Address Data Quality Research Articles

Incremental Machine Learning-integrated Blockchain for Real-time Security Protection in Cyber-enabled Manufacturing Systems

Abstract Cyber-enabled manufacturing systems become increasingly data-rich, generating vast amounts of real-time sensor data for quality control and process optimization. However, it also exposes these systems to significant cyber-physical security threats. For instance, attackers may delete, change, or replace data, leading to defective products, damaged equipment, or operational safety hazards. False data injection attacks can compromise machine learning (ML) models, resulting in erroneous outcomes. To mitigate these risks, it is crucial to employ robust data processing techniques that can adapt to varying process conditions and detect anomalies in real-time. In this context, incremental machine learning (IML) can be valuable, allowing models to be updated incrementally with newly collected data without retraining from scratch. Moreover, although recent studies have demonstrated the potential of blockchain in enhancing data security in manufacturing systems, most existing frameworks are primarily based on cryptography, which does not sufficiently address data quality issues. Thus, this study proposes a gatekeeper mechanism to integrate IML with blockchain and discusses how this integration could potentially increase data integrity of cyber-enabled manufacturing systems. The proposed IML-integrated blockchain can potentially address data security concerns from both intentional (e.g., malicious tampering) and unintentional alterations (e.g., process anomalies). The case study results show that the proposed gatekeeper integration algorithm can successfully filter out over 80% of malicious data entries while maintaining comparable classification performance to standard IML models. Furthermore, the integration of blockchain enables effective detection of tampering attempts, ensuring the trustworthiness of the stored information.

Http://www.mejfm.com/JanFeb%202025/Mobile%20health.htm

Background: Mobile health (mHealth), a subset of digital health, uses mobile applications, wearables, and monitoring technologies to enhance remote and continuous healthcare services. It aims to revolutionise healthcare through individualised, precise and on-demand care. Objectives: This review explores current and future applications and potential of mHealth technologies. It examines the rapidly expanding and revolutionary role of mHealth in healthcare delivery and highlights potential barriers and dilemmas. Methods: A synthesis of recent literature was conducted to provide an overview of mHealth developments, applications, and growing challenges, including data quality, governance, and regulatory gaps. Results: mHealth applications rapidly expand into multiple health fields, from fitness to mental health and chronic disease. The rapidly evolving mHealth technology promises improved health outcomes through real-time monitoring and tailored interventions. Despite significant advancements, real challenges involving data privacy, accessibility and equity, technology validation, and concerns about commercial influence on governance and regulations further complicate the landscape. Conclusions: mHealth offers transformative potential for medicine and achieving precise and individualised healthcare. However, addressing data quality, ethical, and governance challenges is critical for sustainable growth and fully realising mHealth’s benefits in addressing global healthcare needs. Key words : Mobile health, Digital health, Wearables, Remote health monitoring, Digital health applications

Artificial intelligence in surgery: evolution, trends, and future directions.

Artificial intelligence (AI) is significantly transforming surgery by enhancing precision, decision-making, and patient outcomes. This bibliometric analysis examines AI's impact on surgery, highlighting research trends, key contributors, and evolving themes from 1998 to 2024. Utilizing data from the Web of Science Core Collection and analyzed through the Bibliometrix tool, the study reviews publication trends, author impact, institutional contributions, country-specific research activities, and keyword frequency. A total of 821 articles were examined, revealing a 14.53% annual growth rate in publications, increasing from one in 1998 to 328 in 2023. Influential contributors include 10157 authors, notably HASHIMOTO DA and ITO M. Prominent institutions such as Harvard University and Stanford University, along with leading countries like the USA and China, play major roles in this field. High-frequency keywords identify core research areas: surgery, artificial intelligence, classification, diagnosis, and outcomes. Thematic evolution shows a shift from foundational concepts to advanced applications and interdisciplinary collaborations. AI integration into surgical practices is revolutionizing the field, driving advancements in precision, efficiency, and patient care. The study underscores significant research growth, influential contributors, and key trends, emphasizing the importance of continued interdisciplinary collaboration and innovation. Future research should focus on enhancing AI applications, addressing data quality and security challenges, and expanding into diverse surgical contexts to further improve surgical outcomes and patient care. AI in surgery is a rapidly evolving and promising field for innovation, with its full potential reliant on enhanced collaboration across disciplines.

