Categories
Nevin Manimala Statistics

The incremental design of a machine learning framework for medical records processing

J Am Med Inform Assoc. 2024 Jul 17:ocae194. doi: 10.1093/jamia/ocae194. Online ahead of print.

ABSTRACT

OBJECTIVES: This work presents the development and evaluation of coordn8, a web-based application that streamlines fax processing in outpatient clinics using a “human-in-the-loop” machine learning framework. We demonstrate the effectiveness of the platform at reducing fax processing time and producing accurate machine learning inferences across the tasks of patient identification, document classification, spam classification, and duplicate document detection.

METHODS: We deployed coordn8 in 11 outpatient clinics and conducted a time savings analysis by observing users and measuring fax processing event logs. We used statistical methods to evaluate the machine learning components across different datasets to show generalizability. We conducted a time series analysis to show variations in model performance as new clinics were onboarded and to demonstrate our approach to mitigating model drift.

RESULTS: Our observation analysis showed a mean reduction in individual fax processing time by 147.5 s, while our event log analysis of over 7000 faxes reinforced this finding. Document classification produced an accuracy of 81.6%, patient identification produced an accuracy of 83.7%, spam classification produced an accuracy of 98.4%, and duplicate document detection produced a precision of 81.0%. Retraining document classification increased accuracy by 10.2%.

DISCUSSION: coordn8 significantly decreased fax-processing time and produced accurate machine learning inferences. Our human-in-the-loop framework facilitated the collection of high-quality data necessary for model training. Expanding to new clinics correlated with performance decline, which was mitigated through model retraining.

CONCLUSION: Our framework for automating clinical tasks with machine learning offers a template for health systems looking to implement similar technologies.

PMID:39018499 | DOI:10.1093/jamia/ocae194

Categories
Nevin Manimala Statistics

The Relationship between TNF-α, IL-1, IL-12, IL-17, IL-23, IL-36 Expression and Treatment Response in Psoriasis Histopathologically and Immunohistochemically

Cutan Ocul Toxicol. 2024 Jul 17:1-10. doi: 10.1080/15569527.2024.2380310. Online ahead of print.

ABSTRACT

AIM: There is no marker that can predict whether there is resistance to treatment in patients with psoriasis. In this study, we investigated the relationship between the staining rates of TNF-α, IL-1, IL-12, IL-17, IL-23, and IL-36 markers immunohistochemically from cutaneous biopsy and the treatment success.

METHODS: The patients who were followed up in the dermatology clinic with the diagnosis of plaque-type psoriasis vulgaris and received biological treatment and previously had cutaneous biopsy were included in the study. The cutaneous biopsies of the cases that met the conditions were re-sectioned and subjected to immunohistochemical examination for TNF-α, IL-1, IL-12, IL-17, IL-23, and IL-36.

RESULTS: Comparing the staining scores with psoriasis area severity index (PASI); A statistically significant positive correlation was found between PASI and TNF-α staining score(p = 0.034). A statistically significant positive correlation was found between PASI and IL-17 staining score(p = 0.004).When the staining scores and PASI response rates of psoriasis treatment were evaluated in terms of correlation; there was a positive correlation between TNF-α, IL-17, and IL-23 immunohistochemical staining rates and PASI response rates.

CONCLUSIONS: In line with the data obtained from our study, we think that making immunohistochemical scoring before the biological treatment decision in psoriasis patients will be beneficial in treatment selection. In this respect, our study may open a new era in the selection of biological treatments for psoriasis.

PMID:39018470 | DOI:10.1080/15569527.2024.2380310

Categories
Nevin Manimala Statistics

A Prediction Model for Pelvic Floor Recovery After Vaginal Birth With Risk Factors

Urogynecology (Phila). 2024 Jul 16. doi: 10.1097/SPV.0000000000001556. Online ahead of print.

ABSTRACT

IMPORTANCE: Although parturients report few postpartum symptoms, birth is clearly associated with future symptom development. The ability to identify asymptomatic at-risk women would facilitate prevention.

OBJECTIVE: The aim of the study was to develop a model predicting abnormal recovery in women at risk for childbirth-associated pelvic floor injury.

STUDY DESIGN: Women undergoing first vaginal birth at high risk of pelvic floor injury underwent examinations and ultrasound imaging and completed 6-week and 6-month postpartum questionnaires. We defined “abnormal” recovery as having ≥1 of the following 3 findings: (1) levator ani injury, (2) decreased objective pelvic floor strength, and (3) Pelvic Organ Prolapse Quantification point Bp ≥0. Descriptive statistics and bivariate analyses compared “normal” and “abnormal” recovery. Birth characteristics, 6-week examinations, and questionnaires potentially predicted abnormal recovery at 6 months. Significant variables were included as candidates in the multivariable logistic regression predicting “abnormal” recovery after birth.

