Clinical Data Mining: a Review

Beyond the Spreadsheet: Data Management for Physicians in the Era of Big Data

Big Data is transforming health care. Characteristics of Big Data require data management strategies to effectively use, analyze, and apply the data. Clinicians are not typically learned in the fundamentals of these strategies which may cause a divide between collected data and data used. This article introduces the fundamentals of Big Data management and encourages clinicians to work with their information technology partners to further understand these processes and to identify opportunities for collaboration.

Exploring data reduction strategies in the analysis of continuous pressure imaging technology

BACKGROUND

Science is becoming increasingly data intensive as digital innovations bring new capacity for continuous data generation and storage. This progress also brings challenges, as many scientific initiatives are challenged by the shear volumes of data produced. Here we present a case study of a data intensive randomized clinical trial assessing the utility of continuous pressure imaging (CPI) for reducing pressure injuries.

OBJECTIVE

To explore an approach to reducing the amount of CPI data required for analyses to a manageable size without loss of critical information using a nested subset of pressure data.

METHODS

Data from four enrolled study participants excluded from the analytical phase of the study were used to develop an approach to data reduction. A two-step data strategy was used. First, raw data were sampled at different frequencies (5, 30, 60, 120, and 240 s) to identify optimal measurement frequency. Second, similarity between adjacent frames was evaluated using correlation coefficients to identify position changes of enrolled study participants. Data strategy performance was evaluated through visual inspection using heat maps and time series plots.

RESULTS

A sampling frequency of every 60 s provided reasonable representation of changes in interface pressure over time. This approach translated to using only 1.7% of the collected data in analyses. In the second step it was found that 160 frames within 24 h represented the pressure states of study participants. In total, only 480 frames from the 72 h of collected data would be needed for analyses without loss of information. Only ~ 0.2% of the raw data collected would be required for assessment of the primary trial outcome.

CONCLUSIONS

Data reduction is an important component of big data analytics. Our two-step strategy markedly reduced the amount of data required for analyses without loss of information. This data reduction strategy, if validated, could be used in other CPI and other settings where large amounts of both temporal and spatial data must be analysed.

Data Analytics in Healthcare: A Tertiary Study

The field of healthcare has seen a rapid increase in the applications of data analytics during the last decades. By utilizing different data analytic solutions, healthcare areas such as medical image analysis, disease recognition, outbreak monitoring, and clinical decision support have been automated to various degrees. Consequently, the intersection of healthcare and data analytics has received scientific attention to the point of numerous secondary studies. We analyze studies on healthcare data analytics, and provide a wide overview of the subject. This is a tertiary study, i.e., a systematic review of systematic reviews. We identified 45 systematic secondary studies on data analytics applications in different healthcare sectors, including diagnosis and disease profiling, diabetes, Alzheimer's disease, and sepsis. Machine learning and data mining were the most widely used data analytics techniques in healthcare applications, with a rising trend in popularity. Healthcare data analytics studies often utilize four popular databases in their primary study search, typically select 25-100 primary studies, and the use of research guidelines such as PRISMA is growing. The results may help both data analytics and healthcare researchers towards relevant and timely literature reviews and systematic mappings, and consequently, towards respective empirical studies. In addition, the meta-analysis presents a high-level perspective on prominent data analytics applications in healthcare, indicating the most popular topics in the intersection of data analytics and healthcare, and provides a big picture on a topic that has seen dozens of secondary studies in the last 2 decades.

An AI-driven Digital Health solution to support clinical management of long COVID patients: prospective multicenter observational study

Background

COVID-19 pandemic has revealed the weaknesses of most health systems around the world, collapsing them and depleting their available health care resources. Fortunately, the development and enforcement of specific public health policies, such as vaccination, mask wearing, and social distancing, among others, has reduced the prevalence and complications associated with COVID-19 in its acute phase. However, the aftermath of the global pandemic has called for an efficient approach to manage patients with long COVID-19. This is a great opportunity to leverage on innovative digital health solutions to provide exhausted health care systems with the most cost-effective and efficient tools available to support the clinical management of this population. In this context, the SENSING-AI project is focused on the research toward the implementation of an artificial intelligence–driven digital health solution that supports both the adaptive self-management of people living with long COVID-19 and the health care staff in charge of the management and follow-up of this population.

