipients have had complications within five years of surgery, .

Now the National Institute for Health and Care Excellence (NICE) has said the ban could be lifted . These include establishing a national database to record procedures and complications, and that only specialist surgeons at specialist centres carry out the surgery.

The guidelines also recommend that people are offered booklets, called “decision aids”, that clearly set out the possible risks of vaginal mesh implants. Women who opt for surgery over physical therapies should be warned that the implants may cause pain, including during sex.

But campaigners say the new guidelines aren’t materially different from ones published 16 years ago, a charge the regulator rejects, citing the fact the old guidelines did not include decision aids. “They are so weak, they clear the way for the next generation of women to be harmed,” Kath Sansom of Sling The Mesh said in a statement.