Optimizing mRNA vaccines and virusmediated CAR T-cell therapy for immuno-oncology: Synthetic tools for gene modification

With the success of mRNA vaccines during the COVID-19 pandemic and CAR T-cell therapies in clinical trials, there is growing opportunity for immunotherapies in the treatment of many types of cancers. Lentiviral vectors have proven effective at delivery of genetic material or gene editing technology for ex vivo processing, but the benefits and promise of Adeno-associated virus (AAV) and mRNA tools for in vivo immunotherapy have garnered recent interest. Here we describe complete synthetic solutions for immuno-oncology research programs using either mRNA-vaccines or virus-mediated cell and gene engineering. These solutions optimize workflows to minimize screening time while maximizing successful research results through: (1) Efficiency in lentiviral packaging with versatility in titer options for high-quality particles. (2) A highthroughput viral packaging process to enable rapid downstream screening. (3) Proprietary plasmid synthesis and preparation techniques to maintain ITR integrity through AAV packaging and improve gene delivery. (4) Rapid synthesis, in vitro transcription, and novel sequencing of mRNA constructs for complete characterization of critical components such as the polyA tail. The reported research demonstrates a streamlined approach that improves data quality through innovative synthesis and sequencing methodologies as compared to current standard practices.

Cutaneous Adverse Drug Reactions of COVID-19 Vaccines: A Cross-Sectional Study of the Largest Healthcare System in Taiwan

Objectives: Potential cutaneous adverse drug reactions (cADRs) associated with COVID-19 vaccinations are well-known. However, comprehensive evaluation including detailed patient characteristics, vaccine types, signs and symptoms, treatments and outcomes from such cADRs are still lacking in Taiwan. Method(s): A cross-sectional study was conducted from December 2019 to October 2022 to analyze spontaneous ADR reporting data from Taiwan's largest multi-institutional healthcare system. Physicians and pharmacists initially ensured the data quality and completeness of the reported ADR records. Subsequently, we applied descriptive statistics to analyze the patient cohort based on demographic characteristics, administered COVID-19 vaccines, clinical manifestations, and patient management. Result(s): We identified 242 cADRs from 759 reported COVID-19 vaccine-related ADRs, 88.3% of which were judged as "possible" using the Naranjo Scale. The mean age of patients with cADRs was 48.1+/-17.5 years, with the majority (44.2%) of cADRs reported in the 40-64yr old age group. cADRs were more common in women (68.2%) and most of the patients had no history of allergy to vaccines (99.6%). Oxford/AstraZeneca (58.6%) accounted for the most reported brand of COVID-19 vaccines. Patients developed cADRs within 1 to 198 days (median = 5.5 days), and mostly after first-dose vaccination (77.8%). The most frequently reported cADR was rash/eruption (18.7%), followed by itchiness/pruritus (11.7%) and urticaria (9.2%), mainly affecting the lower limbs (23.8%) and upper limbs (22.6%). Medications were prescribed for 65.1% of the cADRs, and signs and symptoms were resolved within 1 to 167 days (median = 7 days) after treatment with oral antihistamines (23.0%), topical corticosteroids (14.6%) or oral corticosteroids (14.4%). Conclusion(s): Our findings provide comprehensive details regarding COVID-19 vaccine-related cADRs in Taiwan. Certain groups, especially women and the middle-aged, who reported a relatively higher rate of cADRs, may benefit from pre-vaccination counseling about the risks of cADRs and the use of appropriate medications.Copyright © 2023

A survival genome-wide association study to identify variants associated with COVID-19 risk of death

Background/Objectives: SARS-CoV-2 infection clinical manifestations hugely vary among patients, ranging from no symptoms, to life-threatening conditions. This variability is also due to host genetics: COVID-19 Host Genetics Initiative identified six loci associated with COVID-19 severity in a previous case-control genome-wide association study. A different approach to investigate the genetics of COVID-19 severity is looking for variants associated with mortality, e.g. by analyzing the association between genotypes and time-to-event data. Method(s): Here we perform a case-only genome-wide survival analysis, of 1,777 COVID-19 patients from the GEN-COVID cohort, 60 days after infection/hospitalization. Case-only studies has the advantage of eliminating selection biases and confounding related to control subjects. Patients were genotyped using Illumina Infinium Global Screening Arrays. PLINK software was used for data quality check and principal component analysis. GeneAbel R package was used for survival analysis and age, sex and the first four principal components were used as covariates in the Cox proportional hazard model. Result(s): We found four variants associated with COVID-19 patient survival at a nominal P < 1.0 x 10-6. Their minor alleles were associated with a higher mortality risk (i.e. hazard ratios (HR)>1). In detail, we observed: HR=1.03 for rs28416079 on chromosome 19 (P=1.34 x 10-7), HR=1.15 for rs72815354 on chromosome 10 (P=1.66 x 10-7), HR=2.12 for rs2785631 on chromosome 1 (P=5.14 x 10-7), and HR=2.27 for rs2785631 on chromosome 5 (P=6.65 x 10-7). Conclusion(s): The present results suggest that germline variants are COVID-19 prognostic factors. Replication in the remaining HGI COVID-19 patient cohort (EGAS00001005304) is ongoing at the time of submission.