Solutions for Lithium Battery Materials Data Issues in Machine Learning: Overview and Future Outlook.

The application of machine learning (ML) techniques in the lithium battery field is relatively new and holds great potential for discovering new materials, optimizing electrochemical processes, and predicting battery life. However, the accuracy of ML predictions is strongly dependent on the underlying data, while the data of lithium battery materials faces many challenges, such as the multi-sources, heterogeneity, high-dimensionality, and small-sample size. Through the systematic review of the existing literatures, several effective strategies are proposed for data processing as follows: classification and extraction, screening and exploration, dimensionality reduction and generation, modeling and evaluation, and incorporation of domain knowledge, with the aim to enhance the data quality, model reliability, and interpretability. Furthermore, other possible strategies for addressing data quality such as database management techniques and data analysis methodologies are also emphasized. At last, an outlook of ML development for data processing methods is presented. These methodologies are not only applicable to the data of lithium battery materials, but also endow important reference significance to electrocatalysis, electrochemical corrosion, high-entropy alloys, and other fields with similar data challenges.

Addressing data quality issues to assess clinical and epidemiological risk factors for COVID-19 among documented cases in Liberia: a single-centre, retrospective, observational study

IntroductionIdentification of risk factors for severe COVID-19 can help to inform case management in resource-constrained settings. We aimed to rigorously but retroactively address data issues to identify risk factors for...

Data quality in hospital information systems: Lessons learned from analyzing 30 years of patient data in a regional German hospital

Background: The integration of Hospital Information Systems (HIS) into healthcare delivery has significantly enhanced patient care and operational efficiency. Nonetheless, the rapid acceleration of digital transformation has led to a substantial increase in the volume of data managed by these systems. This emphasizes the need for robust mechanisms for data management and quality assurance.Objective: This study addresses data quality issues related to patient identifiers within the Hospital Information System (HIS) of a regional German hospital, focusing on improving the accuracy and consistency of these administrative data entries.Methods: Employing a combination of data analysis and expert interviews, this study reviews and programmatically cleanses a dataset with over 2,000,000 patient data entries extracted from the HIS. The areas of investigation are patient admissions, discharges, and geographical data.Results: The analysis revealed that roughly 25% of the dataset was rendered unusable by errors and inconsistencies. By implementing a thorough data cleansing process, we significantly enhanced the utility of the dataset. In doing so, we identified the primary issues affecting data quality, including ambiguities among similar variables and a gap between the intended and actual use of the system.Conclusion: The findings highlight the critical importance of enhancing data quality in healthcare information systems. This study shows the necessity of a careful review of data extracted from the HIS before it can be reliably utilized for machine learning tasks, thereby rendering the data more usable for both clinical and analytical purposes.

What’s in a name field?

The National Center for Health Statistics (NCHS) has a data linkage program that combines national survey data with key sources of health outcomes and health care utilization. The overall accuracy and quality of a data linkage depends on the quality of the data fields. This applies in a variety of data linkage methods, including clear text and privacy preserving record linkage. Data pre-processing and cleaning are essential to address data quality issues in most linkage tasks. Automating data cleaning prevents time-consuming manual reviews particularly when linkages involve a large number of records. For some data fields, these activities are relatively straightforward. For example, dates typically have a limited number of plausible values that make checking and cleaning relatively easy and straightforward. Unique identifiers (e.g., social security number) often conform to some set format or have restrictions on the values that would be expected. Other data fields such as first name and last name present greater challenges with respect to automating the cleaning process. For some data sources, first name and last name fields may contain non-name text that needs to be identified and removed. In this project, we examined the use of an artificial intelligence (AI) based large language model (LLM) and a simple rule-based algorithm to identify non-name text in name fields that should be removed prior to linkage. We also investigated the impact of automated name clean-up algorithms on the quality of an example linkage.

