Machine learning algorithms for detection of visuomotor neural control differences in individuals with PASC and ME

Abstract:

The COVID-19 pandemic has affected millions worldwide, giving rise to long-term symptoms known as post-acute sequelae of SARS-CoV-2 (PASC) infection, colloquially referred to as long COVID. With an increasing number of people experiencing these symptoms, early intervention is crucial. In this study, we introduce a novel method to detect the likelihood of PASC or Myalgic Encephalomyelitis (ME) using a wearable four-channel headband that collects Electroencephalogram (EEG) data. The raw EEG signals are processed using Continuous Wavelet Transform (CWT) to form a spectrogram-like matrix, which serves as input for various machine learning and deep learning models. We employ models such as CONVLSTM (Convolutional Long Short-Term Memory), CNN-LSTM, and Bi-LSTM (Bidirectional Long short-term memory). Additionally, we test the dataset on traditional machine learning models for comparative analysis.

Our results show that the best-performing model, CNN-LSTM, achieved an accuracy of 83%. In addition to the original spectrogram data, we generated synthetic spectrograms using Wasserstein Generative Adversarial Networks (WGANs) to augment our dataset. These synthetic spectrograms contributed to the training phase, addressing challenges such as limited data volume and patient privacy. Impressively, the model trained on synthetic data achieved an average accuracy of 93%, significantly outperforming the original model.

These results demonstrate the feasibility and effectiveness of our proposed method in detecting the effects of PASC and ME, paving the way for early identification and management of the condition. The proposed approach holds significant potential for various practical applications, particularly in the clinical domain. It can be utilized for evaluating the current condition of individuals with PASC or ME, and monitoring the recovery process of those with PASC, or the efficacy of any interventions in the PASC and ME populations. By implementing this technique, healthcare professionals can facilitate more effective management of chronic PASC or ME effects, ensuring timely intervention and improving the quality of life for those experiencing these conditions.

Source: Harit Ahuja, Smriti Badhwar, Heather Edgell, Lauren E. Sergio, Marin Litoiu. Machine learning algorithms for detection of visuomotor neural control differences in individuals with PASC and ME. Front. Hum. Neurosci. Sec. Brain-Computer Interfaces, Volume 18 – 2024 | doi: 10.3389/fnhum.2024.1359162 https://www.frontiersin.org/articles/10.3389/fnhum.2024.1359162/full (Full text)

What do infectious disease specialists think about managing long COVID?

Abstract:

This survey of infectious disease providers on long COVID care revealed a lack of familiarity with existing resources, a sentiment of missing guidelines, and scarcity of dedicated care centers. The low response rate suggests that infectious disease specialists do not consider themselves as the primary providers of long COVID care.

Long COVID (or post-acute sequelae of COVID-19, PASC) complicates an estimated 10–30% of non-hospitalized cases and 50–70% of hospitalized cases of acute SARS-CoV-2 infection.(Reference Davis, McCorkell, Vogel and Topol1) The work-up often requires multiple disciplines to collaborate, both for diagnostic evaluation and for offering symptomatic treatment.(Reference Parker, Brigham and Connolly2) For this purpose, an infrastructure of so-called long COVID clinics has been developing,(Reference Vanichkachorn, Newcomb and Cowl3) oftentimes under the supervision of a single medical specialty. Given that long COVID is a complication of an infection, the medical subspecialty of infectious diseases (ID) has frequently been involved in devising and running such clinics. Here, we intended to survey ID providers in North America regarding their role in managing long COVID and their perspective on the availability of resources. For this purpose, we used the Emerging Infections Network (EIN), which is a provider-based sentinel network funded by the Infectious Diseases Society of America and the Centers for Disease Control and Prevention (http://ein.idsociety.org/). Our implicit hypothesis was that ID providers are insufficiently equipped to provide long COVID care because neither infection work-up nor antiviral treatment play a role in current management.

We designed a questionnaire, tested it among peers, and sent it out to all 2,978 EIN listserv subscribers on 3 occasions between February 7 and February 26, 2023. The survey contained 8 questions, 7 of which were structured questions. There was an option to make additional open-text field comments.

