Statistical Expertise Research Articles

Adopting Optimal Statistical Practices: Reviewers.

In this installment of the Methodology Corner, we briefly discuss how our peer-reviewers might foster optimal statistical practices among our community of researchers. Reviewers are encouraged to seek out training opportunities that enhance their own statistical expertise and to consider tools that might support and enhance the quality of their reviews. We also encourage reviewers with statistical expertise to further lend their time and efforts to reviewership. [J Nurs Educ. 2024;63(11):785-786.].

Establishment of seven lung ultrasound phenotypes: a retrospective observational study of an LUS registry

BackgroundLung phenotypes have been extensively utilized to assess lung injury and guide precise treatment. However, current phenotypic evaluation methods rely on CT scans and other techniques. Although lung ultrasound (LUS) is widely employed in critically ill patients, there is a lack of comprehensive and systematic identification of LUS phenotypes based on clinical data and assessment of their clinical value.MethodsOur study was based on a retrospective database. A total of 821 patients were included from September 2019 to October 2020. 1902 LUS examinations were performed in this period. Using a dataset of 55 LUS examinations focused on lung injuries, a group of experts developed an algorithm for classifying LUS phenotypes based on clinical practice, expert experience, and lecture review. This algorithm underwent validation and refinement with an additional 140 LUS images, leading to five iterative revisions and the generation of 1902 distinct LUS phenotypes. Subsequently, a validated machine learning algorithm was applied to these phenotypes. To assess the algorithm’s effectiveness, experts manually verified 30% of the phenotypes, confirming its efficacy. Using K-means cluster analysis and expert image selection from the 1902 LUS examinations, we established seven distinct LUS phenotypes. To further explore the diagnostic value of these phenotypes for clinical diagnosis, we investigated their auxiliary diagnostic capabilities.ResultsA total of 1902 LUS phenotypes were tested by randomly selecting 30% to verify the phenotypic accuracy. With the 1902 LUS phenotypes, seven lung ultrasound phenotypes were established through statistical K-means cluster analysis and expert screening. The acute respiratory distress syndrome (ARDS) exhibited gravity-dependent phenotypes, while the cardiogenic pulmonary edema exhibited nongravity phenotypes. The baseline characteristics of the 821 patients included age (66.14 ± 11.76), sex (560/321), heart rate (96.99 ± 23.75), mean arterial pressure (86.5 ± 13.57), Acute Physiology and Chronic Health Evaluation II (APACHE II)score (20.49 ± 8.60), and duration of ICU stay (24.50 ± 26.22); among the 821 patients, 78.8% were cured. In severe pneumonia patients, the gravity-dependent phenotype accounted for 42% of the cases, whereas the nongravity-dependent phenotype constituted 58%. These findings highlight the value of applying different LUS phenotypes in various diagnoses.ConclusionsSeven sets of LUS phenotypes were established through machine learning analysis of retrospective data; these phenotypes could represent the typical characteristics of patients with different types of critical illness.

An analytical approach for identifying trend-seasonal components and detecting unexpected behaviour in psychological time-series.

The recent advances in technological capabilities have led to a massive production of time-series data and remarkable progress in longitudinal designs and analyses within psychological research. However, implementing time-series analysis can be challenging due to the various characteristics and complexities involved, as well as the need for statistical expertise. This paper introduces a statistical pipeline on time-series analysis for studying the changes in a single process over time at either a population or individual level, both retrospectively and prospectively. This is achieved through systemization and extension of existing modelling and inference techniques. This analytical approach enables practitioners not only to track but also to model and evaluate emerging trends and apparent seasonality. It also allows for the detection of unexpected events, quantifying their deviations from baseline and forecasting future values. Given that other discernible population- and individual-level changes in psychological and behavioural processes have not yet emerged, continued surveillance is warranted. A near real-time monitoring tool of time-series data could guide community psychological responses across multiple ecological levels, making it a valuable resource for field practitioners and psychologists. An empirical study is conducted to illustrate the implementation of the introduced analytical pipeline in practice and to demonstrate its capabilities.