E-research in early psychosis: Methodological recommendations for ethics and data security

Aims: The COVID-19 pandemic compelled replacement in traditional research practices (paper-pencil questionnaire) to technology-driven practices (online surveys). Such methods may be effective in reaching larger samples, geographically harder-to-reach populations, reduce recruitment costs, increase cost and time efficiency of recruitment. Despite these advantages, concerns about privacy and confidentiality, sample bias, data quality such as inaccurate responses, duplicate survey completion, and fraudster activity or bots prevail. We aim to provide researchers and reviewers with a series of recommendations for effectively executing and evaluating data collection via online platforms. Method(s): A rapid literature review was conducted and best practices and strategies to mitigate problems with e-research data collection were collated in summer 2021. Based on study needs, these strategies were applied in an on-going e-research in early psychosis intervention services with multiple stakeholder groups across Canada. Result(s): The results were categorized and prioritized based on strategy effectiveness (most, moderate, least) and at three implementation stages (before, during, and after recruitment). An 11-step data quality checklist was adapted and implemented in consultation and approval from institutional research ethics board thus ensured ethical acceptability. Key strategies include not sharing the full survey link publicly, collecting and checking paradata, attention check questions, and so forth. Conclusion(s): Given their unique strengths, the challenges of internetbased research and data collection should not deter researchers from using such approaches. Further, our study provides concrete evidence-based practices and insights for advancing ethical and highquality e-research, taking into account specific considerations associated with early psychosis settings.

Change detection of travel behavior: a case study of COVID-19

Travel behavior is important in many fields, such as urban management and disaster management. Since the breakout of COVID-19, many people have changed their preference in travel, which is called travel behavior pattern, to respond to the impact of COVID-19. Understanding when, how, and why people change their travel behavior patterns is significant for antiepidemic and estimating the impact of COVID-19 on human society. However, most current studies ignore that travel behavior is multi-dimensions, and it can be a barrier to understanding travel behavior change. To fill up the vacuum of current research, we used an online Bayesian change detection method to detect individual travel behavior pattern change from big mobile trajectory data. For the low data quality problem caused by various and uneven, we design a novel Monte Carlo data grading framework to assess data quality and filter useable data and thus avoid unreliable results. The analysis result shows Tokyo experienced 6 phases of travel behavior change since 2020, and the change was driven by policies to some extent, especially in the frequency dimension and spatial dimension. Also, the correlation analysis indicates the correlation between four travel behavior dimension dimensions, and the infection number provides us with knowledge about how people will make a change in their travel behavior in the COVID-19 period. © 2023 Elsevier Inc. All rights reserved.

Cost-Effectiveness Analysis of Nonpharmaceutical Interventions Combined with Inactivated Vaccination and Oral Medicine in China

Objectives: Various interventions were used to control the COVID-19 pandemic and protect population health, including vaccination, medication and nonpharmaceutical interventions (NPIs). This study aims to examine the cost-effectiveness of different combinations of NPIs (including social distancing, mask wearing, tracing-testing-isolation, mass testing, and lockdown), oral medicine (Paxlovid), and vaccination (including two-dose and three-dose vaccination) under the Delta and Omicron pandemic in China. Method(s): We constructed a Markov model using a SIRI structure with a one-week cycle length over one-year time horizon to estimate the cost-effectiveness of different combinations in China from societal perspective. Effectiveness of interventions, disease transition probabilities and costs were from published data, quality-adjusted life years (QALYs) gained and incremental cost-effectiveness ratios (ICER) and net monetary benefits were calculated for one-year time horizon. One-way and probabilistic sensitivity analyses were performed to test the robustness of the model. Scenario analysis was developed to examine different situations under the Omicron pandemic. Result(s): Under the Delta pandemic, implementing the combination of social distancing, mask wearing, mass testing and three-dose vaccination was the optimal strategy, with cost at $11165635.33 and utility of 94309.94 QALYs, and had 60% probability of being cost-effective compared with other strategies. Three-dose vaccination combinations were better than two-dose combinations. Under the Omicron pandemic, antigen testing was better than nucleic testing by avoiding cross infections;second, adding Paxlovid or lockdown to the combined intervention strategies could increase limited health outcomes at huge cost and thus were not cost-effective;last, encouraging patients to stay at home can save societal costs compared with concentrated quarantine at hospitals. Conclusion(s): Three-dose vaccination and self-quarantine of asymptomatic and mild cases can save total costs. Under the Omicron pandemic outbreak, antigen testing is a better way to control the pandemic, and adding Paxlovid or lockdown to intervention combinations is not cost-effective.Copyright © 2023

