Tag: 4/6/24

AI Analyses Fitbit Data to Predict Spine Surgery Outcomes

Photo by Barbara Olsen on Pexels

Researchers who had been using Fitbit data to help predict surgical outcomes have a new method to more accurately gauge how patients may recover from spine surgery.

Using machine learning techniques developed at the AI for Health Institute at Washington University in St. Louis, Chenyang Lu, the Fullgraf Professor in the university’s McKelvey School of Engineering, collaborated with Jacob Greenberg, MD, assistant professor of neurosurgery at the School of Medicine, to develop a way to predict recovery more accurately from lumbar spine surgery.

The results show that their model outperforms previous models to predict spine surgery outcomes. This is important because in lower back surgery and many other types of orthopaedic operations, the outcomes vary widely depending on the patient’s structural disease but also varying physical and mental health characteristics across patients. The study is published in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies.

Surgical recovery is influenced by both preoperative physical and mental health. Some people may have catastrophising, or excessive worry, in the face of pain that can make pain and recovery worse. Others may suffer from physiological problems that cause worse pain. If physicians can get a heads-up on the various pitfalls for each patient, that will allow for better individualized treatment plans.

“By predicting the outcomes before the surgery, we can help establish some expectations and help with early interventions and identify high risk factors,” said Ziqi Xu, a PhD student in Lu’s lab and first author on the paper.

Previous work in predicting surgery outcomes typically used patient questionnaires given once or twice in clinics that capture only one static slice of time.

“It failed to capture the long-term dynamics of physical and psychological patterns of the patients,” Xu said. Prior work training machine learning algorithms focus on just one aspect of surgery outcome “but ignore the inherent multidimensional nature of surgery recovery,” she added.

Researchers have used mobile health data from Fitbit devices to monitor and measure recovery and compare activity levels over time but this research has shown that activity data, plus longitudinal assessment data, is more accurate in predicting how the patient will do after surgery, Greenberg said.

The current work offers a “proof of principle” showing, with the multimodal machine learning, doctors can see a much more accurate “big picture” of all the interrelated factors that affect recovery. Proceeding this work, the team first laid out the statistical methods and protocol to ensure they were feeding the AI the right balanced diet of data.

Prior to the current publication, the team published an initial proof of principle in Neurosurgery showing that patient-reported and objective wearable measurements improve predictions of early recovery compared to traditional patient assessments. In addition to Greenberg and Xu, Madelynn Frumkin, a PhD psychological and brain sciences student in Thomas Rodebaugh’s laboratory in Arts & Sciences, was co-first author on that work. Wilson “Zack” Ray, MD, the Henry G. and Edith R. Schwartz Professor of neurosurgery in the School of Medicine, was co-senior author, along with Rodebaugh and Lu. Rodebaugh is now at the University of North Carolina at Chapel Hill.

In that research, they show that Fitbit data can be correlated with multiple surveys that assess a person’s social and emotional state. They collected that data via “ecological momentary assessments” (EMAs) that employ smart phones to give patients frequent prompts to assess mood, pain levels and behaviour multiple times throughout day.

We combine wearables, EMA -and clinical records to capture a broad range of information about the patients, from physical activities to subjective reports of pain and mental health, and to clinical characteristics,” Lu said.

Greenberg added that state-of-the-art statistical tools that Rodebaugh and Frumkin have helped advance, such as “Dynamic Structural Equation Modeling,” were key in analyzing the complex, longitudinal EMA data.

For the most recent study they then took all those factors and developed a new machine learning technique of “Multi-Modal Multi-Task Learning (M3TL)” to effectively combine these different types of data to predict multiple recovery outcomes.

In this approach, the AI learns to weigh the relatedness among the outcomes while capturing their differences from the multimodal data, Lu adds.

This method takes shared information on interrelated tasks of predicting different outcomes and then leverages the shared information to help the model understand how to make an accurate prediction, according to Xu.

It all comes together in the final package producing a predicted change for each patient’s post-operative pain interference and physical function score.

Greenberg says the study is ongoing as they continue to fine tune their models so they can take these more detailed assessments, predict outcomes and, most notably, “understand what types of factors can potentially be modified to improve longer term outcomes.”

Source: Washington University in St. Louis

New Human Monoclonal Antibodies could Fight Influenza B

Creative artwork featuring colourised 3D prints of influenza virus (surface glycoprotein hemagglutinin is blue and neuraminidase is orange; the viral membrane is a darker orange). Note: Not to scale. Credit: NIAID

Researchers at Vanderbilt University Medical Center have isolated human monoclonal antibodies against influenza B, a significant public health threat that disproportionately affects children, the elderly and other immunocompromised individuals, as they report in the journal Immunity.

Seasonal flu vaccines cover influenza B and the more common influenza A but do not stimulate the broadest possible range of immune responses against both viruses.

In addition, people whose immune systems have been weakened by age or illness may not respond effectively to the flu shot.

Small-molecule drugs that block neuraminidase, a major surface glycoprotein of the influenza virus, can help treat early infection, but they provide limited benefit when the infection is more severe, and they are generally less effective in treating influenza B infections. Thus, another way to combat this virus is needed.