Coconut Libtool: Bridging Textual Analysis Gaps for Non‐Programmers

ABSTRACTIn the era of big and ubiquitous data, professionals and students alike are finding themselves needing to perform a number of textual analysis tasks. Historically, the general lack of statistical expertise and programming skills has stopped many with humanities or social sciences backgrounds from performing and fully benefiting from such analyses. Thus, we introduce Coconut Libtool (www.coconut-libtool.com/), an open‐source, web‐based application that utilizes state‐of‐the‐art natural language processing (NLP) technologies. Coconut Libtool analyzes text data from customized files and bibliographic databases such as Web of Science, Scopus, and Lens. Users can verify which functions can be performed with the data they have. Coconut Libtool deploys multiple algorithmic NLP techniques at the backend, including topic modeling (LDA, Biterm, and BERTopic algorithms), network graph visualization, keyword lemmatization, and sunburst visualization. Coconut Libtool is the people‐first web application designed to be used by professionals, researchers, and students in the information sciences, digital humanities, and computational social sciences domains to promote transparency, reproducibility, accessibility, reciprocity, and responsibility in research practices.

Harvesters’ productivity prediction in Brazilian Eucalyptus plantations: development of a model from machine learning

ABSTRACT Productivity analysis in mechanized harvesting has traditionally relied on statistical expertise and mathematical modeling. However, machine learning tools have emerged as a viable alternative, as they serve the same purpose, utilizing a combination of varied attributes (quantitative and qualitative) and handling large datasets. This study aimed to determine whether the inherent attributes of mechanized timber harvesting of Eucalyptus spp. plantations enable the creation of a high-performance model that can accurately predict productivity from machine learning. For the modeling, we considered five attributes concerning forest inventory, in addition to working hours and the operator experience level. We considered the productivity, timber harvested per working hour, as the target attribute of the modeling. We subjected the database to 17 common algorithms in default mode and compared them according to error metrics and accuracy. We also determined the relative importance of each attribute in the predictive model. The inherent attributes concerning mechanized timber harvesting of Eucalyptus spp. plantations evaluated in this study enable the creation of a high-performance model that can accurately predict productivity from machine learning. The Gradient boosting model in ensemble mode can predict the productivity of harvesters in Eucalyptus spp. plantations with an R2 of 0.81. The attributes that have greater relative importance are operator experience level, average individual tree volume, and stand density with 100%, 76.3%, and 65.8%, respectively.

Повышение ВРП экономики Иркутской области на основе роста уровня энергетической эффективности регионального промышленного комплекса

Energy efficiency of fuel and energy consumption is an important indicator of regional economy. The article provides an empirical study of electricity consumption, gross regional product, and electricity consumption per capita in Russia’s regions in 2021. The analysis focused on the role of the Irkutsk Region in the development of Russia’s energy balance and economy. The authors mapped the electric intensity as part of gross regional product and found out that it is very low in the Irkutsk Region, despite the fact that this region is one of the largest consumers of electricity in Russia. The analysis revealed a national need for a better theoretical basis in energy efficiency. The research featured the increase in economic indicators of the Irkutsk Region in conditions of leveling the regional energy efficiency to average indicators. The authors used the methods of statistical research, expert assessments, modeling, and forecasting. They analyzed electric intensity by type of economic activity in various regions of the Siberian Federal District. As a result, they associated the low electric intensity of the gross regional product in Irkutsk with its industrial sector, which uses a lot of electricity and provides a significant share of the gross regional product. They modelled some changes in the volumes of Irkutsk’s gross regional product with an increase in energy efficiency in the industrial power consumption sector. As a result, the gross regional product increased by 57%, rising from 1,268 billion rubles to 2,000 billion rubles. The result was achieved by an increase in the industrial sector from 494 billion rubles to 1,226 billion rubles.

Tackling challenges in rare diseases: The ISGACA approach on non-pancreatic cancers in the periampullary region