Getting it right first time: what have we learnt?

Getting It Right First Time (GIRFT) is a national programme of improvement to identify and reduce unwarranted variation and non-evidence-based practice in healthcare. It aims to improve patient care, increase productivity and reduce costs. Professor Tim Briggs, an orthopaedic surgeon, began the programme with a pilot review visiting every orthopaedic surgery department in England. He used publicly available data to illuminate variation, and worked with the clinicians and management to develop improvements. The impressive initial report in 2015 led to NHS Improvement investing £60m to expand the programme to 40 medical and surgical specialties. The follow-up Orthopaedic report detailed savings of £696m to the NHS. GIRFT is now sharing its data with the CQC and leading the charge with elective recovery following COVID-19. GIRFT differs from previous programmes of improvement through its peer led, supportive approach to promoting change with early engagement of both clinicians and management. Common themes run through the almost 40 specialty reports published to date: variation in procurement and litigation costs, huge variations in patient treatment options (often with a lack of evidence base) and poor data quality. Successfully applied in orthopaedic surgery, it has been taken on enthusiastically by other specialties. Whether it can deliver its objective of £1.4bn savings whilst improving patient outcomes is yet to be seen, but its approach is changing the culture of the NHS.

Data quality model for assessing public COVID-19 big datasets.

For decision-making support and evidence based on healthcare, high quality data are crucial, particularly if the emphasized knowledge is lacking. For public health practitioners and researchers, the reporting of COVID-19 data need to be accurate and easily available. Each nation has a system in place for reporting COVID-19 data, albeit these systems' efficacy has not been thoroughly evaluated. However, the current COVID-19 pandemic has shown widespread flaws in data quality. We propose a data quality model (canonical data model, four adequacy levels, and Benford's law) to assess the quality issue of COVID-19 data reporting carried out by the World Health Organization (WHO) in the six Central African Economic and Monitory Community (CEMAC) region countries between March 6,2020, and June 22, 2022, and suggest potential solutions. These levels of data quality sufficiency can be interpreted as dependability indicators and sufficiency of Big Dataset inspection. This model effectively identified the quality of the entry data for big dataset analytics. The future development of this model requires scholars and institutions from all sectors to deepen their understanding of its core concepts, improve integration with other data processing technologies, and broaden the scope of its applications.

Pan-Respiratory Disease Surveillance in Southeast Asia: Past, Present and Future

The Global Influenza Surveillance and Response System (GISRS) was established by WHO in 1952 to conduct surveillance for influenza to inform strain selection for seasonal vaccines and to monitor for influenza pandemics. In 2016 WHO initiated a pilot project to add RSV to influenza surveillance platforms;this was disrupted by the SARS CoV-2 pandemic, and SARS CoV-2 was the first pathogen to be incorporated into influenza sentinel surveillance on a wide scale. This resulted in a "GISRS-plus" surveillance network for influenza and SARS CoV-2 that is now being standardized by WHO. In the wake of the SARS CoV-2 pandemic, there is global interest and funding to support pan-respiratory disease surveillance, which could result in expanding influenza/SARS CoV-2 surveillance platforms to include other pathogens and enhancing event- and indicator-based surveillance. Challenges with expanding sentinel surveillance include overburdening sentinel surveillance systems, reduced number of samples collected and loss of data quality for influenza and SARS CoV-2;thus, other types of surveillance for respiratory diseases might also be considered. This talk describes CDC-supported influenza surveillance platforms in Southeast Asia and recent successes and challenges in adding SARS CoV-2 to this surveillance. It discusses potential risks and benefits to GISRS-plus surveillance created by including other pathogens. Finally, it discusses decision-making steps on which methods to use for collecting data on respiratory viruses.Copyright © 2023