RESULTS: Fifty-four women (63.5%) had normal and 31 (36.5%) had abnormal recovery at 6 months. At 6 weeks, women with abnormal recovery had decreased pelvic floor strength by Oxford scores (3 [2-5], 6 [2-8]; P = 0.002), lower point Bp (-1 [-3 to 0], -2 [-3 to -1]; P = 0.02), larger genital hiatus (4 [3 to 4], 3 [3 to 3.5]; P = 0.02), and higher levator ani injury rate (76.7%, 22.4%; P < 0.001). Between-group questionnaire differences were not clinically significant. Our final model included postpartum examination findings or birth characteristics: Oxford Scale, 6-week Pelvic Organ Prolapse Quantification GH strain, infant head circumference, and second stage ≥120 minutes. The area under the curve for predicting abnormal recovery at 6 months was 0.84, indicating a good sensitivity and specificity balance.

CONCLUSION: The model identifies women at risk for an abnormal recovery trajectory.

PMID:39018453 | DOI:10.1097/SPV.0000000000001556

Categories
Nevin Manimala Statistics

Predicting the Intravenous Pharmacokinetics of Covalent Drugs in Animals and Humans

J Med Chem. 2024 Jul 17. doi: 10.1021/acs.jmedchem.4c00776. Online ahead of print.

ABSTRACT

30 covalent drugs were used to assess clearance (CL) prediction reliability in animals and humans. In animals, marked CL underprediction was observed using cryopreserved hepatocytes or liver microsomes (LMs) supplemented for cytochrome P450 activity. Improved quantitative performance was observed by combining metabolic stability data from LMs and liver S9 fractions, the latter supplemented with reduced glutathione for glutathione transferase activity. While human LMs provided reliable human CL predictions, prediction statistics were improved further by incorporating S9 stability data. CL predictions with allometric scaling were less robust compared to in vitro drug metabolism methods; the best results were obtained using the fu-corrected intercept model. Human volume of distribution (Vd) was well predicted using allometric scaling of animal pharmacokinetic data; the most reliable results were achieved using simple allometric scaling of unbound Vd values. These results provide a quantitative framework to guide appropriate method selection for human PK prediction with covalent drugs.

PMID:39018425 | DOI:10.1021/acs.jmedchem.4c00776

Categories
Nevin Manimala Statistics

Endophytic and epiphytic metabarcoding reveals fungal communities on cashew phyllosphere in Kenya

PLoS One. 2024 Jul 17;19(7):e0305600. doi: 10.1371/journal.pone.0305600. eCollection 2024.

ABSTRACT

Plants intimately coexist with diverse taxonomically structured microbial communities that influence host health and productivity. The coexistence of plant microbes in the phyllosphere benefits biodiversity maintenance, ecosystem function, and community stability. However, differences in community composition and network structures of phyllosphere epiphytic and endophytic fungi are widely unknown. Using Illumina Miseq sequencing of internal transcribed spacer (ITS) and 28S rRNA gene amplicons, we characterised the epiphytic and endophytic fungal communities associated with cashew phyllosphere (leaf, flower and fruit) from Kwale, Kilifi and Lamu counties in Kenya. The ITS and 28S rRNA gene sequences were clustered into 267 and 108 operational taxonomic units (OTUs) at 97% sequence similarity for both the epiphytes and endophytes. Phylum Ascomycota was abundant followed by Basidiomycota, while class Saccharomycetes was most dominant followed by Dothideomycetes. The major non-ascomycete fungi were associated only with class Tremellales. The fungal communities detected had notable ecological functions as saprotrophs and pathotrophs in class Saccharomyectes and Dothideomycetes. The community composition of epiphytic and endophytic fungi significantly differed between the phyllosphere organs which was statistically confirmed by the Analysis of Similarity test (ANOSIM Statistic R: 0.3273, for 28S rRNA gene and ANOSIM Statistic R: 0.3034 for ITS). The network analysis revealed that epiphytic and endophytic structures were more specialized, modular and had less connectance. Our results comprehensively describe the phyllosphere cashew-associated fungal community and serve as a foundation for understanding the host-specific microbial community structures among cashew trees.

PMID:39018319 | DOI:10.1371/journal.pone.0305600

Categories
Nevin Manimala Statistics

The impact of COVID-19 on sexual risk behaviour for HIV acquisition in east Zimbabwe: An observational study

PLOS Glob Public Health. 2024 Jul 17;4(7):e0003194. doi: 10.1371/journal.pgph.0003194. eCollection 2024.

