Teleneurology Bests On-Site Rounds for Postacute Stroke Care

 Survivors don't want 'care' YOU IMBECILIC BLITHERING IDIOTS! They want 100% recovery! All of you need to be fired for incompetence and leave the field!

Teleneurology Bests On-Site Rounds for Postacute Stroke Care

Teleneurology achieved near-perfect adherence to care(NOT RECOVERY!) guidelines(NOT PROTOCOLS!) in postacute stroke ward rounds, significantly outperforming conventional in-person consultations, a new study showed.Guidelines do not guarantee recovery;protocols, if done right, do!

In a prospective, multicenter, noninferiority study of more than 500 patients, use of teleneurology in ward rounds achieved 92% adherence to guidelines for such indicators as neurologic exam, diagnostic recommendations, and aftercare in postacute stroke. In-person, onsite rounds achieved just 54% adherence.

Teleneurology care(NOT RECOVERY!) also outperformed on-site care(NOT RECOVERY!) across all domains, with the largest differences seen in secondary prevention.

Janina R. Behrens, MD

While the study met its goal of demonstrating noninferiority, achieving superiority was not unexpected, said lead investigator Janina R. Behrens, MD, Department of Neurology and the Center for Stroke Research Berlin at Charité – Universitätsmediz Berlin, Berlin, Germany.

“While both telemedicine and on-site neurologists in our study were provided with the same instructions and checklists, the routine use of specific tools in everyday telemedical practice may have supported a more consistent and systematic approach, potentially reducing the likelihood of overlooking relevant aspects of care(NOT RECOVERY!),” Behrens told Medscape Medical News.

Suggested for you

The study was published online on April 6 in JAMA Neurology.

Telemedicine in Postacute Stroke?

Previous research has shown that the use of teleneurology in acute stroke care is associated with faster treatment and better outcomes. But the use of telemedicine in postacute care was unclear.

For the current study, VISIT STROKE, researchers evaluated whether teleneurologic ward rounds were noninferior to on-site consultations during subacute inpatient stroke care, with a focus on adherence to guideline-based quality measures for etiological classification, neurologic examination, risk assessment, diagnostic recommendations, secondary prevention, and recommended aftercare.

The researchers enrolled 518 patients (mean age, 71 years; 55.7% men) across 15 hospitals within four German telestroke networks, with 501 included in the final analysis.

Most patients had mild neurologic deficits and comorbidities were common, including arterial hypertension (83.3%), diabetes (29.4%), prior stroke (25.2%), and atrial fibrillation (23.5%).

Ischemic stroke was the most common diagnosis (61.5%), followed by transient ischemic attack (26.1%). Hemorrhagic stroke was rare, whereas 10% of cases were ultimately classified as stroke mimics.

Each patient received both a teleneurologic consultation and an on-site neurologic ward round within a median of 2.3 hours (IQR, 40 minutes-6 hours). Assessments were performed independently, and blinded neurovascular experts evaluated each consultation to assess guideline adherence.

Teleneurologists and on-site clinicians had the same standardized instruction and documentation tools, including standard operating procedures, checklists, and guideline-based frameworks for stroke care.

The primary outcome was adherence to the six predefined quality measures. Secondary outcomes included correctness of each individual measure and expert-rated assessments of completeness and accuracy.

Telestroke Bests On-Site Consultations

Teleneurologic ward rounds achieved complete adherence in 92% of cases (95% CI, 90%-94%) compared with 54% (95% CI, 49%-58%) for on-site consultations, exceeding the predefined noninferiority margin and demonstrating superiority.

A 38-percentage point difference was observed on average across all six quality measures. The largest gap was in secondary prevention, with a 21-percentage point difference between a 98% adherence rate with teleneurology and 77% adherence with on-site consultation.

Secondary prevention is an “area where recommendations are frequently updated and require constant integration of multiple patient-specific factors,” Behrens said.

Teleneurologic consultations were rated higher for both completeness and accuracy, with adjusted mean scores of 1.9 (95% CI, 1.6-2.2) and 1.8 (95% CI, 1.6-2.1), respectively.

