Luna Adler

home

authors

luna-adler

Social robots — human and non-humanoid machines that can interact with people &mdash; have the potential to 

 and the proliferation of exoskeleton devices. But there are many areas that have yet to be explored.

, undertook a comprehensive review of 27 trials in which social robots delivered psychosocial interventions for health and well-being. While results were largely promising, they were hindered by small sample sizes, lack of independent randomization, blind assessment or follow-up and elementary statistical analyses. The majority of the trials focused on children, the elderly and patients with autism spectrum disorder, which also limited results. Overall, it is clear that research is still at an early stage.

When emerging robotic technologies mature, researchers believe they will be useful in delivering self-guided health programs. In addition to being more cost-effective and scalable, these interventions can remove the variable of perceived human judgment.

With social robots taking over low-intensity, routine tasks, therapists would be available to do more individualized work.

“Practitioners should be spending as much time as possible on the tasks that they are trained to do incredibly well, such as counselling or caring for patients during their treatment process,” said lead researcher Nicole Robinson, Ph.D., a Research Fellow at the Australian Centre for Robotic Vision at Queensland University of Technology.

The hope is that robots will be able to complete simple tasks, demonstrate skills and communicate information.

“In an ideal scenario, healthcare practitioners are involved in the design and programming of a social robot that will work with patients on a healthcare management task,” Robinson added. “They are not designed to replace healthcare professionals in any way.”

Social robots also have the potential to cut future healthcare costs by providing preventive care. 

“Currently, we cannot provide interventions for all those who want to change their behaviors before they reach a form of diagnosis,” said Leonie Cooper, a Ph.D. candidate at the University of Plymouth in the United Kingdom and a colleague of Robinson. “Of course, many will still need to go on to see therapists, but robots can support many who need psychological support in a range of domains from alcohol usage to weight loss support.”

Increased use of robots could offer large-scale financial benefits. If robots can service a large number of patients, they will extend the reach and impact of healthcare organizations.

But to realize the widespread use of social robots, researchers must conduct large-scale controlled trials. They must conduct more research before they can understand the psychological outcomes of using robots to improve human health and well-being. Humans must also become more comfortable interacting with the machines.

Researchers believe these issues will be addressed in the coming years as technology develops and social robots become more accessible.

FDA Clears Rosa Knee Software for Robotic Knee Surgery

Ad: How Robotics Can Help Kids with Developmental Disabilities

Articles

The technology could improve self-guided health programs.

Social Robots Might Improve Psychosocial Interventions, But Results Remain Murky

Women with epilepsy are 10 times more likely to die during pregnancy than those who don’t have the condition, with seizures acting as the most likely cause of death.

Many of these deaths could be avoided if there were a prognostic model for assessing a patient’s seizure status. Knowing whether a patient is high-risk would allow practitioners to develop personalized care plans to be carried out before, during and after delivery.

A group of researchers set out to develop and externally validate a predictive model that could assess the risk status of pregnant women who are on anti-epileptic drugs. As detailed in 

, researchers determined the net benefit of implementing the EMPiRE (AntiEpileptic drug Monitoring in PREgnancy) model, using different probability thresholds so that caregivers could make informed decisions when it came to monitoring patients and administering medicine. Results suggested that the EMPiRE model displayed the highest net proportional benefit for predicted probability thresholds from 12% to 99%.

Researchers from Queen Mary University of London Shakila Thangaratinam, Ph.D., John Allottey, M.S., and Javier Zamora, Ph.D., M.S., found that using the model “could reduce the number of women unnecessarily given an intervention from as little as two to as much as 54 for every 100 women seen.”

The study recruited 527 participants from 50 hospitals in the United Kingdom. They were all pregnant women with epilepsy who were taking one of the following anti-epileptic drugs: lamotrigine, carbamazepine, phenytoin or levetiracetam. The patients were recruited at the time of their first antenatal visit and proceeded to record their seizures in diaries designed for this purpose.

Using this data, researchers developed the EMPiRE model, a simple nomogram that relies on eight items to calculate the probability that a patient will have seizures. The model relies on data gathered from predictors, such as age at first seizure and mental health history. It can be implemented during the first antenatal visit.

While current protocol treats all pregnant women with epilepsy as if they will experience seizures, the EMPiRE model’s ability to differentiate promises to reduce the number of women who endure unnecessary treatment, such as taking increased amounts of anti-epileptic drugs. It could also lift unnecessary restrictions on activity — such as driving &mdash; and cut the number of women who cease taking anti-epileptic drugs during pregnancy for fear of hurting the fetus.

Researchers believe there may be financial benefits to the EMPiRE model, as well. “There could be a reduction in both actual cost of service to the healthcare provider and improvement of quality of life for the woman,” they told 

™. Being able to accurately estimate the risks could promote a more collaborative approach to treatment for both clinicians and patients, resulting in a shared decision-making process.

While the EMPiRE model is ready for use by healthcare professionals in clinical practice, there are limitations. The model is meant for patients receiving care in high-income settings and researchers caution that, for it to be effective, there should be information available for all predictors in the model.

Moving forward, the researchers also recommend “the model be validated in different settings and populations to fully appreciate its transportability.” To assess its impact in improving health outcomes, they suggest the model be assessed via randomized trials.

Get the best insights in healthcare analytics 

Natural Cycles Is the First FDA-Approved Contraception App. But It’s Not for All Women

Pregnancy Wearables Hit the Market, Raising Questions

Healthcare Orgs Must Know Their Patients Like Target Knows Its Shoppers

The EMPiRE model could save lives and lead to increased quality of life.