An Applied Research Partnership to Improve The Children’s Behavioral Health System Of Care

Objective and ApproachThis session describes a doctoral student-led process to align research, policy, and practice partners around the use of integrated data to address a policy priority—the mounting youth mental health crisis. The project partners engaged in a five-year governance process to leverage integrated administrative data from a large health and human service agency in one U.S. state. Qualitative field notes—collected while conducting quantitative analyses and engaging partners—were analyzed to document a realistic timeline and process for ethical, actionable research using cross-sector data. ResultsFive key lessons for partnership-engaged research emerged, emphasizing the importance of adapting to changes in project themes, leveraging strong partnership to address data quality concerns, nurturing existing and new relationships, balancing data access and data privacy, and supplementing administrative data with contextual data. ConclusionsThough engaging deeply with partners takes substantial time and energy, there are benefits to researchers, policymakers, practitioners, and most importantly, residents whose data are represented. Furthermore, building pathways to legally and ethically access integrated data can promote the efficient, strategic use of data for social policy research, and ultimately, be leveraged to support evidence-based policymaking in an ever-changing world. ImplicationsThis session underscores the value of forming applied research partnerships and building legal and ethical pathways to access integrated data when tackling complex social policy issues.

Exploring Machine Learning Applications in Pediatric Asthma Management: Scoping Review.

The integration of machine learning (ML) in predicting asthma-related outcomes in children presents a novel approach in pediatric health care. This scoping review aims to analyze studies published since 2019, focusing on ML algorithms, their applications, and predictive performances. We searched Ovid MEDLINE ALL and Embase on Ovid, the Cochrane Library (Wiley), CINAHL (EBSCO), and Web of Science (core collection). The search covered the period from January 1, 2019, to July 18, 2023. Studies applying ML models in predicting asthma-related outcomes in children aged <18 years were included. Covidence was used for citation management, and the risk of bias was assessed using the Prediction Model Risk of Bias Assessment Tool. From 1231 initial articles, 15 met our inclusion criteria. The sample size ranged from 74 to 87,413 patients. Most studies used multiple ML techniques, with logistic regression (n=7, 47%) and random forests (n=6, 40%) being the most common. Key outcomes included predicting asthma exacerbations, classifying asthma phenotypes, predicting asthma diagnoses, and identifying potential risk factors. For predicting exacerbations, recurrent neural networks and XGBoost showed high performance, with XGBoost achieving an area under the receiver operating characteristic curve (AUROC) of 0.76. In classifying asthma phenotypes, support vector machines were highly effective, achieving an AUROC of 0.79. For diagnosis prediction, artificial neural networks outperformed logistic regression, with an AUROC of 0.63. To identify risk factors focused on symptom severity and lung function, random forests achieved an AUROC of 0.88. Sound-based studies distinguished wheezing from nonwheezing and asthmatic from normal coughs. The risk of bias assessment revealed that most studies (n=8, 53%) exhibited low to moderate risk, ensuring a reasonable level of confidence in the findings. Common limitations across studies included data quality issues, sample size constraints, and interpretability concerns. This review highlights the diverse application of ML in predicting pediatric asthma outcomes, with each model offering unique strengths and challenges. Future research should address data quality, increase sample sizes, and enhance model interpretability to optimize ML utility in clinical settings for pediatric asthma management.

Data Integration for a Global Deep-Phenotyping Registry for Pulmonary Hypertension - Lessons Learned.

The integration of data from various healthcare centers into disease registries is pivotal for facilitating collaborative research and enhancing clinical insights. In this study, we investigate the integration process of existing registries into the PVRI GoDeep meta-registry, focusing on the complexities and challenges encountered. We detail the integration process, including data transformation, mapping updates, and feedback mechanisms. Our findings underscore the importance of standardized processes and proactive communication in addressing data quality issues, ultimately enhancing the reliability and trustworthiness of meta-registry data. Through careful harmonization of the data and transparent documentation of data processing, we pave the way for leveraging registry data to drive advancements in pulmonary hypertension research and patient care.

Data quality assurance practices in research data repositories—A systematic literature review. An Annual Review of Information Science and Technology (ARIST) paper

AbstractData quality issues can significantly hinder research reproducibility, data sharing, and reuse. At the forefront of addressing data quality issues are research data repositories (RDRs). This study conducted a systematic analysis of data quality assurance (DQA) practices in RDRs, guided by activity theory and data quality literature, resulting in conceptualizing a data quality assurance model (DQAM) for RDRs. DQAM outlines a DQA process comprising evaluation, intervention, and communication activities and categorizes 17 quality dimensions into intrinsic and product‐level data quality. It also details specific improvement actions for data products and identifies the essential roles, skills, standards, and tools for DQA in RDRs. By comparing DQAM with existing DQA models, the study highlights its potential to improve these models by adding a specific DQA activity structure. The theoretical implication of the study is a systematic conceptualization of DQA work in RDRs that is grounded in a comprehensive analysis of the literature and offers a refined conceptualization of DQA integration into broader frameworks of RDR evaluation. In practice, DQAM can inform the design and development of DQA workflows and tools. As a future research direction, the study suggests applying and evaluating DQAM across various domains to validate and refine this model further.