Subgroup analyses supported the overall findings across patient sex, diagnosis, and timing of consultations, although one participating telestroke network achieved noninferiority but not superiority.

Study limitations included its observational design, inclusion of mostly patients with mild stroke, and lack of data on clinical outcomes, all of which limit generalizability, the researchers noted.

How Is Teleneurology Different?

The observed advantage between teleneurology and on-site may reflect differences in how care is organized, Behrens suggests.

“Teleneurological consultations are typically delivered by neurologists working within specialized stroke networks,” she said. “There is a strong focus on standardized protocols, continuous training, and adherence to current guidelines.”

In contrast, on-site consultations may occur in more variable clinical environments, with neurologists who differ in training, specialization, and familiarity with stroke-specific guidelines.

Most patients with stroke treated on wards in small rural hospitals had mild severity in the study. In the most severe cases, specifically those involving large-vessel occlusions, patients are typically transferred to thrombectomy centers, Behrens explained.

“Therefore, the concept evaluated in the study can be broadly applied to typical rural hospitals with a TeleStroke Unit,” she said.

Impact on Patient Outcomes Unknown

While interesting, the study’s findings reflect differences in training, experience level, and systems structure, said Shyam Prabhakaran, MD, chair of neurology at the University of Chicago Medicine in Chicago, who was not part of the study.

Standardized tools and decision support are key contributors to guidelines adherence, Prabhakaran told Medscape Medical News.

However, he cautioned that the results should be interpreted carefully. Although guideline adherence is an important indicator of quality, the study did not assess clinical outcomes such as functional recovery or mortality.

“We do not know that this model improves patient outcomes yet,” he said.

Incorporating teleneurology into routine postacute stroke care will require hospital buy-in and will not replace the “utility of in-person evaluation by neurologists and advanced practice providers in specific severe or unusual circumstances,” Prabhakaran said.

This study was funded by the German Innovation Fund of the Federal Joint Committee. Disclosure information for study authors is available in the original study publication. Prabhakaran reported having no relevant financial disclosures.

Videoconferencing proves feasible in addressing lower body rehab for stroke survivors, study shows

 'Feasible' GIVES ME NO CONFIDENCE AT ALL THAT YOU'LL GET ME TO 100% RECOVERY! Don't you dare use your tyranny of low expectations to justify anything less!

Videoconferencing proves feasible in addressing lower body rehab for stroke survivors, study shows

The good news is that more seniors are surviving stroke than ever before. The “bad” news is that senior living providers need to assist more residents than ever before with rehabilitation. (THE BAD NEWS IS YOU'RE NOT GOING TO GET 100% RECOVERED BECAUSE NO ONE HAS BEEN WORKING ON THAT SOLUTION!)

The need to, at the very least, provide short-term solutions, or “help bridge the service delivery gap,” opens the door for telehealth rehabilitation options, new research shows.

The researchers looked at a telehealth tool, TRAIL, which included a four-week, self-management exercise program for seniors rehabbing from stroke. The program was meant to work their lower body, and proved “feasible” in improving users’ mobility and gait, according to the results.

At least 11% of seniors in residential care facilities have had at least one stroke, the Centers for Disease Control & Prevention estimates. 

“Shortened length of inpatient stays and continued challenges in transitioning back to the community — including poor access to continued stroke rehabilitation services — have resulted in substantial unmet recovery needs,” study co-author Sarah Park said in a statement. “[Stroke survivors] can struggle to regain balance, stability and gait coordination for daily life activities and even proper ambulation.”

Importantly, the researchers did not seem to think that the telehealth option was a “preferred” option, but instead could serve as an important interim solution for seniors waiting to move into a skilled nursing facility. Rehabbing via videoconferencing also could be a critical tool in case of another emergency like the pandemic, during which in-person rehab options would be limited, the researchers noted. 

A number of tech solutions have emerged in recent months to meet the growing need for stroke recovery options. This includes smartphone apps to track movement and guide exercises with the help of artificial intelligence. Another device, an ankle-foot robotic wearable, could become available by next year.