Shared longitudinal health records for clinical and population health

The ability of a health information exchange (HIE) to consolidate information, collected from multiple, disparate information systems, into a single, person-centric health record can provide a comprehensive and longitudinal representation of an individual's medical history. Shared, longitudinal health records can be leveraged to enhance the delivery of individual clinical care and provide opportunities to improve health outcomes at the population level. This chapter describes the clinical benefits imparted by the shared health record (SHR) component an HIE infrastructure. It also characterizes the potential public health benefits of the aggregate level, population health indicators calculated, stored, and distributed by a health management information system (HMIS) component. Tools for visualizing health indicators from the HMIS, including disease surveillance systems developed during the COVID-19 pandemic, are also described. Postpandemic components such as the SHR and HMIS will likely play critical roles in strengthening health information infrastructures in states and nations. © 2023 Elsevier Inc. All rights reserved.

Drug Discovery and Big Data: From Research to the Community

Technology and artificial intelligence, alongside the COVID-19 pandemic vastly increasing technology use in health care, have precipitated an escalation of big data. Although real-world data (RWD) and real-world evidence (RWE) have contributed to determining outcomes outside the scope of randomized clinical trials (RCTs), RWD and RWE are underutilized in demonstrating drug effectiveness. Utilizing RWD may enhance the ability of regulatory agencies to approve drugs, provide drug effectiveness insight to payers, and improve personalized medicine. Additionally, RWD and RWE may assist in overcoming the limitations of RCT data such as treatment adherence and underrepresented patient subgroups and may support and expedite drug repositioning. Even though the limitations of using RWE and RWD include fragmented data context, poor data quality, and information governance, healthcare analytics hubs such as the European Health Data Space are designed to foster synergy among private and public healthcare players and may assist in overcoming these potential limitations. Such healthcare analytics hubs may enhance the utilization of RWE and/or RWD, which could ultimately result in better patient outcomes. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Quality of routine health data at the onset of the COVID-19 pandemic in Ethiopia, Haiti, Laos, Nepal, and South Africa.

BACKGROUND: During the COVID-19 pandemic, governments and researchers have used routine health data to estimate potential declines in the delivery and uptake of essential health services. This research relies on the data being high quality and, crucially, on the data quality not changing because of the pandemic. In this paper, we investigated those assumptions and assessed data quality before and during COVID-19. METHODS: We obtained routine health data from the DHIS2 platforms in Ethiopia, Haiti, Lao People's Democratic Republic, Nepal, and South Africa (KwaZulu-Natal province) for a range of 40 indicators on essential health services and institutional deaths. We extracted data over 24 months (January 2019-December 2020) including pre-pandemic data and the first 9 months of the pandemic. We assessed four dimensions of data quality: reporting completeness, presence of outliers, internal consistency, and external consistency. RESULTS: We found high reporting completeness across countries and services and few declines in reporting at the onset of the pandemic. Positive outliers represented fewer than 1% of facility-month observations across services. Assessment of internal consistency across vaccine indicators found similar reporting of vaccines in all countries. Comparing cesarean section rates in the HMIS to those from population-representative surveys, we found high external consistency in all countries analyzed. CONCLUSIONS: While efforts remain to improve the quality of these data, our results show that several indicators in the HMIS can be reliably used to monitor service provision over time in these five countries.

Towards a Consistent Representation of Contradictions Within Health Data for Efficient Implementation of Data Quality Assessments.

Contradictions as a data quality indicator are typically understood as impossible combinations of values in interdependent data items. While the handling of a single dependency between two data items is well established, for more complex interdependencies, there is not yet a common notation or structured evaluation method established to our knowledge. For the definition of such contradictions, specific biomedical domain knowledge is required, while informatics domain knowledge is responsible for the efficient implementation in assessment tools. We propose a notation of contradiction patterns that reflects the provided and required information by the different domains. We consider three parameters (α, ß, θ): the number of interdependent items as α, the number of contradictory dependencies defined by domain experts as ß, and the minimal number of required Boolean rules to assess these contradictions as θ. Inspection of the contradiction patterns in existing R packages for data quality assessments shows that all six examined packages implement the (2,1,1) class. We investigate more complex contradiction patterns in the biobank and COVID-19 domains showing that the minimum number of Boolean rules might be significantly lower than the number of described contradictions. While there might be a different number of contradictions formulated by the domain experts, we are confident that such a notation and structured analysis of the contradiction patterns helps to handle the complexity of multidimensional interdependencies within health data sets. A structured classification of contradiction checks will allow scoping of different contradiction patterns across multiple domains and effectively support the implementation of a generalized contradiction assessment framework.