The response rate was very low, with 117 of 2,978 providers who filled out the survey (3.9%). Of these 117, 46 stated that they did not care for long COVID patients, and we analyzed the responses of the remaining 71 providers (2.4% of 2,978). Most of these would see long COVID patients once a month or less often (50/71). Thirteen indicated they were specifically seeing long COVID patients. Only 15 out of 71 (21%) felt “very comfortable” in making a diagnosis of long COVID, and most thought the resources available to clinicians involved in long COVID care were inadequate (55%) or were unaware of such resources (18%). The management consists mostly of a case-by-case-based approach without standardization (55%), followed by behavioral education for energy conservation (44%). Access to a long COVID clinic was considered easy by only 17%, while 48% stated there was no dedicated clinic located nearby, and 35% highlighted that locally available clinics were not easily accessible.

The open-text field answers were notable for showing that long COVID is a “complicated syndrome, currently without a specialty home” and that it is not easy to provide “holistic care to patients in our existing system.” Also, the absence of straightforward definitions, national guidelines, and dedicated research was pointed out. Lastly, one provider argued that “this is a primary care issue with collaboration with any needed specialists.”

The low response rate, the small percentage of ID providers heavily involved in long COVID care, and some free text statements can be seen as key findings of our survey. Our interpretation is that long COVID—although originating from an acute infection—is not perceived to be in the wheelhouse of the infectious diseases subspecialty. Infectious disease providers may not consider themselves as well-equipped as a generalist such as primary care providers.(Reference Berger, Altiery, Assoumou and Greenhalgh4) Long COVID patients, however, are likely to benefit from designated points of generalist care, with access to pertinent medical specialties and rehabilitative services (physical therapy, occupational health, and mental health), in order to receive comprehensive management for their signs and symptoms. In addition, widespread healthcare worker burnout in the wake of the pandemic may contribute to a subjective saturation with COVID-19-related topics and have reduced survey participation.

A minority of responders considered themselves very comfortable in diagnosing long COVID, the resources for appropriate clinical care were mostly felt to be inadequate, and management seems to happen on a case-by-case base (i.e., non-standardized). This points to the general unease about what constitutes best practice in long COVID care. We speculate that similar findings would be encountered in other medical specialties. Also, there is a considerable need for more research in the field, as evidenced by a recent award by the Agency for Healthcare Research and Quality to study new models of delivery of long COVID care (https://www.ahrq.gov/coronavirus/long-covid-grant-awards.html).

In conclusion, our survey of infectious disease providers and their perspective on long COVID care suggested a lack of familiarity with existing resources, a sentiment of missing guidelines, and scarcity of dedicated care centers. In addition, the low response rate to this survey can be interpreted as ID providers not regarding their specialty as the primary point of contact for delivering long COVID care.

Source: Lyons MD, Beekmann SE, Polgreen PM, Marschall J. What do infectious disease specialists think about managing long COVID? Antimicrobial Stewardship & Healthcare Epidemiology. 2023;3(1):e236. doi:10.1017/ash.2023.519 https://www.cambridge.org/core/journals/antimicrobial-stewardship-and-healthcare-epidemiology/article/what-do-infectious-disease-specialists-think-about-managing-long-covid/E89D7EA86E873D517D24FBB20D304A8D (Full text)

 

The long-term health outcomes, pathophysiological mechanisms and multidisciplinary management of long COVID

Abstract:

There have been hundreds of millions of cases of coronavirus disease 2019 (COVID-19), which is caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). With the growing population of recovered patients, it is crucial to understand the long-term consequences of the disease and management strategies.

Although COVID-19 was initially considered an acute respiratory illness, recent evidence suggests that manifestations including but not limited to those of the cardiovascular, respiratory, neuropsychiatric, gastrointestinal, reproductive, and musculoskeletal systems may persist long after the acute phase. These persistent manifestations, also referred to as long COVID, could impact all patients with COVID-19 across the full spectrum of illness severity.