ObjectiveRare but aggressive cancer types like non-pancreatic periampullary cancers pose unique challenges for cancer research due to their low incidence rates and lack of consensus on optimal treatment strategies, therefore necessitating a collaborative approach. The International Study Group on non-pancreatic peri-Ampullary CAncer (ISGACA) aimed to build a collaborative initiative to pool expertise, funding opportunities, and data from over 60 medical centers, in order to improve outcomes for underrepresented patients with rare cancers. MethodsThe ISGACA approach predefined a stepwise approach including a research scope, establishing a dedicated steering committee, creating a recognizable brand, identifying research gaps, following a well-defined timeline, ensuring robust data collection, addressing legal and ethical considerations, securing financial resources, investing in research ethics training and statistical expertise, raising awareness, creating uniformity, and initiating prospective studies. ResultsOverall, 60 medical centers joined the ISGACA consortium (41 in Europe, 15 in North-America, three in Asia, one in Australia). The database includes 4309 patients. Nine publications and several ongoing studies which in turn allowed for a successful application of research grants. Subsequently, an international consensus meeting established uniform definitions and classifications, and one prospective multicenter international clinical trial has been initiated. ConclusionBy sharing knowledge, expertise, and clinical data, the ISGACA approach has not only gathered sufficient evidence to secure grants and ethical approvals for prospective studies, but also demonstrates options for standardizing patient care and improving outcomes for patients with rare cancers. The ISGACA approach offers a detailed methodology for initiating research on rare cancers and could serve as a replicable model for future research initiatives.

Using machine learning techniques for exploration and classification of laboratory data

Abstract Objectives The study aims to acquaint readers with six widely used machine learning (ML) techniques (Principal Component Analysis (PCA), Uniform Manifold Approximation and Projection (UMAP), k-means, hierarchical clustering and the decision tree models (rpart and random forest)) that might be useful for the analysis of laboratory data. Methods Utilizing a recently validated data set from lung cancer diagnostics, we investigate how ML can support the search for a suitable tumor marker panel for the differentiation of small cell (SCLC) and non-small cell lung cancer (NSCLC). Results The ML techniques used here effectively helped to gain a quick overview of the data structures and provide initial answers to the clinical questions. Dimensionality reduction techniques such as PCA and UMAP offered insightful visualization and impression of the data structure, suggesting the existence of two tumor groups with a large overlap of largely inconspicuous values. This impression was confirmed by a cluster analysis with the k-means algorithm, indicative of unsupervised learning. For supervised learning, decision tree models like rpart or random forest demonstrated their utility in differential diagnosis of the two tumor types. The rpart model, which constructs binary decision trees based on the recursive partitioning algorithm, suggests a tree involving four serum tumor markers (STMs), which were confirmed by the random forest approach. Both highlighted pro-gastrin-releasing peptide (ProGRP), neuron specific enolase (NSE), cytokeratin-19 fragment (CYFRA 21-1) and cancer antigen (CA) 72-4 as key tumor markers, aligning with the outcomes of the initial statistical analysis. Cross-validation of the two proposals showed a higher area under the receiver operating characteristic (AUROC) curve of 0.95 with a 95 % confidence interval (CI) of 0.92–0.97 for the random forest model compared to an AUROC curve of 0.88 (95 % CI: 0.83–0.93). Conclusions ML can provide a useful overview of inherent medical data structures and distinguish significant from less pertinent features. While by no means replacing human medical and statistical expertise, ML can significantly accelerate the evaluation of medical data, supporting a more informed diagnostic dialogue between physicians and statisticians.

Tc-llama 2: fine-tuning LLM for technology and commercialization applications

This paper introduces TC-Llama 2, a novel application of large language models (LLMs) in the technology-commercialization field. Traditional methods in this field, reliant on statistical learning and expert knowledge, often face challenges in processing the complex and diverse nature of technology-commercialization data. TC-Llama 2 addresses these limitations by utilizing the advanced generalization capabilities of LLMs, specifically adapting them to this intricate domain. Our model, based on the open-source LLM framework, Llama 2, is customized through instruction tuning using bilingual Korean-English datasets. Our approach involves transforming technology-commercialization data into formats compatible with LLMs, enabling the model to learn detailed technological knowledge and product hierarchies effectively. We introduce a unique model evaluation strategy, leveraging new matching and generation tasks to verify the alignment of the technology-commercialization relationship in TC-Llama 2. Our results, derived from refining task-specific instructions for inference, provide valuable insights into customizing language models for specific sectors, potentially leading to new applications in technology categorization, utilization, and predictive product development.

Top Ten Tips Palliative Care Clinicians Should Know About Interpreting a Clinical Trial.