Objective

The objective of this protocol is the prospective collection of psychometric and biometric data from 10 patients for training algorithms and prediction models to complement the SENSING-AI cohort.

Methods

Publicly available health and lifestyle data registries will be consulted and complemented with a retrospective cohort of anonymized data collected from clinical information of patients diagnosed with long COVID-19. Furthermore, a prospective patient-generated data set will be captured using wearable devices and validated patient-reported outcomes questionnaires to complement the retrospective cohort. Finally, the ‘Findability, Accessibility, Interoperability, and Reuse’ guiding principles for scientific data management and stewardship will be applied to the resulting data set to encourage the continuous process of discovery, evaluation, and reuse of information for the research community at large.

Results

The SENSING-AI cohort is expected to be completed during 2022. It is expected that sufficient data will be obtained to generate artificial intelligence models based on behavior change and mental well-being techniques to improve patients’ self-management, while providing useful and timely clinical decision support services to health care professionals based on risk stratification models and early detection of exacerbations.

Conclusions

SENSING-AI focuses on obtaining high-quality data of patients with long COVID-19 during their daily life. Supporting these patients is of paramount importance in the current pandemic situation, including supporting their health care professionals in a cost-effective and efficient management of long COVID-19.

Trial Registration

Clinicaltrials.gov NCT05204615; https://clinicaltrials.gov/ct2/show/NCT05204615

International Registered Report Identifier (IRRID)

DERR1-10.2196/37704

Clinical phenotypes and prognostic factors of adult-onset Still's disease: data from a large inpatient cohort

Objectives

To define different clinical phenotypes and assess prognostic factors of adult-onset Still’s disease (AOSD).

Methods

Overall, 492 patients with AOSD seen between 2004 and 2018 at a single centre were retrospectively studied.

Results

Of these patients, 78% were female, and the median age at onset was 34 (25–49) years [median (25th–75th percentile)]. The median follow-up time was 7 (3–10) years [median (25th–75th percentile)]. Clinical manifestations at admission were used to subdivide patients with AOSD as follows: systemic inflammation (cluster 1), pure (cluster 2), and intermediate (cluster 3). Each subtype had distinct clinical manifestations and prognoses: cluster 1 (34.6%)—multiple organ manifestations, highest infection rate and mortality, and more than half of the patients with at least one relapse during follow-up; cluster 2 (21.3%)—exclusively female, rash and joint involvement, no internal organ involvement, no mortality, and most of the patients with a monocyclic course; and cluster 3 (44.1%)—less infection rate, no serious complications, and lower mortality rate. The 5- and 10-year survival rates after diagnosis were 92.4% and 86.9%, respectively. Independent risk factors for mortality were age at onset ≥50 (hazard ratio (HR): 6.78, 95% CI: 2.10–21.89), hepatomegaly (HR: 5.05, 95% CI: 1.44–17.70), infection (HR: 15.56, 95% CI: 5.88–41.20), and MAS (HR: 26.82, 95% CI: 7.52–95.60).

Conclusion

Three subtypes of AOSD were identified with distinct clinical manifestations and prognoses. Age at onset ≥50, hepatomegaly, infection, and MAS were prognostic factors for AOSD mortality.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13075-021-02688-4.

Recent Developments in Privacy-Preserving Mining of Clinical Data

With the dramatic increases in both the capability to collect personal data and the capability to analyze large amounts of data, increasingly sophisticated and personal insights are being drawn. These insights are valuable for clinical applications but also open up possibilities for identification and abuse of personal information. In this paper, we survey recent research on classical methods of privacy-preserving data mining. Looking at dominant techniques and recent innovations to them, we examine the applicability of these methods to the privacy-preserving analysis of clinical data. We also discuss promising directions for future research in this area.