XRAInet: AI-based decision support for pneumothorax and pleural effusion management.

This study aimed to develop and assess the performance of an artificial intelligence(AI)-driven decision support system, XRAInet, in accurately identifying pediatric patients with pleural effusion or pneumothorax and determining whether tube thoracostomy intervention is warranted. In this diagnostic accuracy study, we retrospectively analyzed a data set containing 510 X-ray images from 170 pediatric patients admitted between 2005 and 2022. Patients were categorized into two groups: Tube (requiring tube thoracostomy) and Conservative (managed conservatively). XRAInet, a deep learning-based algorithm, was trained using this data set. We evaluated its performance using various metrics, including mean Average Precision (mAP), recall, precision, and F1 score. XRAInet, achieved a mAP score of 0.918. This result underscores its ability to accurately identify and localize regions necessitating tube thoracostomy for pediatric patients with pneumothorax and pleural effusion. In an independent testing data set, the model exhibited a sensitivity of 64.00% and specificity of 96.15%. In conclusion, XRAInet presents a promising solution for improving the detection and decision-making process for cases of pneumothorax and pleural effusion in pediatric patients using X-ray images. These findings contribute to the expanding field of AI-driven medical imaging, with potential applications for enhancing patient outcomes. Future research endeavors should explore hybrid models, enhance interpretability, address data quality issues, and align with regulatory requirements to ensure the safe and effective deployment of XRAInet in healthcare settings.

Implementing machine learning models in business analytics: challenges, solutions, and impact on decision-making

This research paper explores the challenges, solutions, and impact of implementing machine learning (ML) models in business analytics. It delves into the complexities of integrating ML into decision-making processes, addressing data quality, technical infrastructure, organizational dynamics, and ethical considerations. Analyzing emerging trends and strategic recommendations, the paper provides insights for businesses seeking to leverage ML for enhanced decision-making and competitive advantage. Examining case examples and discussing future directions underscores the transformative potential of ML in reshaping industries and unlocking new opportunities for growth and success.

AI in Dermatology: A Systematic Review on Skin Cancer Detection

Skin cancer is the most common type of cancer worldwide and poses a significant public health challenge. Its visible nature often leads individuals to seek medical attention, highlighting the importance of early detection for better patient outcomes. In recent years, Artificial Intelligence (AI) has shown promise in improving the detection and diagnosis of skin cancer, offering the potential to enhance clinical outcomes. A systematic review was conducted, involving a comprehensive literature search to identify studies focused on AI techniques in detecting, diagnosing, or treating skin cancer. Strict inclusion and exclusion criteria were applied to assess the eligibility of scientific articles, resulting in the selection of nine relevant studies. These studies were analyzed to address predefined research questions about the effectiveness of AI in diagnosing skin cancer. The review found that AI-assisted clinicians achieved higher sensitivity and specificity in diagnosing skin cancer than those without assistance. Various AI algorithms demonstrated high sensitivity in detecting skin cancers, highlighting their potential to support primary care clinicians in evaluating suspicious lesions. The analysis also highlighted the effectiveness of smartphone applications designed for skin cancer risk assessment, which could facilitate self-examinations and enhance early detection rates. Despite these promising findings, the field of AI in skin cancer diagnosis is still in its early stages. Challenges remain, including developing robust algorithms, addressing data quality issues, and improving the interpretability of AI-generated results. Collaboration between AI developers and healthcare professionals is crucial to ensure these tools' clinical effectiveness and safety. The review emphasizes the need for continued validation of AI technologies and their integration into clinical practice to improve patient outcomes and alleviate the burden on healthcare systems.