Herein, we comprehensively review the current literature on long COVID, highlighting its epidemiological understanding, the impact of vaccinations, organ-specific sequelae, pathophysiological mechanisms, and multidisciplinary management strategies. In addition, the impact of psychological and psychosomatic factors is also underscored.

Despite these crucial findings on long COVID, the current diagnostic and therapeutic strategies based on previous experience and pilot studies remain inadequate, and well-designed clinical trials should be prioritized to validate existing hypotheses. Thus, we propose the primary challenges concerning biological knowledge gaps and efficient remedies as well as discuss the corresponding recommendations.

Source: Li, J., Zhou, Y., Ma, J. et al. The long-term health outcomes, pathophysiological mechanisms and multidisciplinary management of long COVID. Sig Transduct Target Ther 8, 416 (2023). https://doi.org/10.1038/s41392-023-01640-z https://www.nature.com/articles/s41392-023-01640-z (Full text)

Re: What happens inside a long covid clinic?

Dear Editor

As a patient with severe long covid and myalgic encephalomyelitis (M.E.), I was pleased to see the article ‘What happens in a long covid clinic?’ [1] raising awareness of the scale and impact of long covid and the importance of long covid clinics. According to a recent estimate by Altmann et al, 1 in 10 people who contract COVID-19 will be affected by long covid, whilst the oncoming impact of long covid on health systems, populations and economies will be “so large as to be unfathomable”.[2]

Around 2-14% of patients with long covid develop orthostatic tachycardia six to eight months after COVID infection and as many as 60% show some symptoms of POTS. [3] Yet there remain no agreed guidelines for POTS in long covid, making the early diagnosis and management of the condition in primary care challenging. NICE guidance on long covid only mentions POTS in passing with no information on management.[4] The approach outlined by Espinosa-Gonzalez and colleagues to diagnose and manage POTS in primary care could greatly improve function and health for people with POTS.[5]

While I commend the excellent NHS services highlighted in the feature [1], as a patient with severe long covid I would question how prevalent this integrated medically-led care model is across the country despite it being in the ‘The NHS plan for improving long covid services’.[6] Many patients I speak to in long covid support groups report long waits, only to then be offered basic wellbeing classes or rehabilitation without any active treatment for symptoms.

Access to clinics for the most severely affected is variable with not all services offering remote consultations or home visits. It is imperative that long covid clinics are medically led, inter-disciplinary and able to prescribe medications. Additionally, we need the same standard of care for patients with ME/CFS, who are still waiting for NICE guidance from 2021[7] to be implemented. A recent survey noted there remain significant gaps in provision for patients with ME/CFS.[8]

Previously young fit and healthy patients with severe long covid and ME are being left bed-bound without adequate diagnosis, support, care or treatment as there is no specialty or service that is set up to provide this. I went from climbing mountains and working on-call to unable to stand or feed myself in the space of 8 weeks with long covid – I am still severely affected a year later. Given the multi-system complexity of long covid and ME/CFS it is time for an interdisciplinary patient-centred service for post-viral illnesses that recognises the biological nature of the disease and the unique challenges patients with severe long covid and ME have with safely accessing services given their limited energy available, severe cognitive effects, physical immobility and range of complications across bodily systems.

The Department of Health and Social Care are currently seeking views on the interim delivery plan for ME/CFS care in an online consultation [9], which is relevant to both patient groups and professionals and could lay the groundwork for more comprehensive care of post-viral illnesses in the UK.

Yours sincerely,

Dr Alexis Gilbert BSc MBBS MPH FFPH

Source: MJ 2023;382:p1791 https://www.bmj.com/content/382/bmj.p1791/rr (Full text)

Cognitive dysfunction in post-COVID-19 condition: Mechanisms, management, and rehabilitation

Abstract:

The long-term effects of COVID-19 on cognitive function have become an area of increasing concern. This paper provides an overview of characteristics, risk factors, possible mechanisms, and management strategies for cognitive dysfunction in post-COVID-19 condition (PCC).