Evidence-based practice is foundational to high-quality palliative care delivery. However, the clinical trials that compose the evidence base are often methodologically imperfect. Applying their conclusions without critical application to the clinical practice context can harm patients. The tips provided can help clinicians infer judiciously from clinical trial results and avoid credulously accepting findings without critique. We suggest that statistical and mathematical expertise is unnecessary, but rather a keen curiosity about investigators' rationale for certain design choices and how these choices can affect results is key. For a more comprehensive understanding of clinical trials, this article can be used with the authors' corresponding ten tips article that focuses on designing a clinical trial.

The Study of the Epidemiology of Pediatric Hypertension Registry (SUPERHERO): Rationale and Methods.

Despite increasing prevalence of hypertension in youth and high adult cardiovascular mortality rates, the long-term consequences of youth-onset hypertension remain unknown. This is due to limitations of prior research such as small sample sizes, reliance on manual record review, and limited analytic methods that did not address major biases. The Study of the Epidemiology of Pediatric Hypertension (SUPERHERO) is a multisite retrospective Registry of youth evaluated by subspecialists for hypertension disorders. Sites obtain harmonized electronic health record data using standardized biomedical informatics scripts validated with randomized manual record review. Inclusion criteria are index visit for International Classification of Diseases Diagnostic Codes, 10th Revision (ICD-10 code)-defined hypertension disorder ≥January 1, 2015 and age <19 years. We exclude patients with ICD-10 code-defined pregnancy, kidney failure on dialysis, or kidney transplantation. Data include demographics, anthropomorphics, U.S. Census Bureau tract, histories, blood pressure, ICD-10 codes, medications, laboratory and imaging results, and ambulatory blood pressure. SUPERHERO leverages expertise in epidemiology, statistics, clinical care, and biomedical informatics to create the largest and most diverse registry of youth with newly diagnosed hypertension disorders. SUPERHERO's goals are to (i) reduce CVD burden across the life course and (ii) establish gold-standard biomedical informatics methods for youth with hypertension disorders.

Study of the Social Responsibility of Ukrainian Employers for the Health of Employees on the Example of Enterprises of the Machine-Building Industry in the Kharkiv Region

The work aims to develop a methodical approach to assessing the employer’s level of social responsibility for employee health. Methods of statistical analysis, expert assessments, and content analysis were used. Developed a methodological approach to determining the level of social responsibility of the employer for maintaining the health of workers, which was tested in a sample of 18 enterprises of the machine-building industry of Kharkiv and Kharkiv region; it is determined by calculating an integrated indicator that combines quantitative and qualitative characteristics of the working environment in three planes (sections), which characterize the factors influencing human health: social conditions and lifestyle, the level of ecology of the working space, and the level of medical care at the enterprise. The results of the employer’s efforts to preserve the health of the employee are transformed into the health of the employee, which is analyzed through the indicator “Health Index”.

The prediction of emotional decision making from working memory and inhibitory control in preschool children: using decision tree model

ABSTRACT While there is a theoretical distinction between cool (cognitive) and hot (emotional) executive functions, potential relationships can be identified between tasks associated with these two aspects. A decision tree serves as a model for training and analyzing data, predicting the target variable based on independent variables in a hierarchical fashion. In contrast to other predictive methods, this model doesn’t necessitate statistical expertise and makes decisions akin to human decision-making through hierarchical “if” and “then” rules, providing an easily interpretable framework. To date, no studies have explored the relationship between cool and hot executive functions using decision tree models. In this study, preschool children specifically Persian-speaking Iranian children aged 4 to 5 years (N = 71, M age = 59.07; SD = 6.03), participated in cool (Forward Digit Span, Backward Digit Span, Day-Night inhibitory control, and Happy-Sad Inhibitory control) and hot (Children Gambling Task) executive function tasks. Analyses were performed using MATLAB programming software. The C4.5 version of the decision tree was employed to predict the final CGT blocks’ scores using scores from cool executive function tasks as inputs. By employing this method, a minimal prediction error (approaching zero) was achieved, significantly showing the robust predictive capability of cool executive function in anticipating hot executive function. This outcome suggests potential relationships between the cognitive and emotional aspects of executive function.

