Early evaluation of a natural language processing tool to improve access to educational resources for surgical patients.

PURPOSE: Accessible patient information sources are vital in educating patients about the benefits and risks of spinal surgery, which is crucial for obtaining informed consent. We aim to assess the effectiveness of a natural language processing (NLP) pipeline in recognizing surgical procedures from clinic letters and linking this with educational resources. METHODS: Retrospective examination of letters from patients seeking surgery for degenerative spinal disease at a single neurosurgical center. We utilized MedCAT, a named entity recognition and linking NLP, integrated into the electronic health record (EHR), which extracts concepts and links them to systematized nomenclature of medicine-clinical terms (SNOMED-CT). Investigators reviewed clinic letters, identifying words or phrases that described or identified operations and recording the SNOMED-CT terms as ground truth. This was compared to SNOMED-CT terms identified by the model, untrained on our dataset. A pipeline linking clinic letters to patient-specific educational resources was established, and precision, recall, and F1 scores were calculated. RESULTS: Across 199 letters the model identified 582 surgical procedures, and the overall pipeline after adding rules a total of 784 procedures (precision = 0.94, recall = 0.86, F1 = 0.91). Across 187 letters with identified SNOMED-CT terms the integrated pipeline linking education resources directly to the EHR was successful in 157 (78%) patients (precision = 0.99, recall = 0.87, F1 = 0.92). CONCLUSIONS: NLP accurately identifies surgical procedures in pre-operative clinic letters within an untrained subspecialty. Performance varies among letter authors and depends on the language used by clinicians. The identified procedures can be linked to patient education resources, potentially improving patients' understanding of surgical procedures.

RetroSnake: A modular pipeline to detect human endogenous retroviruses in genome sequencing data.

Human endogenous retroviruses (HERVs) integrated into the human genome as a result of ancient exogenous infections and currently comprise ∼8% of our genome. The members of the most recently acquired HERV family, HERV-Ks, still retain the potential to produce viral molecules and have been linked to a wide range of diseases including cancer and neurodegeneration. Although a range of tools for HERV detection in NGS data exist, most of them lack wet lab validation and they do not cover all steps of the analysis. Here, we describe RetroSnake, an end-to-end, modular, computationally efficient, and customizable pipeline for the discovery of HERVs in short-read NGS data. RetroSnake is based on an extensively wet-lab validated protocol, it covers all steps of the analysis from raw data to the generation of annotated results presented as an interactive html file, and it is easy to use by life scientists without substantial computational training. Availability and implementation: The Pipeline and an extensive documentation are available on GitHub.

Transforming and evaluating the UK Biobank to the OMOP Common Data Model for COVID-19 research and beyond.

OBJECTIVE: The coronavirus disease 2019 (COVID-19) pandemic has demonstrated the value of real-world data for public health research. International federated analyses are crucial for informing policy makers. Common data models (CDMs) are critical for enabling these studies to be performed efficiently. Our objective was to convert the UK Biobank, a study of 500 000 participants with rich genetic and phenotypic data to the Observational Medical Outcomes Partnership (OMOP) CDM. MATERIALS AND METHODS: We converted UK Biobank data to OMOP CDM v. 5.3. We transformedparticipant research data on diseases collected at recruitment and electronic health records (EHRs) from primary care, hospitalizations, cancer registrations, and mortality from providers in England, Scotland, and Wales. We performed syntactic and semantic validations and compared comorbidities and risk factors between source and transformed data. RESULTS: We identified 502 505 participants (3086 with COVID-19) and transformed 690 fields (1 373 239 555 rows) to the OMOP CDM using 8 different controlled clinical terminologies and bespoke mappings. Specifically, we transformed self-reported noncancer illnesses 946 053 (83.91% of all source entries), cancers 37 802 (70.81%), medications 1 218 935 (88.25%), and prescriptions 864 788 (86.96%). In EHR, we transformed 13 028 182 (99.95%) hospital diagnoses, 6 465 399 (89.2%) procedures, 337 896 333 primary care diagnoses (CTV3, SNOMED-CT), 139 966 587 (98.74%) prescriptions (dm+d) and 77 127 (99.95%) deaths (ICD-10). We observed good concordance across demographic, risk factor, and comorbidity factors between source and transformed data. DISCUSSION AND CONCLUSION: Our study demonstrated that the OMOP CDM can be successfully leveraged to harmonize complex large-scale biobanked studies combining rich multimodal phenotypic data. Our study uncovered several challenges when transforming data from questionnaires to the OMOP CDM which require further research. The transformed UK Biobank resource is a valuable tool that can enable federated research, like COVID-19 studies.