The VUMC researchers describe how, from the bone marrow of an individual previously vaccinated against influenza, they isolated two groups of monoclonal antibodies that bound to distinct parts of the neuraminidase glycoprotein on the surface of influenza B.

One of the antibodies, FluB-400, broadly inhibited virus replication in laboratory cultures of human respiratory epithelial cells. It also protected against influenza B in animal models when given by injection or through the nostrils.

Intranasal antibody administration may be more effective and have fewer systemic side effects than more typical routes – intravenous infusion or intramuscular injection – partly because intranasal antibodies may “trap” the virus in the nasal mucus, thereby preventing infection of the underlying epithelial surface, the researchers suggested.

These findings support the development of FluB-400 for the prevention and treatment of influenza B and will help guide efforts to develop a universal influenza vaccine, they said.

“Antibodies increasingly have become an interesting medical tool to prevent or treat viral infections,” said the paper’s corresponding author, James Crowe Jr, MD. “We set out to find antibodies for the type B influenza virus, which continues to be a medical problem, and we were happy to find such especially powerful molecules in our search.”

Source: Vanderbilt University Medical Center

Ancient Medicinal Minerals Inspire New Tissue Repair Technology

Photo by MJ RAHNAMA

For centuries, civilizations have used naturally occurring, inorganic materials for their perceived healing properties. Egyptians thought green copper ore helped eye inflammation, the Chinese used cinnabar for heartburn, and Native Americans used clay to reduce soreness and inflammation.

Today, researchers at Texas A&M University are still discovering ways that inorganic materials can be used for healing.

In two recently published articles, Dr Akhilesh Gaharwar, a Tim and Amy Leach Endowed Professor in the Department of Biomedical Engineering, and Dr Irtisha Singh, assistant professor in the Department of Cell Biology and Genetics, uncovered new ways that inorganic materials can aid tissue repair and regeneration.

The first article, published in Acta Biomaterialia, explains that cellular pathways for bone and cartilage formation can be activated in stem cells using inorganic ions. The second article, published in Advanced Science, explores the usage of mineral-based nanomaterials, specifically 2D nanosilicates, to aid musculoskeletal regeneration.

“These investigations apply cutting-edge, high-throughput molecular methods to clarify how inorganic biomaterials affect stem cell behavior and tissue regenerative processes,” Singh said.

The ability to induce natural bone formation holds promise for improvements in treatment outcomes, patient recovery times and the reduced need for invasive procedures and long-term medication.

“Enhancing bone density and formation in patients with osteoporosis, for example, can help mitigate the risks of fractures, lead to stronger bones, improve quality of life and reduce healthcare costs,” Gaharwar said. “These insights open up exciting prospects for developing next-generation biomaterials that could provide a more natural and sustainable approach to healing.”

Gaharwar said the newfound approach differs from current regeneration methods that rely on organic or biologically derived molecules and provides tailored solutions for complex medical issues.

“One of the most significant findings from our research is the ability of these nanosilicates to stabilise stem cells in a state conducive to skeletal tissue regeneration,” he said. “This is crucial for promoting bone growth in a controlled and sustained manner, which is a major challenge in current regenerative therapies.”

Gaharwar recently received a grant for his work in using inorganic biomaterials in conjunction with 3D bioprinting techniques to design custom bone implants for reconstructive injuries.

“In reconstructive surgery, particularly for craniofacial defects, induced bone growth is crucial for restoring both function and appearance, vital for essential functions like chewing, breathing and speaking,” he said. “Inducing bone formation has several critical applications in orthopaedics and dentistry.”

“This approach not only bridges ancient practices with modern scientific methods but also minimises the use of protein therapeutics, which carry risks of inducing abnormal tissue growth and cancerous formations,” Gaharwar said. “Collectively, these findings elucidate the potential of inorganic biomaterials to act as powerful mediators in tissue engineering and regenerative strategies, marking a significant step forward in the field.”

Source: Texas A&M University

Who will be SA’s Minister of Health in the New Cabinet?

By Marcus Low

ANC President Cyril Ramaphosa, with Minister of Health, Dr Joe Phaahla and his deputy Dr Sibongiseni Dhlomo, during the signing into law of the National Health Insurance Bill. (Photo: @MYANC/Twitter)

After the ANC received less than 41% of the votes in last week’s national elections, negotiations are now underway that will determine how and by who South Africa is governed. Ministerial posts, including the country’s top health job, might be on the negotiating table. Spotlight considers the candidates for the post of South Africa’s Minister of Health.


For most of the last 30 years, it went almost without saying that the country’s Minister of Health would be drawn from the ranks of the ANC. But given the dramatic decline in the party’s electoral fortunes and the consequent pressure to enter into coalitions or other deals, the pool of realistic candidates for the post of health minister might this year be larger than before.  

The President has the prerogative to appoint any members of the National Assembly as ministers, whether or not they are of the same party as the President. The President can also at his or her discretion appoint two ministers who are not members of parliament. It is also relatively trivial for a party to ask a Member of Parliament (MP)  to stand down and to have another sworn in, as happened with Minister of Electricity Kgosientsho Ramokgopa. This means that candidates who were not high enough on party lists to get seats in parliament could still be substituted in. 