ABSTRACT

The Covid-19 pandemic and associated restrictions have the potential to alter sexual risk behaviours for HIV acquisition with important implications for HIV prevention programmes in sub-Saharan Africa. To date, no large-scale data have been published to substantiate hypothesised changes in sexual risk behaviours. We used longitudinal survey data to assess the impact of Covid-19 on sexual risk behaviours in east Zimbabwe. Data on sexual behaviours in HIV-negative adults aged 15-54 years were collected in two rounds of a general population open-cohort survey conducted in Manicaland, Zimbabwe shortly before (July 2018 to December 2019; N = 7316) and several months into the Covid-19 epidemic (February to July 2021; N = 6356). Descriptive statistics and logistic regression models of serial cross-sectional and prospective cohort data were used to assess changes in sexual risk behaviours. The proportion of females aged 15-19 years reporting sexual debut declined from 29.7% before Covid-19 to 20.3% during Covid-19 (adjusted odds ratio (AOR) = 0.49, 95% confidence interval (95% CI), 0.38-0.63). Fewer sexually-active females reported multiple sexual partners during Covid-19 (3.35% versus 6.07%; AOR = 0.55, 95% CI, 0.43-0.72). No population-level changes in male behaviour between survey rounds were recorded but the cohort analysis revealed a complex pattern of behaviour change with HIV risk behaviours increasing for some individuals and decreasing for others. Overall HIV risk behaviours remained high in a sub-Saharan African population with a generalised HIV epidemic over a period of Covid-19 lockdowns when movements and social contacts were restricted.

PMID:39018312 | DOI:10.1371/journal.pgph.0003194

Categories
Nevin Manimala Statistics

Systematic review and tools appraisal of prognostic factors of return to work in workers on sick leave due to musculoskeletal and common mental disorders

PLoS One. 2024 Jul 17;19(7):e0307284. doi: 10.1371/journal.pone.0307284. eCollection 2024.

ABSTRACT

With the overall objective of providing implication for clinical and research practices regarding the identification and measurement of modifiable predicting factors for return to work (RTW) in people with musculoskeletal disorders (MSDs) and common mental disorders (CMDs), this study 1) systematically examined and synthetized the research evidence available in the literature on the topic, and 2) critically evaluated the tools used to measure each identified factor. A systematic search of prognostic studies was conducted, considering four groups of keywords: 1) population (i.e., MSDs or CMDs), 2) study design (prospective), 3) modifiable factors, 4) outcomes of interest (i.e., RTW). Studies showing high risk of bias were eliminated. Tools used to measure prognostic factors were assessed using psychometric and usability criteria. From the 78 studies that met inclusion criteria, 19 (for MSDs) and 5 (for CMDs) factors reaching moderate or strong evidence were extracted. These factors included work accommodations, RTW expectations, job demands (physical), job demands (psychological), job strain, work ability, RTW self-efficacy, expectations of recovery, locus of control, referred pain (back pain), activities as assessed with disability questionnaires, pain catastrophizing, coping strategies, fears, illness behaviours, mental vitality, a positive health change, sleep quality, and participation. Measurement tools ranged from single-item tools to multi-item standardized questionnaires or subscales. The former generally showed low psychometric properties but excellent usability, whereas the later showed good to excellent psychometric properties and variable usability. The rigorous approach to the selection of eligible studies allowed the identification of a relatively small set of prognostic factors, but with a higher level of certainty. For each factor, the present tool assessment allows an informed choice to balance psychometric and usability criteria.

PMID:39018306 | DOI:10.1371/journal.pone.0307284

Categories
Nevin Manimala Statistics

Associations between the neighbourhood food environment and food and drink purchasing in England during lockdown: A repeated cross-sectional analysis

PLoS One. 2024 Jul 17;19(7):e0305295. doi: 10.1371/journal.pone.0305295. eCollection 2024.

ABSTRACT

INTRODUCTION: Evidence for the effect of neighbourhood food environment (NFE) exposures on diet in the UK is mixed, potentially due to exposure misclassification. This study used the first national COVID-19 lockdown in England as an opportunity to isolate the independent effects of the NFE exposure on food and drink purchasing, and assessed whether these varied by region.

METHODS: Transaction-level purchasing data for food and drink items for at-home (1,221 households) and out-of-home consumption (171 individuals) were available from the GB Kantar Fast Moving Consumer Goods Panel for London and the North of England. The study period included 23rd March to 10th May 2020 (‘lockdown’), and the same period in 2019 for comparison. NFE exposures included food outlet density and proximity, and NFE composition within a 1 km network buffer around the home. Associations were estimated for both years separately, adjusted for individual and household characteristics, population density and area deprivation. Interaction terms between region and exposures were explored.