Inpatient COVID-19 mortality has reduced over time: Results from an observational cohort.

BACKGROUND: The Covid-19 pandemic in the United Kingdom has seen two waves; the first starting in March 2020 and the second in late October 2020. It is not known whether outcomes for those admitted with severe Covid were different in the first and second waves. METHODS: The study population comprised all patients admitted to a 1,500-bed London Hospital Trust between March 2020 and March 2021, who tested positive for Covid-19 by PCR within 3-days of admissions. Primary outcome was death within 28-days of admission. Socio-demographics (age, sex, ethnicity), hypertension, diabetes, obesity, baseline physiological observations, CRP, neutrophil, chest x-ray abnormality, remdesivir and dexamethasone were incorporated as co-variates. Proportional subhazards models compared mortality risk between wave 1 and wave 2. Cox-proportional hazard model with propensity score adjustment were used to compare mortality in patients prescribed remdesivir and dexamethasone. RESULTS: There were 3,949 COVID-19 admissions, 3,195 hospital discharges and 733 deaths. There were notable differences in age, ethnicity, comorbidities, and admission disease severity between wave 1 and wave 2. Twenty-eight-day mortality was higher during wave 1 (26.1% versus 13.1%). Mortality risk adjusted for co-variates was significantly lower in wave 2 compared to wave 1 [adjSHR 0.49 (0.37, 0.65) p<0.001]. Analysis of treatment impact did not show statistically different effects of remdesivir [HR 0.84 (95%CI 0.65, 1.08), p = 0.17] or dexamethasone [HR 0.97 (95%CI 0.70, 1.35) p = 0.87]. CONCLUSION: There has been substantial improvements in COVID-19 mortality in the second wave, even accounting for demographics, comorbidity, and disease severity. Neither dexamethasone nor remdesivir appeared to be key explanatory factors, although there may be unmeasured confounding present.

Multimorbidity Patterns and Memory Trajectories in Older Adults: Evidence From the English Longitudinal Study of Aging.

BACKGROUND: We aimed to examine the multimorbidity patterns within a representative sample of UK older adults and their association with concurrent and subsequent memory. METHODS: Our sample consisted of 11 449 respondents (mean age at baseline was 65.02) from the English Longitudinal Study of Aging (ELSA). We used 14 health conditions and immediate and delayed recall scores (IMRC and DLRC) over 7 waves (14 years of follow-up). Latent class analyses were performed to identify the multimorbidity patterns and linear mixed models were estimated to explore their association with their memory trajectories. Models were adjusted by sociodemographics, body mass index (BMI), and health behaviors. RESULTS: Results showed 8 classes: Class 1: Heart Disease/Stroke (26%), Class 2: Asthma/Lung Disease (16%), Class 3: Arthritis/Hypertension (13%), Class 4: Depression/Arthritis (12%), Class 5: Hypertension/Cataracts/Diabetes (10%), Class 6: Psychiatric Problems/Depression (10%), Class 7: Cancer (7%), and Class 8: Arthritis/Cataracts (6%). At baseline, Class 4 was found to have lower IMRC and DLRC scores and Class 5 in DLRC, compared to the no multimorbidity group (n = 6380, 55.72% of total cohort). For both tasks, in unadjusted models, we found an accelerated decline in Classes 1, 3, and 8; and, for DLRC, also in Classes 2 and 5. However, it was fully attenuated after adjustments. CONCLUSIONS: These findings suggest that individuals with certain combinations of health conditions are more likely to have lower levels of memory compared to those with no multimorbidity and their memory scores tend to differ between combinations. Sociodemographics and health behaviors have a key role to understand who is more likely to be at risk of an accelerated decline.

The side effect profile of Clozapine in real world data of three large mental health hospitals.