Although technically the pool of possible health ministers is thus quite large, political realities narrow the choices down considerably. 

Let’s start with candidates from the ANC, given that odds are still that our next health minister will be from the party. 

First in line is South Africa’s current Minister of Health Dr Joe Phaahla. He is not on the ANC’s national candidates list, but he is high up on the party’s regional list for Limpopo and thus set to become a member of the National Assembly. Though some might describe his time as health minister over the last three years as uninspiring, he also hasn’t been implicated in any scandals or made any obvious blunders.

It might well be that President Cyril Ramaphosa, presuming he stays in the job, sees Phaahla as a safe pair of hands and considers him the right person to drive the ANC’s stated goal of preparing for and starting the implementation of National Health Insurance. Phaahla previously served for some years as Deputy Minister of Health. 

Second in line is the current Deputy Minister of Health Dr Sibongiseni Dhlomo. He is also not on the ANC’s national list, but he is high up on the ANC’s KwaZulu-Natal regional list and thus also set to join the National Assembly. He is a former MEC of health for KwaZulu-Natal and former chair of parliament’s portfolio committee for health. If Phaahla is not to return, Dhlomo would be the most natural replacement. 

After those first two candidates, things get much harder to predict. 

Former health ministers Dr Aaron Motsoaledi and Mmamoloko Kubayi are on the ANC’s national list and Dr Zweli Mkhize is on the ANC’s KwaZulu-Natal regional list. Given that Motsoaledi’s time at Home Affairs has been something of a disaster, it is not impossible that Ramaphosa might feel he can get more out of him back in the health portfolio where his record was somewhat better.

A return of Mkhize to the health portfolio seems extremely unlikely given the grubby circumstances under which he left. Kubayi’s role for a few months as acting health minister was really just that of a care-taker, and a return is unlikely. 

One interesting trend is that the ANC has largely chosen medical doctors as health ministers and deputy ministers – Phaahla, Dhlomo, Motsoaledi, and Mkhize are all medical doctors. 

Current Eastern Cape MEC for Health Nomakhosazana Meth is high on the ANC’s national list, though the poor performance of the Eastern Cape Department of Health in recent years should mean her chances of getting the top health job are slim.

In previous years, current Limpopo MEC for Health Dr Phophi Ramathuba was considered a possibility by some, but her name is only on the ANC’s candidates list for the Limpopo legislature and a few ill-judged incidents, such as a video in which she berated a pregnant woman, would make her a controversial choice. She’s also often been at loggerheads with unions in Limpopo. A lack of standing with healthcare workers may also hold back the prospects of one or two others with health backgrounds who did make it onto the ANC’s national list. 

Candidates from other parties 

The DA remains South Africa’s official opposition. Should they become part of a ruling coalition or government of national unity, the current Western Cape MEC for Health would be the party’s most obvious candidate for the role of health minister. Mbombo is however only on the DA’s list for the Western Cape legislature and is thus likely to again be the province’s MEC for health.

Jack Bloom, the party’s leading health MPL in Gauteng over the last two decades would be a long shot for the post of health minister, as would Dr Karl le Roux, an award-winning rural doctor who has joined the party. Bloom is on the DA’s list for the provincial legislature and not on the lists for the national assembly. It is thus not entirely out of the question that he could become MEC for health in Gauteng.  

The EFF received the fourth most votes nationally, having been third in the previous national elections. In the previous parliament they were represented on the portfolio committee for health by Dr Sophie Thembekwayo (not a medical doctor) and Naledi Chirwa. Chirwa is last on the EFF’s national candidates list and is thus very unlikely to return to the National Assembly. Thembekwayo is 36th on the EFF’s national candidates list. 

It is also possible that other parties such as MK or the IFP could end up as part of a governing coalition or government of national unity and that candidates from these parties would thus also be in with an outside chance for the top health job. There will be many new, and to us unknown, faces in parliament – no doubt we’ve missed some people with solid health backgrounds in our analysis. 

As mentioned earlier, the President can appoint two ministers to his or her Cabinet from outside the National Assembly. It is thus possible that someone with health management expertise could be roped in from outside the usual political circles.

Though very long shots, outsiders like Dr Fareed Abdullah – former CEO of the South African National AIDS Council and an important player in the early days of HIV treatment – or Professor Glenda Gray – outgoing President of the South African Medical Research Council – might well, and arguably should, be considered. Though we’d be surprised if strong outsider candidates like these two are interested in the job given how politically fraught the role is likely to be. That said, we suspect the right outsider candidate would be a hit in healthcare circles. 

Ultimately, whichever way the current negotiations pan out, the ball remains in the ANC’s court when it comes to determining who will be our next Minister of Health. That means the decision is likely to remain subject to the ANC’s internal politics, with all the complexities that entails.

Despite all the intriguing possibilities, chances are thus that it will be Phaahla or Dhlomo who get the nod – and in terms of South Africa’s healthcare trajectory things will probably remain roughly as they are now. 

Republished from Spotlight under a Creative Commons licence.

Read the original article