SCSQ: A sample cooperation optimization method with sample quality for recurrent neural networks

Time series forecasting holds significant value across various application scenarios. However, practical implementations often encounter challenges related to low-quality time series data resulting from system failures or external interference. Unfortunately, existing forecasting methods primarily focus on optimizing model architecture for accurate predictions and overlook the importance of addressing data quality issues. In this paper, we propose optimizing data utilization to enhance model performance based on data quality and introduce the Sample Cooperation with Sample Quality (SCSQ) method to facilitate recurrent neural networks training. Firstly, we define sample quality as the matching degree between samples and model, and suggest using the attention entropy to calculate the sample quality through an attention mechanism. Secondly, we optimize the model's gradient vector based on sample quality. To address optimization training involving samples of different qualities effectively, we propose a more reasonable objective function within our proposed sample gradient conflict optimization module and devise a novel algorithm leveraging approximation techniques along with ADMM algorithm implementation. Through experiments conducted on six datasets, the results demonstrate that SCSQ significantly improves LSTM's performance. In certain cases, it even surpasses the state-of-the-art models. Additionally, SCSQ enhances the anti-interference ability of LSTM against low-quality samples.

Advances in filarial hydrocelectomy reporting in Uganda and Nigeria

IntroductionSurgery for hydrocele is part of the WHO recommended essential package of care for people affected by Lymphatic filariasis (LF). In Uganda and Nigeria, LF programme support for hydrocele surgery began in 2017. In 2021 the two programmes adopted a newly developed smartphone-based application to monitor hydrocele surgery and outcome. The application, referred to as the Hydrocele Tracker, gathers information on surgical registration, preoperative information, intraoperative information, postoperative information and follow-up evaluations. It was developed to improve supervision, understand surgical outcomes and reasons for complications, improve reporting and improve data quality for Ministries of Health with active LF programmes.MethodsHydrocele patient information was collected between October 2021 and May 2023 in Uganda (Lango sub-region, 9 districts) and March 2021 - September 2022 in Nigeria (Benue, Kaduna, Kebbi, Sokoto and Kogi States). Additionally patient feedback surveys were undertaken to elicit patient experience and satisfaction with the hydrocele surgery.ResultsPatient data from 2,911 records in the Hydrocele Tracker are presented.DiscussionThe discussion highlights the implications of the data for LF programming, the value of digitisation and approaches to address data quality.

Electronic Health Records for Predicting Outcomes to Work-Related Musculoskeletal Disorders: A Scoping Review.

Through electronic health records (EHRs), musculoskeletal (MSK) therapists such as chiropractors and physical therapists, as well as occupational medicine physicians could collect data on many variables that can be traditionally challenging to collect in managing work-related musculoskeletal disorders (WMSDs). The review's objectives were to explore the extent of research using EHRs in predicting outcomes of WMSDs by MSK therapists. A systematic search was conducted in Medline, PubMed, CINAHL, and Embase. Grey literature was searched. 2156 unique papers were retrieved, of which 38 were included. Three themes were explored, the use of EHRs to predict outcomes to WMSDs, data sources for predicting outcomes to WMSDs, and adoption of standardised information for managing WMSDs. Predicting outcomes of all MSK disorders using EHRs has been researched in 6 studies, with only 3 focusing on MSK therapists and 4 addressing WMSDs. Similar to all secondary data source research, the challenges include data quality, missing data and unstructured data. There is not yet a standardised or minimum set of data that has been defined for MSK therapists to collect when managing WMSD. Further work based on existing frameworks is required to reduce the documentation burden and increase usability. The review outlines the limited research on using EHRs to predict outcomes of WMSDs. It highlights the need for EHR design to address data quality issues and develop a standardised data set in occupational healthcare that includes known factors that potentially predict outcomes to help regulators, research efforts, and practitioners make better informed clinical decisions.

“Allot?” is “A Lot!” Towards Developing More Generalized Speech Recognition System for Accessible Communication

The proliferation of Automatic Speech Recognition (ASR) systems has revolutionized translation and transcription. However, challenges persist in ensuring inclusive communication for non-native English speakers. This study quantifies the gap between accented and native English speech using Wav2Vec 2.0, a state-of-the-art transformer model. Notably, we found that accented speech exhibits significantly higher word error rates of 30-50%, in contrast to native speakers’ 2-8% (Baevski et al. 2020). Our exploration extends to leveraging accessible online datasets to highlight the potential of enhancing speech recognition by fine-tuning the Wav2Vec 2.0 model. Through experimentation and analysis, we highlight the challenges with training models on accented speech. By refining models and addressing data quality issues, our work presents a pipeline for future investigations aimed at developing an integrated system capable of effectively engaging with a broader range of individuals with diverse backgrounds. Accurate recognition of accented speech is a pivotal step toward democratizing AI-driven communication products.