RESULTS: There were no consistent patterns of association between NFE exposures and food and drink purchasing in either time period. In 2019, there was some evidence for a 1.4% decrease in energy purchased from ultra-processed foods for each additional 500 m in the distance to the nearest OOH outlet (IR 0.986, 95% CI 0.977 to 0.995, p = 0.020). In 2020, there was some evidence for a 1.8% reduction in total take-home energy for each additional chain supermarket per km2 in the neighbourhood (IR 0.982, 95% CI 0.969, 0.995, p = 0.045). Region-specific effects were observed in 2019 only.

DISCUSSION: Findings suggest that the differences in exposure to the NFE may not explain differences in the patterns or healthiness of grocery purchasing. Observed pre-pandemic region-specific effects allude to the importance of geographical context when designing research and policy. Future research may assess associations for those who relied on their NFE during lockdown.

PMID:39018304 | DOI:10.1371/journal.pone.0305295

Categories
Nevin Manimala Statistics

Humor in parenting: Does it have a role?

PLoS One. 2024 Jul 17;19(7):e0306311. doi: 10.1371/journal.pone.0306311. eCollection 2024.

ABSTRACT

BACKGROUND: Despite the widespread use of humor in social interactions and the considerable literature on humor in multiple fields of study, the use of humor in parenting has received very little formal study. The purpose of this pilot study was to gather preliminary data on the use of humor in the raising of children.

MATERIALS AND METHODS: We developed and administered a 10-item survey to measure people’s experiences being raised with humor and their views regarding humor as a parenting tool. Responses were aggregated into Disagree, Indeterminate, and Agree, and analyzed using standard statistical methods.

RESULTS: Respondents (n = 312) predominantly identified as male (63.6%) and white (76.6%) and were (by selection) between the ages of 18-45 years old. The majority of participants reported that they: were raised by people who used humor in their parenting (55.2%); believe humor can be an effective parenting tool (71.8%) and in that capacity has more potential benefit than harm (63.3%); either use (or plan to use) humor in parenting their own children (61.8%); and would value a course on how to utilize humor in parenting (69.7%). Significant correlations were found between the use of humor and both i) the quality of respondents’ relationships with their parents and ii) assessments of how good a job their parents had done.

CONCLUSIONS: In this pilot study, respondents of childbearing/rearing age reported positive views about humor as a parenting tool.

PMID:39018300 | DOI:10.1371/journal.pone.0306311

Categories
Nevin Manimala Statistics

Improving prevention and early detection of sepsis among patient groups at risk: Introducing a model for a multimodal information campaign-The SepWiss study protocol

PLoS One. 2024 Jul 17;19(7):e0305107. doi: 10.1371/journal.pone.0305107. eCollection 2024.

ABSTRACT

BACKGROUND: Sepsis is a life-threatening organ dysfunction due to a dysregulated host response to infection. Annually, sepsis leads to approx. 90.000 deaths in Germany. Risk factors include amongst others older age (>60), innate or acquired dysfunction of the immune system, and underlying chronic diseases of the lung, heart, liver, or kidneys. The manifestation of sepsis is a medical emergency, and patient outcomes depend on timely diagnosis and immediate treatment. In addition, vaccinations e.g., against pneumococci or influenza virus, are a highly effective public health tool to prevent the most common underlying infections that may lead to sepsis. However, a lack of public awareness for the relevance of vaccination and detecting sepsis as an emergency underlines the need for public health interventions that address these issues. SepWiss aims to evaluate the effects of a multimodal information campaign designed to address this lack of awareness among the risk population in Germany.

METHODS: SepWiss is an intervention at state level, consisting of a multimodal information campaign targeting risk groups in the German federal states of Berlin and Brandenburg (intervention region). Based on available evidence, various information formats were developed and implemented by outdoor advertising, social media, educational formats and through stakeholders’ platforms, starting in August 2021. The control region comprises of the remaining 14 German federal states. We will analyze vaccination coverage (primary outcome), and sepsis knowledge, the ability to detect sepsis as an emergency, and attitude towards vaccination (secondary outcomes) amongst the risk population in a controlled before-after comparison. The implementation is accompanied by a mixed-method process evaluation.

DISCUSSION: SepWiss is the first project of its kind to evaluate a complex multi-faceted evidence-based information campaign with regards to the topics of vaccination coverage, and the importance of sepsis detection and prevention for the most vulnerable populations in Germany. Results will be valuable for informing further nationwide campaigns.

TRIAL REGISTRATION: German Registry for Clinical Trials: DRKS00024475. Registered February 24th, 2021.

PMID:39018297 | DOI:10.1371/journal.pone.0305107