Prolonged cognitive dysfunction is one of the most common impairments in PCC, affecting between 17% and 28% of the individuals more than 12 weeks after the infection and persisting in some cases for several years. Cognitive dysfunctions can be manifested as a wide range of symptoms including memory impairment, attention deficit, executive dysfunction, and reduced processing speed. Risk factors for developing PCC, with or without cognitive impairments, include advanced age, preexisting medical conditions, and the severity of acute illness. The underlying mechanisms remain unclear, but proposed contributors include neuroinflammation, hypoxia, vascular damage, and latent virus reactivation not excluding the possibility of direct viral invasion of the central nervous system, illustrating complex viral pathology.

As the individual variation of the cognitive impairments is large, a neuropsychological examination and a person-centered multidimensional approach are required. According to the World Health Organization, limited evidence on COVID-19-related cognitive impairments necessitates implementing rehabilitation interventions from established practices of similar conditions. Psychoeducation and compensatory skills training are recommended. Assistive products and environmental modifications adapted to individual needs might be helpful. In specific attention- and working memory dysfunctions, cognitive training—carefully monitored for intensity—might be effective for people who do not suffer from post-exertional malaise. Further research is crucial for evidence-based interventions specific to COVID-19-related cognitive impairments.

Source: Möller M, Borg K, Janson C, Lerm M, Normark J, Niward K. Cognitive dysfunction in post-COVID-19 condition: Mechanisms, management, and rehabilitation. J Intern Med. 2023 Sep 27. doi: 10.1111/joim.13720. Epub ahead of print. PMID: 37766515. https://onlinelibrary.wiley.com/doi/10.1111/joim.13720 (Full text)

Forming a consensus opinion to inform long COVID support mechanisms and interventions: a modified Delphi approach

Abstract:

Background: Current approaches to support patients living with post-COVID condition, also known as Long COVID, are highly disparate with limited success in managing or resolving a well-documented and long-standing symptom burden. With approximately 2.1 million people living with the condition in the UK alone and millions more worldwide, there is a desperate need to devise support strategies and interventions for patients.

Methods: A three-round Delphi consensus methodology was distributed internationally using an online survey and was completed by healthcare professionals (including clinicians, physiotherapists, and general practitioners), people with long COVID, and long COVID academic researchers (round 1 n = 273, round 2 n = 186, round 3 n = 138). Across the three rounds, respondents were located predominantly in the United Kingdom (UK), with 17.3-15.2% (round 1, n = 47; round 2 n = 32, round 2 n = 21) of respondents located elsewhere (United States of America (USA), Austria, Malta, United Arab Emirates (UAE), Finland, Norway, Malta, Netherlands, Iceland, Canada, Tunisie, Brazil, Hungary, Greece, France, Austrailia, South Africa, Serbia, and India). Respondents were given ∼5 weeks to complete the survey following enrolment, with round one taking place from 02/15/2022 to 03/28/22, round two; 05/09/2022 to 06/26/2022, and round 3; 07/14/2022 to 08/09/2022. A 5-point Likert scale of agreement was used and the opportunity to include free text responses was provided in the first round.

Findings: Fifty-five statements reached consensus (defined as >80% agree and strongly agree), across the domains of i) long COVID as a condition, ii) current support and care available for long COVID, iii) clinical assessments for long COVID, and iv) support mechanisms and rehabilitation interventions for long COVID, further sub-categorised by consideration, inclusion, and focus. Consensus reached proposes that long COVID requires specialised, comprehensive support mechanisms and that interventions should form a personalised care plan guided by the needs of the patients. Supportive approaches should focus on individual symptoms, including but not limited to fatigue, cognitive dysfunction, and dyspnoea, utilising pacing, fatigue management, and support returning to daily activities. The mental impact of living with long COVID, tolerance to physical activity, emotional distress and well-being, and research of pre-existing conditions with similar symptoms, such as myalgic encephalomyelitis, should also be considered when supporting people with long COVID.