In addition, one study from last year found that telehealth not only helps(NOT GOOD ENOUGH! Survivors want full recovery!) stroke patients with gait and lower body issues, but also cognition and vision impairment, McKnight’s reported.

The study on TRAIL was conducted by researchers at the University of British Columbia, Okanagan, in Canada, and their findings were published last month in the Physical Therapy and Rehabilitation Journal.

Secondary prevention of stroke. A telehealth-delivered physical activity and diet pilot randomised trial (ENAbLE-pilot)

You'll have to ask your doctor to get the diet protocol. I'm sure it doesn't cover all your needs post stroke.

For dementia prevention; for cognitive improvement; for cholesterol reduction; for plaque removal; for Parkinsons prevention; for inflammation reduction; etc.

Secondary prevention of stroke. A telehealth-delivered physical activity and diet pilot randomised trial (ENAbLE-pilot)

Coralie Kym English https://orcid.org/0000-0001-5910-7927 Coralie.English@newcastle.edu.au, Emily Ramage https://orcid.org/0000-0002-0599-7028, […], and Amanda Patterson+14View all authors and affiliations

Accepted Manuscripts

https://doi.org/10.1177/17474930231201360

• 
  

• • Abstract
• Get access
• • Cite article
  • Share options
  • Information, rights and permissions
  • Metrics and citations

Abstract

Background:

Improving physical activity levels and diet quality are important for secondary stroke prevention.

Aim:

To test the feasibility and safety of 6-month, co-designed telehealth-delivered interventions to increase physical activity and improve diet quality.

Methods:

2 x 2 factorial trial (physical activity [PA]; diet [DIET]; PA + DIET; control) randomised, open-label, blinded endpoint trial. Primary outcomes were feasibility and safety. Secondary outcomes included stroke risk factors (blood pressure, self-report physical activity (International Physical Activity Questionnaire [IPAQ]) and diet quality (Australian Recommended Food Score [ARFS]), and quality of life. Between-group differences were analysed using linear mixed models.

Results:

Over 23 months 99 people were screened for participation and 40 (40%) randomised (3 months to 10 years post- stroke, mean age 59 [16] years). Six participants withdrew and an additional 5 were lost to follow-up. Fifteen serious adverse events were reported, none were deemed definitely or probably related to the intervention. Median attendance was 32 (of 36) PA sessions and nine (of 10) DIET sessions. The proportion of missing primary outcome data (blood pressure) was 3% at 3 months, 11% at 6 months and 14% at 12 months. Between group 95% confidence intervals showed promising, clinically relevant difference in support of the interventions across the range of physical activity, diet quality and blood pressure outcomes.

Conclusion:

Our telehealth physical activity and diet interventions were safe and feasible and may have led to significant behaviour change.

Trial Registration:

ACTRN12620000189921

Telehealth for rehabilitation and recovery after stroke: State of the evidence and future directions

 You're putting the cart before the horse. First you create 100% recovery protocols, then you fix them so they can be delivered via telehealth.

Telehealth for rehabilitation and recovery after stroke: State of the evidence and future directions

Show all authors

Coralie English, Maria Gabriella Ceravolo, Simone Dorsch, ...

First Published January 5, 2022 Review Article 

https://doi.org/10.1177/17474930211062480

Article information

Abstract

Aims:

The aim of this rapid review and opinion paper is to present the state of the current evidence and present future directions for telehealth research and clinical service delivery for stroke rehabilitation.

Methods:

We conducted a rapid review of published trials in the field. We searched Medline using key terms related to stroke rehabilitation and telehealth or virtual care. We also searched clinical trial registers to identify key ongoing trials.

Results:

The evidence for telehealth to deliver stroke rehabilitation interventions is not strong and is predominantly based on small trials prone to Type 2 error. To move the field forward, we need to progress to trials of implementation that include measures of adoption and reach, as well as effectiveness. We also need to understand which outcome measures can be reliably measured remotely, and/or develop new ones. We present tools to assist with the deployment of telehealth for rehabilitation after stroke.