OBJECTIVE: Mining the data contained within Electronic Health Records (EHRs) can potentially generate a greater understanding of medication effects in the real world, complementing what we know from Randomised control trials (RCTs). We Propose a text mining approach to detect adverse events and medication episodes from the clinical text to enhance our understanding of adverse effects related to Clozapine, the most effective antipsychotic drug for the management of treatment-resistant schizophrenia, but underutilised due to concerns over its side effects. MATERIAL AND METHODS: We used data from de-identified EHRs of three mental health trusts in the UK (>50 million documents, over 500,000 patients, 2835 of which were prescribed Clozapine). We explored the prevalence of 33 adverse effects by age, gender, ethnicity, smoking status and admission type three months before and after the patients started Clozapine treatment. Where possible, we compared the prevalence of adverse effects with those reported in the Side Effects Resource (SIDER). RESULTS: Sedation, fatigue, agitation, dizziness, hypersalivation, weight gain, tachycardia, headache, constipation and confusion were amongst the highest recorded Clozapine adverse effect in the three months following the start of treatment. Higher percentages of all adverse effects were found in the first month of Clozapine therapy. Using a significance level of (p< 0.05) our chi-square tests show a significant association between most of the ADRs and smoking status and hospital admission, and some in gender, ethnicity and age groups in all trusts hospitals. Later we combined the data from the three trusts hospitals to estimate the average effect of ADRs in each monthly interval. In gender and ethnicity, the results show significant association in 7 out of 33 ADRs, smoking status shows significant association in 21 out of 33 ADRs and hospital admission shows the significant association in 30 out of 33 ADRs. CONCLUSION: A better understanding of how drugs work in the real world can complement clinical trials.

Blood Protein Markers of Neocortical Amyloid-ß Burden: A Candidate Study Using SOMAscan Technology.

BACKGROUND: Four previously reported studies have tested for association of blood proteins with neocortical amyloid-ß burden (NAB). If shown to be robust, these proteins could have utility as a blood test for enrichment in clinical trials of Alzheimer's disease (AD) therapeutics. OBJECTIVE: This study aimed to investigate whether previously identified blood proteins also show evidence for association with NAB in serum samples from the Australian Imaging, Biomarker and Lifestyle Flagship Study of Ageing (AIBL). The study considers candidate proteins seen in cohorts other than AIBL and candidates previously discovered in the AIBL cohort. METHODS: Our study used the SOMAscan platform for protein quantification in blood serum. Linear and logistic regressions were used to model continuous NAB and dichotomized NAB respectively using single proteins as a predictor. Multiple protein models were built using stepwise regression techniques and support vectors machines. Age and APOEɛ4 carriage were used as covariates for all analysis. RESULTS: Of the 41 proteins previously reported, 15 AIBL candidates and 20 non-AIBL candidates were available for testing. Of these candidates, pancreatic polypeptide (PPY) and IgM showed a significant association with NAB. Notably, IgM was found to associate with continuous NAB across cognitively normal control subjects. CONCLUSIONS: We have further demonstrated the association of PPY and IgM with NAB, despite technical differences between studies. There are several reasons for a lack of significance for the other candidates including platform differences and the use of serum rather than plasma samples. To investigate the possibility of technical differences causing lack of replication, further studies are required.

Alzheimer's disease biomarker discovery using SOMAscan multiplexed protein technology.

Blood proteins and their complexes have become the focus of a great deal of interest in the context of their potential as biomarkers of Alzheimer's disease (AD). We used a SOMAscan assay for quantifying 1001 proteins in blood samples from 331 AD, 211 controls, and 149 mild cognitive impaired (MCI) subjects. The strongest associations of protein levels with AD outcomes were prostate-specific antigen complexed to α1-antichymotrypsin (AD diagnosis), pancreatic prohormone (AD diagnosis, left entorhinal cortex atrophy, and left hippocampus atrophy), clusterin (rate of cognitive decline), and fetuin B (left entorhinal atrophy). Multivariate analysis found that a subset of 13 proteins predicted AD with an accuracy of area under the curve of 0.70. Our replication of previous findings provides further evidence that levels of these proteins in plasma are truly associated with AD. The newly identified proteins could be potential biomarkers and are worthy of further investigation.

Protein interaction networks associated with cardiovascular disease and cancer: exploring the effect of bias on shared network properties.

The human network of Protein-Protein Interactions (PPIs) (interactome) provides information on biological systems that can be used to aid prediction of protein function and disease association. As some classes of protein may be the focus of much study, data sets may contain bias, which may affect the results of network analyses. Implicated cancer proteins and proteins including significant known mediators of cardiovascular disease (cvd) display a tendency to play a central role in a previously constructed interactome. However, removing possible bias in the interactome by only considering interactions obtained from non-targeted approaches affects the significance of the findings.