Population differences in completeness and reliability of Dutch COVID-19 registry data: The influence of testing policy, test readiness, and registration policy from an epidemiological perspective.

During the COVID-19 pandemic, the bidirectional relationship between policy and data reliability has been a challenge for researchers of the local municipal health services. Policy decisions on population specific test locations and selective registration of negative test results led to population differences in data quality. This hampered the calculation of reliable population specific infection rates needed to develop proper data driven public health policy.

Federated Learning for Healthcare Domain - Pipeline, Applications and Challenges

Federated learning is the process of developing machine learning models over datasets distributed across data centers such as hospitals, clinical research labs, and mobile devices while preventing data leakage. This survey examines previous research and studies on federated learning in the healthcare sector across a range of use cases and applications. Our survey shows what challenges, methods, and applications a practitioner should be aware of in the topic of federated learning. This paper aims to lay out existing research and list the possibilities of federated learning for healthcare industries.© 2022 Copyright held by the owner/author(s).

Innovations in clinical documentation integrity practice: Continual adaptation in a data-intensive healthcare organisation.

BACKGROUND: Numbers of clinical documentation integrity specialists (CDIS) and CDI programs have increased rapidly. CDIS review patient records concurrently with patient admissions and visits to ensure that information is accurate, complete and non-ambiguous, and query clinicians when they see opportunities for improving data. The occupation was initially focused on improving data for reimbursement, but rapid changes to clinical coding requirements, technologies and payment systems led to a quickly evolving role for CDI programs and changes in CDIS practice. OBJECTIVE: This case study seeks to uncover the ongoing innovation and adaptation occurring in a CDI program by tracing the evolution of a single CDI program over time. METHOD: We present a case study of the CDI program at the HonorHealth hospital system in Arizona. RESULTS: The HonorHealth CDI program holds a unique hybrid expertise and role within the healthcare organisation that allows it to rapidly adapt to support emergent demands both internal and external to the organisation, such as supporting accurate data collection for the COVID-19 pandemic. CONCLUSION: CDIS are a vital component in present data-intensive resourcing efforts. The hybrid expertise of CDIS and capacity for adaption and relationship building has enabled the HonorHealth CDI program to adapt rapidly to meet a growing array of clinical documentation integrity needs, including emergent needs during the COVID-19 pandemic. IMPLICATIONS: The HonorHealth case study can guide other CDI programs in adaptation of the CDI role and practices in response to changing organisational needs.

Estimates of excess mortality during the COVID-19 pandemic strongly depend on subjective methodological choices.

Excess mortality is often used to assess the health impact of the COVID-19 pandemic. It involves comparing the number of deaths observed during the pandemic with the number of deaths that would counterfactually have been expected in the absence of the pandemic. However, published data on excess mortality often vary even for the same country. The reason for these discrepancies is that the estimation of excess mortality involves a number of subjective methodological choices. The aim of this paper was to summarize these subjective choices. In several publications, excess mortality was overestimated because population aging was not adjusted for. Another important reason for different estimates of excess mortality is the choice of different pre-pandemic reference periods that are used to estimate the expected number of deaths (e.g., only 2019 or 2015-2019). Other reasons for divergent results include different choices of index periods (e.g., 2020 or 2020-2021), different modeling to determine expected mortality rates (e.g., averaging mortality rates from previous years or using linear trends), the issue of accounting for irregular risk factors such as heat waves and seasonal influenza, and differences in the quality of the data used. We suggest that future studies present the results not only for a single set of analytic choices, but also for sets with different analytic choices, so that the dependence of the results on these choices becomes explicit.

Safety of COVID-19 Vaccines.