Conclusion:

The current, and likely long-term, pandemic means that we cannot wait for stronger evidence before implementing telehealth. As a research and clinical community, we owe it to people living with stroke internationally to investigate the best possible telehealth solutions for providing the highest quality rehabilitation.

Keywords

Telehealth, rehabilitation, virtual care

Access Options

 

Telehealth coaching to improve self-management for secondary prevention after stroke: A randomized controlled trial of Stroke Coach

 You would need none of this if you had EXACT STROKE PREVENTION PROTOCOLS. That would include diet. This type of intervention is needed because you blithering idiots haven't created those stroke prevention protocols. Do you not understand?

Telehealth coaching to improve self-management for secondary prevention after stroke: A randomized controlled trial of Stroke Coach

 

Show all authors

Brodie M Sakakibara, Scott A Lear, Susan I Barr, ...

First Published May 27, 2021 Research Article Find in PubMed 

https://doi.org/10.1177/17474930211017699

Article information

Abstract

Background

Stroke Coach is a lifestyle coaching telehealth program to improve self-management of stroke risk factors.

Aims

To examine the efficacy of Stroke Coach on lifestyle behavior and risk factor control among community-living stroke survivors within one-year post stroke.

Methods

Participants were randomized to Stroke Coach or an attention control Memory Training group. Lifestyle behavior was measured using the Health Promoting Lifestyle Profile II. Secondary outcomes included specific behavioral and cardiometabolic risk factors, health-related quality of life (HRQoL), cognitive status, and depressive symptoms. Measurements were taken at baseline, post-intervention (6 months), and retention (12 month). Linear mixed-effects models were used to test the study hypotheses (p < 0.05). All analyses were intention-to-treat.

Results

The mean age of the Stroke Coach (n = 64) and Memory Training (n = 62) groups was 67.2 and 69.1 years, respectively. The majority of participants (n = 100) had mild stroke (modified Rankin Scale = 1 or 2), were active, with controlled blood pressure (mean = 129/79 mmHg) at baseline. At post-intervention, there were no significant differences in lifestyle (b = −2.87; 95%CI − 8.03 to 2.29; p = 0.28). Glucose control, as measured by HbA1c (b = 0.17; 95%CI 0.17 to 0.32; p = 0.03), and HRQoL, measured using SF-36 Physical Component Summary (b = −3.05; 95%CI −5.88 to −0.21; p = 0.04), were significantly improved in Stroke Coach compared to Memory Training, and the improvements were maintained at retention.

Conclusion

Stroke Coach did not improve lifestyle behavior; however, there were improvements to HbA1c and HRQoL among community-living stroke survivors with mild stroke-related disability. (ClinicalTrials.gov identifier: NCT02207023)

Keywords Secondary prevention, health promotion, chronic disease management, behavior change, telehealth

Introduction

Stroke has considerable long-term consequences, notably deficits in motor and sensory function, communication, and cognition. These deficits pose serious barriers for stroke survivors to effectively manage their health. Unfortunately, post-discharge care remains underdeveloped for stroke survivors^1,2 and stroke survivors are observed to have high rates of secondary cerebrovascular events.³ There is a need for the development and investigation of innovative secondary prevention health services for stroke survivors.

We developed the Stroke Coach, a novel telehealth intervention to promote healthy lifestyle behaviors after stroke.^4,5 Stroke Coach was developed using Intervention Mapping as a guiding framework to ensure the intervention was theoretically guided and comprised of evidence-based behavior change techniques.⁶ Social Cognitive Theory was the underlying premise for behavior change, while Control Theory methods were directed towards sustaining the changes to ensure long-term health benefits. Furthermore, Stroke Coach is based on evidence that improvements to lifestyle can improve cardiometabolic risk,^7,8 and that the delivery of health services using technology to stroke survivors is feasible and acceptable.⁹ Stroke Coach resources and manuals are available at www.neurorehab.ubc.ca.

Aims and hypotheses

We hypothesized that individuals who participate in Stroke Coach would experience greater improvements in lifestyle behavior than individuals in an attention-controlled Memory Training Program. We also examined the effects of Stroke Coach on individual behavioral and cardiometabolic stroke risk factors, quality of life, and health outcomes.