Estimating multiplicity of infection, allele frequencies, and prevalences accounting for incomplete data.

Molecular surveillance of infectious diseases allows the monitoring of pathogens beyond the granularity of traditional epidemiological approaches and is well-established for some of the most relevant infectious diseases such as malaria. The presence of genetically distinct pathogenic variants within an infection, referred to as multiplicity of infection (MOI) or complexity of infection (COI) is common in malaria and similar infectious diseases. It is an important metric that scales with transmission intensities, potentially affects the clinical pathogenesis, and a confounding factor when monitoring the frequency and prevalence of pathogenic variants. Several statistical methods exist to estimate MOI and the frequency distribution of pathogen variants. However, a common problem is the quality of the underlying molecular data. If molecular assays fail not randomly, it is likely to underestimate MOI and the prevalence of pathogen variants. A statistical model is introduced, which explicitly addresses data quality, by assuming a probability by which a pathogen variant remains undetected in a molecular assay. This is different from the assumption of missing at random, for which a molecular assay either performs perfectly or fails completely. The method is applicable to a single molecular marker and allows to estimate allele-frequency spectra, the distribution of MOI, and the probability of variants to remain undetected (incomplete information). Based on the statistical model, expressions for the prevalence of pathogen variants are derived and differences between frequency and prevalence are discussed. The usual desirable asymptotic properties of the maximum-likelihood estimator (MLE) are established by rewriting the model into an exponential family. The MLE has promising finite sample properties in terms of bias and variance. The covariance matrix of the estimator is close to the Cramér-Rao lower bound (inverse Fisher information). Importantly, the estimator's variance is larger than that of a similar method which disregards incomplete information, but its bias is smaller. Although the model introduced here has convenient properties, in terms of the mean squared error it does not outperform a simple standard method that neglects missing information. Thus, the new method is recommendable only for data sets in which the molecular assays produced poor-quality results. This will be particularly true if the model is extended to accommodate information from multiple molecular markers at the same time, and incomplete information at one or more markers leads to a strong depletion of sample size.

Free and open-source QSAR-ready workflow for automated standardization of chemical structures in support of QSAR modeling

The rapid increase of publicly available chemical structures and associated experimental data presents a valuable opportunity to build robust QSAR models for applications in different fields. However, the common concern is the quality of both the chemical structure information and associated experimental data. This is especially true when those data are collected from multiple sources as chemical substance mappings can contain many duplicate structures and molecular inconsistencies. Such issues can impact the resulting molecular descriptors and their mappings to experimental data and, subsequently, the quality of the derived models in terms of accuracy, repeatability, and reliability. Herein we describe the development of an automated workflow to standardize chemical structures according to a set of standard rules and generate two and/or three-dimensional “QSAR-ready” forms prior to the calculation of molecular descriptors. The workflow was designed in the KNIME workflow environment and consists of three high-level steps. First, a structure encoding is read, and then the resulting in-memory representation is cross-referenced with any existing identifiers for consistency. Finally, the structure is standardized using a series of operations including desalting, stripping of stereochemistry (for two-dimensional structures), standardization of tautomers and nitro groups, valence correction, neutralization when possible, and then removal of duplicates. This workflow was initially developed to support collaborative modeling QSAR projects to ensure consistency of the results from the different participants. It was then updated and generalized for other modeling applications. This included modification of the “QSAR-ready” workflow to generate “MS-ready structures” to support the generation of substance mappings and searches for software applications related to non-targeted analysis mass spectrometry. Both QSAR and MS-ready workflows are freely available in KNIME, via standalone versions on GitHub, and as docker container resources for the scientific community. Scientific contribution: This work pioneers an automated workflow in KNIME, systematically standardizing chemical structures to ensure their readiness for QSAR modeling and broader scientific applications. By addressing data quality concerns through desalting, stereochemistry stripping, and normalization, it optimizes molecular descriptors' accuracy and reliability. The freely available resources in KNIME, GitHub, and docker containers democratize access, benefiting collaborative research and advancing diverse modeling endeavors in chemistry and mass spectrometry.