The role of retail companies in the spatial development of the Russian Far East

Subject. This article discusses the importance of federal retailers and their impact on the spatial development of the Russian Far East in terms of ensuring territorial and economic accessibility of goods to the population. Objectives. The article aims to conduct a comprehensive study of the retail market of the Far Eastern Federal District and identify vectors of its development taking into account the federal retailers' entry into the retail market . Methods. For the study, I used the methods of statistical analysis and expert assessment. Results. The article identifies strategic areas for the development of retail trade in the context of digitalization, the growth of the e-commerce share, and the Turn to the East policy. Conclusions. The results of the study can be used when developing a strategy for the socio-economic and spatial development of the Far Eastern Federal District.

Development of a harmonized sociodemographic and clinical questionnaire for mental health research: A Delphi-method-based consensus recommendation.

Harmonized tools are essential for reliable data sharing and accurate identification of relevant factors in mental health research. The primary objective of this study was to create a harmonized questionnaire to collect demographic, clinical and behavioral data in diverse clinical trials in adult psychiatry. We conducted a literature review and examined 24 questionnaires used in previously published randomized controlled trials in psychiatry, identifying a total of 27 domains previously explored. Using a Delphi-method process, a task force team comprising experts in psychiatry, epidemiology and statistics selected 15 essential domains for inclusion in the final questionnaire. The final selection resulted in a concise set of 22 questions. These questions cover factors such as age, sex, gender, ancestry, education, living arrangement, employment status, home location, relationship status, and history of medical and mental illness. Behavioral factors like physical activity, diet, smoking, alcohol and illicit drug use were also included, along with one question addressing family history of mental illness. Income was excluded due to high confounding and redundancy, while language was included as a measure of migration status. The recommendation and adoption of this harmonized tool for the assessment of demographic, clinical and behavioral data in mental health research can enhance data consistency and enable comparability across clinical trials.

Modelling the Color and Microbial Properties of Canned Ngu by Response Surface Method

Background: Ngu is an African salad dressing used to improve the stability and shelf life of African salad. The aim of this study was to produce canned Ngu using three stabilizers at various concentrations, constant sterilization temperature, and varied sterilization times. Methods: Ngu (50 L) was prepared from potash using three stabilizers at various concentrations. A three-level factorial response surface design was applied to generate the experimental runs for the production of the canned Ngu. The Ngu emulsion was filled inside 250 ml bottle jars, sterilized at 121 oC at various times, and canned. The color of the canned Ngu was evaluated using the Comission Internationale de l'Eclairage color scale, and its microbiological attributes, Total Viable Count (TVC) and Total Fungal Count was determined with standard procedures. The effect of the stabilizers (Akparata, Ofo, and Carboxyl Methyl Cellulose), stabilizer concentration, and sterilization time on the color and microbial properties of the canned Ngu was assessed. The Statistical Software Design Expert version 8.0.7 was utilized for response surface analysis and derivation of model equation. Results: Increase in sterilization time increased the a* value and decreased the b* value of the canned Ngu. The quadratic effect of stabilizer, stabilizer concentration, and sterilization time indicated that the alteration of stabilizer from Carboxyl Methyl Cellulose to Akparata and then to Ofo increased the L* value, of the canned Ngu. An increase in the quadratic effect of stabilizer concentration increased the a* value but decreased the L* and b* values of the canned Ngu. However, the TVC and b* value of the canned Ngu reduced as the quadratic effects of the sterilization time increased. Conclusion: Total Fungal Count and TVC value of all the canned Ngu samples were within acceptable limits, ensuring the samples safe for human consumption.

Modelling hepatitis C infection acquired from blood transfusions in the UK between 1970 and 1991 for the Infected Blood Inquiry.

The Statistics Expert Group was convened at the request of the Infected Blood Inquiry to provide estimates of the number of infections and deaths from blood-borne infections including hepatitis B virus, human immunodeficiency virus, hepatitis C virus (HCV) and variant Creutzfeldt Jakob disease, as a direct result of contaminated blood and blood products administered in the United Kingdom of Great Britain and Northern Ireland (UK). In the absence of databases of HCV infections and related deaths for all nations of the UK, a statistical model was required to estimate the number of infections and subsequent deaths from HCV acquired from blood transfusions from January 1970 to August 1991. We present this statistical model in detail alongside the results of its application to each of the four nations in the UK. We estimated that 26 800 people (95% uncertainty interval 21 300-38 800) throughout the UK were chronically infected with HCV because of contaminated blood transfusions between January 1970 and August 1991. The number of deaths up to the end of 2019 that occurred as a result of this chronic infection is estimated to be 1820 (95% uncertainty interval 650-3320).