Methods

Study design and participants

In this multi-site, single-blinded (assessors) randomized controlled trial we recruited from acute, rehabilitation, and outpatient stroke units from four regional hospitals in British Columbia, Canada. We used multiple recruitment strategies, including in-person recruitment by clinicians and research coordinators and mailouts. Participants were community-living individuals, ≥50 years of age, within one-year post-stroke, with a modified Rankin Scale (mRS)¹⁰ score of 1 to 4, and telephone access. The University of British Columbia Clinical Research Ethics Board approved the study (H13-03353), and all participants provided informed consent. This study’s protocol is reported in detail elsewhere.⁵ Appendix A documents our reporting of the study according to the consolidated standards of reporting trials (CONSORT) guidelines.¹¹

Baseline evaluation (T1 = 0 months)

Sociodemographic and stroke information were collected using a self-report form.

Primary outcome

Lifestyle behavior was measured using the 52-item Health Promoting Lifestyle Profile II (HPLPII).¹² We determined 50 participants per group would have 85% power to detect a group mean difference of 12 points^13,14 on the HPLPII (alpha = 0.05). We recruited 126 participants to adjust for a potential 20% dropout.

Secondary outcomes

Health-related quality of life (HRQoL) was measured using the Physical and Mental Component Summaries of the Medical Outcomes Study: Short Form-36.¹⁵ Depressive symptoms and cognitive function were assessed using the Center for Epidemiologic Studies Depression Scale¹⁶ and Montreal Cognitive Assessment,¹⁷ respectively.

Walking physical activity averaged over four days was measured using the StepWatch Activity Monitor.¹⁸ Daily grams of fat consumption, medication adherence, and body composition were measured using the Canadian version of the SmartDiet Questionnaire,¹⁹ Morisky Medication Adherence Scale,^a,20 and body mass index, respectively. Blood pressure measurements²¹ were taken using a digital blood pressure monitor. Glycated hemoglobin (HbA1c), fasting glucose, high- and low-density lipoprotein, C-reactive protein, and homocysteine were measured using standard outpatient blood laboratory services.

More at link.

EXPRESS: Telehealth coaching to improve self-management for secondary prevention after stroke: A randomized controlled trial of Stroke Coach

 Wrong focus. You need coaching for your doctors and hospitals to create EXACT STROKE PREVENTION PROTOCOLS. Guidelines don't count.

EXPRESS: Telehealth coaching to improve self-management for secondary prevention after stroke: A randomized controlled trial of Stroke Coach

Show all authors

Brodie M Sakakibara, Scott A Lear, Susan I Barr, , , , , , , ...

First Published May 5, 2021 Research Article 

https://doi.org/10.1177/17474930211017699

Article information

Abstract

Background: 

Stroke Coach is a lifestyle coaching telehealth program to improve self-management of stroke risk factors.

Aims: 

To examine the efficacy of Stroke Coach on lifestyle behaviour and risk factor control among community-living stroke survivors within one-year post stroke.

Methods: 

Participants were randomized to Stroke Coach or an attention control Memory Training group. Lifestyle behaviour was measured using the Health Promoting Lifestyle Profile II. Secondary outcomes included specific behavioural and cardiometabolic risk factors, health-related quality of life (HRQoL), cognitive status, and depressive symptoms. Measurements were taken at baseline, post-intervention (6 months), and retention (12 month). Linear mixed-effects models were used to test the study hypotheses (p<0.05). All analyses were intention-to-treat.

Results: 

The mean age of the Stroke Coach (n=64) and Memory Training (n=62) groups was 67.2 and 69.1 years, respectively. The majority of participants (n = 100) had mild stroke (modified Rankin Scale = 1 or 2), were active, with controlled blood pressure (mean = 129/79 mmHg) at baseline. At post-intervention, there were no significant differences in lifestyle (b = -2.87; 95%CI -8.03 to 2.29; p=0.28). Glucose control, as measured by HbA1c (b = 0.17; 95%CI 0.17 to 0.32; p=0.03), and HRQoL, measured using SF-36 Physical Component Summary (b = -3.05; 95%CI -5.88 to -0.21; p=0.04), were significantly improved in Stroke Coach compared to Memory Training, and the improvements were maintained at retention.