Interpretation: We provide an outline that achieved consensus with stakeholders that could be used to inform the design and implementation of bespoke long COVID support mechanisms.

Source: Owen R, Ashton REM, Ferraro FV, Skipper L, Bewick T, Leighton P, Phillips BE, Faghy MA. Forming a consensus opinion to inform long COVID support mechanisms and interventions: a modified Delphi approach. EClinicalMedicine. 2023 Aug 9;62:102145. doi: 10.1016/j.eclinm.2023.102145. PMID: 37599906; PMCID: PMC10432807. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10432807/ (Full text)

Post-COVID-19 syndrome management: Utilizing the potential of dietary polysaccharides

Abstract:

The COVID-19 pandemic has caused significant global impact, resulting in long-term health effects for many individuals. As more patients recover, there is a growing need to identify effective management strategies for ongoing health concerns, such as post-COVID-19 syndrome, characterized by persistent symptoms or complications beyond several weeks or months from the onset of symptoms. In this review, we explore the potential of dietary polysaccharides as a promising approach to managing post-COVID-19 syndrome.

We summarize the immunomodulatory, antioxidant, antiviral, and prebiotic activities of dietary polysaccharides for the management of post-COVID-19 syndrome. Furthermore, the review investigates the role of polysaccharides in enhancing immune response, regulating immune function, improving oxidative stress, inhibiting virus binding to ACE2, balancing gut microbiota, and increasing functional metabolites. These properties of dietary polysaccharides may help alleviate COVID-19 symptoms, providing a promising avenue for effective treatment strategies.

Source: Cheong KL, Yu B, Teng B, Veeraperumal S, Xu B, Zhong S, Tan K. Post-COVID-19 syndrome management: Utilizing the potential of dietary polysaccharides. Biomed Pharmacother. 2023 Aug 16;166:115320. doi: 10.1016/j.biopha.2023.115320. Epub ahead of print. PMID: 37595427. https://www.sciencedirect.com/science/article/pii/S0753332223011113 (Full text)

A technology-enabled multi-disciplinary team-based care model for the management of Long COVID and other fatiguing illnesses within a federally qualified health center: protocol for a two-arm, single-blind, pragmatic, quality improvement professional cluster randomized controlled trial

Abstract:

Background: The clinical burden of Long COVID, myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS), and other post-infectious fatiguing illnesses (PIFI) is increasing. There is a critical need to advance understanding of the effectiveness and sustainability of innovative approaches to clinical care of patients having these conditions.

Methods: We aim to assess the effectiveness of a Long COVID and Fatiguing Illness Recovery Program (LC&FIRP) in a two-arm, single-blind, pragmatic, quality improvement, professional cluster, randomized controlled trial in which 20 consenting clinicians across primary care clinics in a Federally Qualified Health Center system in San Diego, CA, will be randomized at a ratio of 1:1 to either participate in (1) weekly multi-disciplinary team-based case consultation and peer-to-peer sharing of emerging best practices (i.e., teleECHO (Extension for Community Healthcare Outcomes)) with monthly interactive webinars and quarterly short courses or (2) monthly interactive webinars and quarterly short courses alone (a control group); 856 patients will be assigned to participating clinicians (42 patients per clinician). Patient outcomes will be evaluated according to the study arm of their respective clinicians. Quantitative and qualitative outcomes will be measured at 3- and 6-months post-baseline for clinicians and every 3-months post assignment to a participating clinician for patients. The primary patient outcome is change in physical function measured using the Patient-Reported Outcomes Measurement Information System (PROMIS)-29. Analyses of differences in outcomes at both the patient and clinician levels will include a linear mixed model to compare change in outcomes from baseline to each post-baseline assessment between the randomized study arms. A concurrent prospective cohort study will compare the LC&FIRP patient population to the population enrolled in a university health system. Longitudinal data analysis approaches will allow us to examine differences in outcomes between cohorts.