Breaking the Silence: Unveiling Child Abuse in Bangladesh

Child abuse is a grave global concern that goes beyond geographical, cultural, and socio-economic boundaries. Bangladesh is a country characterized by its rich cultural heritage and diverse population. It’s a densely populated South Asian nation, that has made significant strides in improving various aspects of human development over the past decades. However, despite these advancements, child abuse remains a significant challenge that demands urgent attention. Child abuse takes various forms, including physical, sexual, emotional, and neglectful abuse, each leaving scars that can impede a child&amp;apos;s potential to thrive and contribute positively to society. Moreover, the intricate tapestry of socioeconomic disparities, traditional practices, and limited access to education and healthcare services further compounds the vulnerabilities of children, often exposing them to increased risks of exploitation and maltreatment. This paper will delve into the prevailing cultural norms and societal attitudes that might perpetuate child abuse, exploring how traditional beliefs and practices intersect with modern challenges. By analyzing statistical data, academic research, and expert opinions, the study will provide a nuanced understanding of the scale of the problem, helping to identify gaps in current policy frameworks and protective mechanisms. Additionally, the research will scrutinize the role of various stakeholders, such as government agencies, non-governmental organizations, and international bodies, in addressing child abuse in Bangladesh.

A general framework for developing computable clinical phenotype algorithms.

To present a general framework providing high-level guidance to developers of computable algorithms for identifying patients with specific clinical conditions (phenotypes) through a variety of approaches, including but not limited to machine learning and natural language processing methods to incorporate rich electronic health record data. Drawing on extensive prior phenotyping experiences and insights derived from 3 algorithm development projects conducted specifically for this purpose, our team with expertise in clinical medicine, statistics, informatics, pharmacoepidemiology, and healthcare data science methods conceptualized stages of development and corresponding sets of principles, strategies, and practical guidelines for improving the algorithm development process. We propose 5 stages of algorithm development and corresponding principles, strategies, and guidelines: (1) assessing fitness-for-purpose, (2) creating gold standard data, (3) feature engineering, (4) model development, and (5) model evaluation. This framework is intended to provide practical guidance and serve as a basis for future elaboration and extension.

A roadmap to artificial intelligence (AI): Methods for designing and building AI ready data to promote fairness

ObjectivesWe evaluated methods for preparing electronic health record data to reduce bias before applying artificial intelligence (AI). MethodsWe created methods for transforming raw data into a data framework for applying machine learning and natural language processing techniques for predicting falls and fractures. Strategies such as inclusion and reporting for multiple races, mixed data sources such as outpatient, inpatient, structured codes, and unstructured notes, and addressing missingness were applied to raw data to promote a reduction in bias. The raw data was carefully curated using validated definitions to create data variables such as age, race, gender, and healthcare utilization. For the formation of these variables, clinical, statistical, and data expertise were used. The research team included a variety of experts with diverse professional and demographic backgrounds to include diverse perspectives. ResultsFor the prediction of falls, information extracted from radiology reports was converted to a matrix for applying machine learning. The processing of the data resulted in an input of 5,377,673 reports to the machine learning algorithm, out of which 45,304 were flagged as positive and 5,332,369 as negative for falls. Processed data resulted in lower missingness and a better representation of race and diagnosis codes. For fractures, specialized algorithms extracted snippets of text around keywork “femoral” from dual x-ray absorptiometry (DXA) scans to identify femoral neck T-scores that are important for predicting fracture risk. The natural language processing algorithms yielded 98% accuracy and 2% error rate The methods to prepare data for input to artificial intelligence processes are reproducible and can be applied to other studies. ConclusionThe life cycle of data from raw to analytic form includes data governance, cleaning, management, and analysis. When applying artificial intelligence methods, input data must be prepared optimally to reduce algorithmic bias, as biased output is harmful. Building AI-ready data frameworks that improve efficiency can contribute to transparency and reproducibility. The roadmap for the application of AI involves applying specialized techniques to input data, some of which are suggested here. This study highlights data curation aspects to be considered when preparing data for the application of artificial intelligence to reduce bias.