Conclusion: 

Stroke Coach did not improve lifestyle behaviour(Because you were giving them guidelines not exact protocols.), however, there were improvements to HbA1c and HRQoL among community-living stroke survivors with mild stroke-related disability. (ClinicalTrials.gov identifier: NCT02207023)

Keywords Chronic disease, Clinical trial, Intervention, Prevention, Rehabilitation, Risk factors, Stroke, Telemedicine

Access Options

 

In-Ambulance Stroke Consults Reduces Critical Treatment Time for Patients

But since you don't know how fast tPA needs to be delivered to get 100% recovery you have no goal to shoot for.  Please quit flailing in the dark with your research and just FUCKING SOLVE STROKE.  

So you saved 28.5 million neurons.

Big fucking whoopee.

15 minutes is nothing, you'll save 28.5 million neurons, a miniscule fraction of the billions that will be left to die by doing nothing to stop the 5 causes of the neuronal cascade of death in the first week.  You don't even know what the hell you are doing to solve stroke. GET THE HELL OUT AND LET SURVIVORS RUN IT.

Oops, I'm not playing by the polite rules of Dale Carnegie,  'How to Win Friends and Influence People'. 

Politeness will never solve anything in stroke. Yes, I'm a bomb thrower and proud of it. Someday a stroke 'leader' will ream me out for making them look bad by being truthful , I look forward to that day.

 

In-Ambulance Stroke Consults Reduces Critical Treatment Time for Patients

Prehospital stroke triaging using telestroke consultation in emergency medical services unit (TEMS) is feasible, and could result in shorter door-to-needle time and onset to groin times, according to a study published in the Journal of Stroke and Cerebrovascular Diseases.

Patients with stroke symptoms were evaluated via TEMS using a video call with a stroke provider. After TEMS evaluation, patients were transferred to the nearest stroke centre or thrombectomy capable center depending on stroke severity and symptom onset time.

“We realised that if we could start seeing these patients before they came into the emergency room, we could reduce the time it took for us to treat them,” said Christine Holmstedt, MD, Medical University of South Carolina, Charleston, South Carolina. “We compared time metrics between patients evaluated via TEMS to those via standard telestroke consultation.”

A total of 49 patients were evaluated via TEMS between May 2017 and March 2020. Median age was 66 years, 24 (49%) were females, 15 (30.6%) received intravenous alteplase (tPA) after arrival to a local hospital, and 3 (6.1%) underwent mechanical thrombectomy after bypassing the nearest stroke centre.

Compared with 52 patients who received tPA after standard telestroke consultation, TEMS patients had shorter door-to-needle time (21 min vs 38 min; P< .001). In addition, patients who received mechanical thrombectomy after bypassing the nearest stroke centre had shorter onset to groin time compared with those transferred from nearest stroke centre (216 min vs. 293 min; P = .04).

“A 15-minute reduction in door-to-treatment time leads to patients with reduced complications from tPA and significant reduction in disability or death,” said Dr. Holmstedt. “They are more likely to be discharged to an acute rehab rather than long-term care, and they have much better functional outcomes.”

This program is especially important in rural areas where patients are spread out geographically. Dr. Holmstedt is currently working to assess the economic impact of the telestroke program and the potential for further expansion.

“These improved outcomes reduce disability and even death for patients seen with acute stroke,” said Dr. Holmstedt. “And they don’t negatively impact the EMT workflow, so we can bring more efficient treatment options to the state’s rural population -- and that’s significant.”

Reference: https://www.strokejournal.org/article/S1052-3057(21)00113-0/fulltext

SOURCE: Medical University of South Carolina

 

Study: In-ambulance telehealth consultation leads to faster stroke treatment

So you saved 34.2 million neurons.

Big fucking whoopee.