Discussion: We hypothesize that weekly teleECHO sessions with monthly interactive webinars and quarterly short courses will significantly improve clinician- and patient-level outcomes compared to the control group. This study will provide much needed evidence on the effectiveness of a technology-enabled multi-disciplinary team-based care model for the management of Long COVID, ME/CFS, and other PIFI within a federally qualified health center.

Trial registration: ClinicalTrials.gov, NCT05167227 . Registered on December 22, 2021.

Source: Godino JG, Samaniego JC, Sharp SP, Taren D, Zuber A, Armistad AJ, Dezan AM, Leyba AJ, Friedly JL, Bunnell AE, Matthews E, Miller MJ, Unger ER, Bertolli J, Hinckley A, Lin JS, Scott JD, Struminger BB, Ramers C. A technology-enabled multi-disciplinary team-based care model for the management of Long COVID and other fatiguing illnesses within a federally qualified health center: protocol for a two-arm, single-blind, pragmatic, quality improvement professional cluster randomized controlled trial. Trials. 2023 Aug 12;24(1):524. doi: 10.1186/s13063-023-07550-3. PMID: 37573421. https://trialsjournal.biomedcentral.com/articles/10.1186/s13063-023-07550-3 (Full text)

Post-COVID cognitive dysfunction: current status and research recommendations for high risk population

Abstract:

Post-COVID cognitive dysfunction (PCCD) is a condition in which patients with a history of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection, usually three months from the onset, exhibit subsequent cognitive impairment in various cognitive domains, and cannot be explained by an alternative diagnosis.

While our knowledge of the risk factors and management strategy of PCCD is still incomplete, it is necessary to integrate current epidemiology, diagnosis and treatment evidence, and form consensus criteria to better understand this disease to improve disease management. Identifying the risk factors and vulnerable population of PCCD and providing reliable strategies for effective prevention and management is urgently needed.

In this paper, we reviewed epidemiology, diagnostic markers, risk factors and available treatments on the disease, formed research recommendation framework for vulnerable population, under the background of post-COVID period.

Source: Quan M, Wang X, Gong M, Wang Q, Li Y, Jia J. Post-COVID cognitive dysfunction: current status and research recommendations for high risk population. Lancet Reg Health West Pac. 2023 Jul 5;38:100836. doi: 10.1016/j.lanwpc.2023.100836. PMID: 37457901; PMCID: PMC10344681. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10344681/ (Full text)

Long COVID as a never-ending puzzle: the experience of primary care physicians

Abstract:

Background: Long COVID provides a new context in which primary healthcare needs to be reexamined, especially because it has health and social dimensions. The experiences of care for patients with long COVID and primary care physicians’ perceptions are an unexplored area.

Aim: To explore the experiences of Slovenian primary care physicians in management and treatment of patients with long COVID.

Design & setting: A qualitative interview study in Slovenian primary care was carried out between November 2021 and April 2022.

Method: Semi-structured interviews were held with physicians that had treated patients with long COVID until saturation was reached. Qualitative content analysis (QCA) was used to analyze the data collected.

Results: Seventeen participants were interviewed. Six categories were defined based on the coding process: the definition and symptoms of long COVID; social exclusion, sick leave, returning to the work environment, cooperation with rehabilitation centers and the importance of trust and good communication with the patient.

Conclusion: The study shows the experiences of Slovenian primary care physicians in the management and treatment of long COVID. The problems related to long COVID were divided into two groups: health problems and psycho-social problems. Slovenian physicians have the greatest problems with dealing with the patient’s ability to work. It was found that adequate communication and trust between physicians and patients are two important indicators for an integrated model of managing long COVID.

Source: Rotar Pavlic D, Maksuti A, Mihevc M, Munda A, Medija K, Strauch V. Long COVID as a never-ending puzzle: the experience of primary care physicians. BJGP Open. 2023 Jul 12:BJGPO.2023.0074. doi: 10.3399/BJGPO.2023.0074. Epub ahead of print. PMID: 37437953. https://bjgpopen.org/content/early/2023/07/11/BJGPO.2023.0074 (Full text available as PDF file)