By June 1, 2022, there were 38 prophylactic COVID-19 vaccines approved in 197 countries around the world. The ongoing approval of new vaccines and the accumulation of more than a year's worth of data on their use give particular importance to the consolidation and analysis of information on the safety of such vaccines. The aim of study was to analyse the information on adverse events after immunisation (AEFIs) with coronavirus vaccines in the individual case safety reports entered into the VigiBase database by June 1, 2022. Material(s) and Method(s): the author analysed safety reports retrieved from VigiBase through the VigiLyze interface in the expert access mode. The search was carried out using the generic keyword "Covid-19 vaccine" in combination with the trade names of all 38 coronavirus vaccines. Result(s): the article presents consolidated information on the number and content of the safety reports on COVID-19 vaccines. The author noted that the reports were characterised by a high level of information completeness and quality, which could be due to the fact that the main reporters were the countries with developed pharmacovigilance systems. The analysis of patient complaints showed that the reported symptoms of AEFIs coincided with the manifestations of side effects of the vaccines included in the package leaflets. The author carried out a review of the cases of serious AEFIs and the cases of adverse events of special interest requiring additional monitoring after immunisation. It revealed a positive correlation of individual vaccines with the cases of somnolence in post-COVID-19 patients. Conclusion(s): the data obtained on the global safety of coronavirus vaccines may be of practical interest to doctors, researchers, developers, and healthcare regulators.Copyright © 2023 Safety and Risk of Pharmacotherapy. All rights reserved.

Physiological Metrics Collected from Wearable Devices Identify Inflammatory and Clinical Inflammatory Bowel Disease Flares

BACKGROUND: Inflammatory bowel disease (IBD) flares are common and unpredictable. Disease monitoring relies on symptom reporting or single timepoint assessments of stool, blood, imaging, or endoscopy-these are inconvenient and invasive and do not always reflect the patient perspective. Advances in wearable technology allow for passive, continuous and non-invasive assessment of physiological metrics including heart rate variability (HRV), the measure of small time differences between each heartbeat, a marker of autonomic nervous system function. Our group has previously demonstrated that changes in autonomic function precedes an IBD flare, can predict psychological state transitions and even identify inflammatory events including SARS-CoV-2 infection. To develop algorithms that can predict IBD flares using wearable device signatures, we launched a national wearable device study called The IBD Forecast study. To assess data quality and feasibility, the first 125 Apple Watch users to enroll were evaluated. METHOD(S): The IBD Forecast study is a prospective cohort study enrolling anyone >=18 years of age in the United States (US) with IBD who is willing to (1) use a commercially available wearable device, (2) download our custom eHive app and (3) answer daily survey questions. HRV metrics (mean of the standard deviations of all the NN intervals [SDNN]) were analyzed using a mixed-effect cosigner model that incorporated body mass index, age, and sex. SDNN is a time domain HRV index that reflects both sympathetic and parasympathetic nervous system activity and is calculated from the variance of intervals between adjacent QRS complexes (the normal-to-normal [NN] intervals). Clinical flare was assessed with daily Patient Reported Outcome (PRO)-2 surveys (flare;PRO-2 Crohn's disease >7, PRO-2 ulcerative colitis >2). Inflammatory flare was assessed via patient reported C-reactive protein (CRP), with inflammatory flare defined as >5 mg/L. RESULT(S): The first 125 study participants were enrolled across 29 states in the US (Table 1). Circadian features of changes of HRV were modelled (Figure 1). The mesor, or midline of the circadian pattern of the SDNN was higher in those with clinical flare (mean 44.43;95% CI 41.25-47.75) compared to those in clinical remission (mean 43.03;95% CI 39.94-46.22) (p<0.004). The mesor of the circadian pattern of the SDNN was lower in those with an inflammatory flare (mean 38.16;95% CI 30.86-45.72) compared to those with normal inflammatory markers (mean 49.51;95% CI 43.12-56.26) (p<0.001). CONCLUSION(S): Longitudinally collected HRV metrics from a commonly worn commercial wearable device can identify symptomatic and inflammatory flares. This preliminary analysis of a small proportion of the IBD Forecast Study cohort demonstrates the feasibility of using wearable devices to identify, and may potentially predict, IBD flares. [Formula presented] [Formula presented]Copyright © 2023

Covid severity prediction: Who cares about the data quality?

COVID-19 is an ongoing pandemic disrupting daily life and overwhelming the healthcare infrastructure. Since the outburst of the pandemic, researchers have used various techniques to predict many aspects of the disease, including mortality rate and severity. The reproducibility of this research is challenging due to varying methodologies used to collect data, data quality, vague description of methodological approach to training prediction models, over-relying on data imputation, and over-fitting. This paper focuses on these challenges and provides a short yet comprehensive review of research on COVID mortality and severity prediction. The emphasis is on the reproducibility of the results and data quality issues. To further elaborate on the issue, we report the development of severity prediction models using two data sets. CRISP-DM is used as a methodological approach. We analyze and criticize the quality of the used data sets and how they affect the performance and limitations of the trained models. We conclude this paper with comments on data quality issues, the importance of reproducibility, and suggestions to improve reproducibility. © 2022 IEEE.