 

  In 18 minutes you'll save 34.2 million neurons, a miniscule fraction of the billions that will be left to die by doing nothing to stop the 5 causes of the neuronal cascade of death in the first week.  You don't even know what the hell you are doing to solve  stroke. GET THE HELL OUT AND LET SURVIVORS RUN IT.

Hell I only lost 177 million neurons in the 90 minutes it took to get tPA. A small reduction in that is nothing compared to the 5.4 BILLION  neurons I lost in the first week. Will you please THINK about what you are doing.Maybe if you knew how fast tPA needs to be applied to get 100% recovered you would have a goal to shoot for.

 

Study: In-ambulance telehealth consultation leads to faster stroke treatment

South Carolina researchers found that door-to-treatment time was cut by 18 minutes with in-ambulance telehealth consultation

Yesterday at 1:40 PM

---

By Laura French

CHARLESTON, S.C. — A recent study found that in-ambulance telehealth consultations led to quicker treatment times for stroke patients. 

The study conducted by researchers at Medical University of South Carolina (MUSC) Health, in partnership with Georgetown Memorial Hospital and Hampton Regional Medical Center, found that door-to-treatment times were cut by about 18 minutes on average when telehealth consultations began in the ambulance, according to an MUSC press release. 

"A 15-minute reduction in door-to-treatment time leads to patients with reduced complications from tPA and significant reduction in disability or death," said Christine Holmestedt, D.O., the medical director of MUSC Health's Comprehensive Stroke Center, in a statement. "They are more likely to be discharged to an acute rehab rather than long-term care, and they have much better functional outcomes." 

The study tested a new telestroke workflow that involved three-way communication between the patient and EMS crew, a stroke specialist and staff at the receiving hospital. The in-ambulance consultations helped emergency department doctors and nurses better prepare for the patient's arrival, and also helped determine whether the ambulance should be rerouted to a comprehensive stroke center rather than the closest hospital, according to MUSC. 

"These improved outcomes reduce disability and even death for patients seen with acute stroke," Holmstedt stated. "And they don't negatively impact the EMT workflow, so we can bring more efficient treatment options to the state's rural population."

Artificial intelligence system learns to diagnose, classify intracranial hemorrhage

Fascinating idea, remove the neurologist from the equation and speed up the diagnosis considerably, wouldn't even need to set up telehealth centers.  I'm all for it.

Artificial intelligence system learns to diagnose, classify intracranial hemorrhage

Mass.-General-developed system able to ‘explain’ reasons behind decisions based on CT scan images

Credit: Hyunkwang Lee, Harvard School of Engineering and Applied Sciences, and Sehyo Yune, MD, Massachusetts General Hospital Department of Radiology