ELII: A novel inverted index for fast temporal query, with application to a large Covid-19 EHR dataset

Fast temporal query on large EHR-derived data sources presents an emerging big data challenge, as this query modality is intractable using conventional strategies that have not focused on addressing Covid-19-related research needs at scale. We introduce a novel approach called Event-level Inverted Index (ELII) to optimize time trade-offs between one-time batch preprocessing and subsequent open-ended, user-specified temporal queries. An experimental temporal query engine has been implemented in a NoSQL database using our new ELII strategy. Near-real-time performance was achieved on a large Covid-19 EHR dataset, with 1.3 million unique patients and 3.76 billion records. We evaluated the performance of ELII on several types of queries: classical (non-temporal), absolute temporal, and relative temporal. Our experimental results indicate that ELII accomplished these queries in seconds, achieving average speed accelerations of 26.8 times on relative temporal query, 88.6 times on absolute temporal query, and 1037.6 times on classical query compared to a baseline approach without using ELII. Our study suggests that ELII is a promising approach supporting fast temporal query, an important mode of cohort development for Covid-19 studies.

Recommendation System Using Autoencoders

The magnitude of the daily explosion of high volumes of data has led to the emergence of the Big Data paradigm. The ever-increasing amount of information available on the Internet makes it increasingly difficult for individuals to find what they need quickly and easily. Recommendation systems have appeared as a solution to overcome this problem. Collaborative filtering is widely used in this type of systems, but high dimensions and data sparsity are always a main problem. With the idea of deep learning gaining more importance, several works have emerged to improve this type of filtering. In this article, a product recommendation system is proposed where an autoencoder based on a collaborative filtering method is employed. A comparison of this model with the Singular Value Decomposition is made and presented in the results section. Our experiment shows a very low Root Mean Squared Error (RMSE) value, considering that the recommendations presented to the users are in line with their interests and are not affected by the data sparsity problem as the datasets are very sparse, 0.996. The results are quite promising achieving an RMSE value of 0.029 in the first dataset and 0.010 in the second one.

Data Mining in HIV-AIDS Surveillance System : Application to Portuguese Data

The Human Immunodeficiency Virus (HIV) is an infectious agent that attacks the immune system cells. Without a strong immune system, the body becomes very susceptible to serious life threatening opportunistic diseases. In spite of the great progresses on medication and prevention over the last years, HIV infection continues to be a major global public health issue, having claimed more than 36 million lives over the last 35 years since the recognition of the disease. Monitoring, through registries, of HIV-AIDS cases is vital to assess general health care needs and to support long-term health-policy control planning. Surveillance systems are therefore established in almost all developed countries. Typically, this is a complex system depending on several stakeholders, such as health care providers, the general population and laboratories, which challenges an efficient and effective reporting of diagnosed cases. One issue that often arises is the administrative delay in reports of diagnosed cases. This paper aims to identify the main factors influencing reporting delays of HIV-AIDS cases within the portuguese surveillance system. The used methodologies included multilayer artificial neural networks (MLP), naive bayesian classifiers (NB), support vector machines (SVM) and the k-nearest neighbor algorithm (KNN). The highest classification accuracy, precision and recall were obtained for MLP and the results suggested homogeneous administrative and clinical practices within the reporting process. Guidelines for reductions of the delays should therefore be developed nationwise and transversally to all stakeholders.

Data analysis and data mining: current issues in biomedical informatics

BACKGROUND

Medicine and biomedical sciences have become data-intensive fields, which, at the same time, enable the application of data-driven approaches and require sophisticated data analysis and data mining methods. Biomedical informatics provides a proper interdisciplinary context to integrate data and knowledge when processing available information, with the aim of giving effective decision-making support in clinics and translational research.

OBJECTIVES

To reflect on different perspectives related to the role of data analysis and data mining in biomedical informatics.

METHODS

On the occasion of the 50th year of Methods of Information in Medicine a symposium was organized, which reflected on opportunities, challenges and priorities of organizing, representing and analysing data, information and knowledge in biomedicine and health care. The contributions of experts with a variety of backgrounds in the area of biomedical data analysis have been collected as one outcome of this symposium, in order to provide a broad, though coherent, overview of some of the most interesting aspects of the field.

RESULTS

The paper presents sections on data accumulation and data-driven approaches in medical informatics, data and knowledge integration, statistical issues for the evaluation of data mining models, translational bioinformatics and bioinformatics aspects of genetic epidemiology.

CONCLUSIONS

Biomedical informatics represents a natural framework to properly and effectively apply data analysis and data mining methods in a decision-making context. In the future, it will be necessary to preserve the inclusive nature of the field and to foster an increasing sharing of data and methods between researchers.