New Model Could Help Predict Seizures in Pregnant Women with Epilepsy

More than a million people die or are injured each year due to adverse drug reactions (ADRs). Approximately 2 million of these incidents occur in hospital settings, leading to more than 100,000 deaths — despite the fact that the drugs in question are being prescribed by doctors at regular dosages.

Many of these deaths and injuries could be prevented if it weren’t for low rates of spontaneous reporting in the pre- and post-market stages of drug development. In fact, more than 90 percent of new ADRs remain unreported — a major problem, especially when it comes to predicting the less common adverse effects of specific drugs.

Seeking to correct this issue, researchers developed a new deep neural network (DNN) model that can both identify the ADRs of existing drugs and predict the ADRs of new drugs.

, the new DNN model used machine learning and statistical methods to identify the ADRs of 746 existing drugs and predict the ADRs of 232 new drugs. The model examined the chemical and biological information of drugs from 2009 to 2012. None of the findings were reliant on past human reportage.

The DNN model has the potential to help physicians beyond the initial point of prescribing and administering drugs. Using the new information, doctors can better evaluate the risk of ADRs, prescribe the least risky medicine for their patients, monitor for possible ADRs, and take an appropriate course of action when ADRs do occur.

In addition to aiding doctors in saving lives, there are potential financial benefits to this new DNN model.

“Developing new drugs costs a lot of money and time,” says lead researcher Jung-Hsien Chiang, Ph.D., of Taiwan’s National Cheng Kung University. “If the pharmaceutical companies can get the additional information during the new drug development stage through our DNN model, it can help them to make a safer drug and reduce the risk when it launches to market.”

In terms of next steps, Chiang believes the new DNN model must incorporate more data in order to expand the number of drugs and ADRs it can detect. This will include collecting additional medical literature and retraining the model.

“We also need to reconsider the risk of ADRs for drug-to-drug,” says Chiang. To accomplish this, researchers will examine complicating factors, such as the potential for additional adverse effects when prescribing multiple drugs simultaneously.

While more research is needed, this new DNN model could represent a large step forward in terms of patient safety and pharmacovigilance.

Navigate the digital transformation with confidence. 

Machine Learning Could Boost Feasibility of Neutron Imaging

Cellphones Can Boost Patient-Centered Care, Drug Adherence Rates

The model relied on statistics and machine learning to identify pain points, potentially saving lives.

New Deep Neural Network Model Can Predict Adverse Drug Reactions

Physical inactivity is a pressing public health issue

Contributing to this crisis are the extended hours of sedentary behavior of office workers. Digital technology interventions are a possible solution, but researchers and developers are often unclear as to which avenues have already been explored.

, researchers examined 68 articles that addressed efforts to help reduce sedentary behavior in office workers. Researchers found 45 disparate interventions and identified six technological features that were most commonly used, shining a light on where the research must focus from here.

Lead researcher Yitong Huang, M.S., says the ultimate goal was to provide an “overview of the technological landscape, in terms of what has been designed, tested, what has been scaled up and what has not but has shown promise, and is hence worth more investment to move it downstream to further evaluation and development.”

Researchers used the United Kingdom Medical Research Council (MRC) framework for developing and evaluating complex interventions to group the studies. Categories included: development, feasibility and/piloting, evaluation or implementation.

Says Huang: “In my view, with screenless digital media, wireless communication technologies and data fusion, future digital interventions will be better embedded in the physical environment and can adapt to the user’s real-time status and needs, which affords really exciting opportunities for scalable delivery of BCTs (behavior change techniques) like ‘problem-solving’ and ‘changing the social or physical environment.’”

The increasing availability of digital technology means it’s easier to try these methods. For instance, unobtrusive devices that prompt the user throughout the day with subtle reminders to move their body and take breaks from their screens have the potential to create positive change.

“The development of such interventions will require interdisciplinary and intersectoral collaborations between intervention designers, technology designers and engineers, etc.,” Huang says.

While developing these technologies may be costly in the short term, Huang believes that they will be prove financially beneficial over time.

“Healthy active lifestyles can prevent or delay the onset of many diseases or personal injuries, which does not only save healthcare expenditures for individuals and families, but also brings economic benefits to employers and the broader economy,” Huang says. “For instance, businesses with (an) active workforce can benefit from higher productivity, less absenteeism due to sickness or repetitive strain injury, less presentism and lower job turnover rates.”

But while developing this technology may save money, it’s difficult to predict the exact numbers. Each intervention must pass through multiple stages of development and evaluation before its efficacy and scalability can be known. “Cost effectiveness often needs to be determined with economic evaluation on a case-by-case basis,” Huang adds.

This study is the first to provide an overview of the efforts to minimize office workers’ SB. The results are meant to serve as a roadmap for healthcare executives trying to “locate the relevant design inputs and experts working in the field.”

Collaboration between research communities and a greater understanding of the MRC framework will be key in developing these digital technologies.

Can mHealth Apps and Text Messages Get Teens to Exercise?

Real-Time Health Data Help Patients with Diabetes Take Action

How Personalized Interactions with Robots Could Help Stroke Victims

A new review provides a roadmap for health-tech innovators who are focused on white-collar wellness.

Luna Adler

Articles

Social Robots Might Improve Psychosocial Interventions, But Results Remain Murky

New Model Could Help Predict Seizures in Pregnant Women with Epilepsy

New Deep Neural Network Model Can Predict Adverse Drug Reactions

How Digital Health Interventions Can Reduce Sedentary Behavior in Office Workers