A team of investigators from the Massachusetts General Hospital (MGH) Department of Radiology has developed a system using artificial intelligence to quickly diagnose and classify brain hemorrhages and to provide the basis of its decisions from relatively small image datasets. Such a system could become an indispensable tool for hospital emergency departments evaluating patients with symptoms of a potentially life-threatening stroke, allowing rapid application of the correct treatment. The team’s report has been published online in Nature Biomedical Engineering.
While ever-increasing computational power and the availability of big datasets have improved machine learning – the process by which computers analyze data, identify patterns and essentially teach themselves how to perform a task without the direct involvement of a human programmer – important obstacles can prevent such systems from being integrated into clinical decision making. These include the need for large and well annotated datasets – previously developed imaging analysis systems capable of duplicating the performance of a physician were trained with more than 100,000 images – and the “black box” problem, the inability of systems to explain how they arrived at a decision. The U.S. Food and Drug Administration requires any decision support system to provide data allowing users to review the reasons behind its findings.
“It is somewhat paradoxical to use the words ‘small data’ or ‘explainable’ to describe a study that used deep learning,” says Hyunkwang Lee, a graduate student at the Harvard School of Engineering and Applied Sciences, one of the two lead authors of the study. “However, in medicine, it is especially hard to collect high-quality big data. It is critical to have multiple experts label a dataset to ensure consistency of data. This process is very expensive and time-consuming.”
Co-lead author Sehyo Yune, MD, of MGH Radiology adds, “Some critics suggest that machine learning algorithms cannot be used in clinical practice, because the algorithms do not provide justification for their decisions. We realized that it is imperative to overcome these two challenges to facilitate the use in health care of machine learning, which has an immense potential to improve the quality of and access to care.
To train their system, the MGH team began with 904 head CT scans, each consisting of around 40 individual images, that were labeled by a team of five MGH neuroradiologists as to whether they depicted one of five hemorrhage subtypes, based on the location within the brain, or no hemorrhage. To improve the accuracy of this deep-learning system the team – led by senior author Synho Do, PhD, director of the MGH Radiology Laboratory of Medical Imaging and Computation and an assistant professor of Radiology at Harvard Medical School – built in steps mimicking the way radiologists analyze images. These include adjusting factors such as contrast and brightness to reveal subtle differences not immediately apparent and scrolling through adjacent CT scan slices to determine whether or not something that appears on a single image reflects a real problem or is a meaningless artifact.
Once the model system was created, the investigators tested it on two separate sets of CT scans – a retrospective set taken before the system was developed, consisting of 100 scans with and 100 without intracranial hemorrhage, and a prospective set of 79 scans with and 117 without hemorrhage, taken after the model was created. In its analysis of the retrospective set, the model system was as accurate in detecting and classifying intracranial hemorrhages as the radiologists that had reviewed the scans had been. In its analysis of the prospective set, it proved to be even better than non-expert human readers.
To solve the “black box” problem, the team had the system review and save the images from the training dataset that most clearly represented the classic features of each of the five hemorrhage subtypes. Using this atlas of distinguishing features, the system is able to display a group of images similar to those of the CT scan being analyzed in order to explain the basis of its decisions.
“Rapid recognition of intracranial hemorrhage, leading to prompt appropriate treatment of patients with acute stroke symptoms, can prevent or mitigate major disability or death,” says co-author Michael Lev, MD, MGH Radiology. “Many facilities do not have access to specially trained neuroradiologists – especially at night or over weekends – which can require non-expert providers to determine whether or not a hemorrhage is the cause of a patient’s symptoms. The availability of a reliable, ‘virtual second opinion’ – trained by neuroradiologists – could make those providers more efficient and confident and help ensure that patients get the right treatment.”
Co-author Shahein Tajmir, MD, MGH Radiology adds, “In addition to providing that much needed virtual second opinion, this system also could be deployed directly onto scanners, alerting the care team to the presence of a hemorrhage and triggering appropriate further testing before the patient is even off the scanner. The next step will be to deploy the system into clinical areas and further validate its performance with many more cases. We are currently building a platform to allow for the widespread application of such tools throughout the department. Once we have this running in the clinical setting, we can evaluate its impact on turnaround time, clinical accuracy and the time to diagnosis.”

###

The additional co-authors of the Nature Biomedical Engineering are Mohammad Mansouri, Myeongchan Kim, Claude E. Guerrier, MD, Sarah A. Ebert, MD, Stuart R. Pomerantz, MD, Javier M. Romero, MD, Shahmir Kamalian, MD, and Ramon G. Gonzalez, MD, PhD, all from MGH Radiology. Support for the study includes National Institutes of Health grant 5U01 EB025153.
Massachusetts General Hospital, founded in 1811, is the original and largest teaching hospital of Harvard Medical School. The MGH Research Institute conducts the largest hospital-based research program in the nation, with an annual research budget of more than $900 million and major research centers in HIV/AIDS, cardiovascular research, cancer, computational and integrative biology, cutaneous biology, genomic medicine, medical imaging, neurodegenerative disorders, regenerative medicine, reproductive biology, systems biology, photomedicine and transplantation biology. The MGH topped the 2015 Nature Index list of health care organizations publishing in leading scientific journals and earned the prestigious 2015 Foster G. McGaw Prize for Excellence in Community Service. In August 2018 the MGH was once again named to the Honor Roll in the U.S. News & World Report list of “America’s Best Hospitals.”

Media Contact
Terri Ogan Janos
tjanos@partners.org
617-726-0954