Limits...
Building Data-Driven Pathways From Routinely Collected Hospital Data: A Case Study on Prostate Cancer.

Bettencourt-Silva JH, Clark J, Cooper CS, Mills R, Rayward-Smith VJ, de la Iglesia B - JMIR Med Inform (2015)

Bottom Line: The extent and uses of such data rely on its quality, which is not consistently checked, nor fully understood.The proposed framework and pathway formalism enable the summarization, visualization, and querying of complex patient-centric clinical information, as well as the computation of quality indicators and dimensions.This is an important development for the reuse of big data in hospitals.

View Article: PubMed Central - HTML - PubMed

Affiliation: School of Computing Sciences, University of East Anglia, Norwich, United Kingdom. jhbs@cmp.uea.ac.uk.

ABSTRACT

Background: Routinely collected data in hospitals is complex, typically heterogeneous, and scattered across multiple Hospital Information Systems (HIS). This big data, created as a byproduct of health care activities, has the potential to provide a better understanding of diseases, unearth hidden patterns, and improve services and cost. The extent and uses of such data rely on its quality, which is not consistently checked, nor fully understood. Nevertheless, using routine data for the construction of data-driven clinical pathways, describing processes and trends, is a key topic receiving increasing attention in the literature. Traditional algorithms do not cope well with unstructured processes or data, and do not produce clinically meaningful visualizations. Supporting systems that provide additional information, context, and quality assurance inspection are needed.

Objective: The objective of the study is to explore how routine hospital data can be used to develop data-driven pathways that describe the journeys that patients take through care, and their potential uses in biomedical research; it proposes a framework for the construction, quality assessment, and visualization of patient pathways for clinical studies and decision support using a case study on prostate cancer.

Methods: Data pertaining to prostate cancer patients were extracted from a large UK hospital from eight different HIS, validated, and complemented with information from the local cancer registry. Data-driven pathways were built for each of the 1904 patients and an expert knowledge base, containing rules on the prostate cancer biomarker, was used to assess the completeness and utility of the pathways for a specific clinical study. Software components were built to provide meaningful visualizations for the constructed pathways.

Results: The proposed framework and pathway formalism enable the summarization, visualization, and querying of complex patient-centric clinical information, as well as the computation of quality indicators and dimensions. A novel graphical representation of the pathways allows the synthesis of such information.

Conclusions: Clinical pathways built from routinely collected hospital data can unearth information about patients and diseases that may otherwise be unavailable or overlooked in hospitals. Data-driven clinical pathways allow for heterogeneous data (ie, semistructured and unstructured data) to be collated over a unified data model and for data quality dimensions to be assessed. This work has enabled further research on prostate cancer and its biomarkers, and on the development and application of methods to mine, compare, analyze, and visualize pathways constructed from routine data. This is an important development for the reuse of big data in hospitals.

No MeSH data available.


Related in: MedlinePlus

The CaP VIS system showing the left side of the screen with the graphical representation of a castration resistant patient pathway. The patient was first treated with hormone therapy and had a subsequent palliative prostatic resection. The plotted pathway shows the trend of the PSA biomarker together with diagnosis line and treatments.
© Copyright Policy - open-access
Related In: Results  -  Collection

License 1 - License 2
getmorefigures.php?uid=PMC4526987&req=5

figure4: The CaP VIS system showing the left side of the screen with the graphical representation of a castration resistant patient pathway. The patient was first treated with hormone therapy and had a subsequent palliative prostatic resection. The plotted pathway shows the trend of the PSA biomarker together with diagnosis line and treatments.

Mentions: The main process responsible for producing the pathways starts from the ODS and follows steps 1a to 5a in Figure 3. Datasets were extracted from the ODS in the pathway format defined in the subsection “Defining a Pathway”, and used to build the pathway dictionary (as described in the subsection “Building the Pathway Dictionary and Database”), and the raw pathways database (following steps 1a and 2a). The pathways engine, which works with the information stored in the raw pathways database (step 3a), is responsible for the segmentation, summarization, cleansing, and indexing of the raw pathways. Such operations together allow for the mapping, selection, and retrieval of individual or groups of similar paths using regular expressions or ad-hoc algorithms. The detailed pathways are organized by patient identifier and stored as “plots” (following step 4a) that allow an interpreter and the visualization software (CaP VIS) to produce a detailed graphical representation (step 5a). The interpreter will parse each activity from a pathway and, based on the dictionary and a set of rules determined for each element code, plot the corresponding graphical representation. An important feature of the visualization system is to integrate the pathways with histopathological or further clinical information. A coding lookup table was added in order to translate and present diagnosis (International Classification of Diseases, ICD) and procedures (Office of Population Censuses and Surveys) codes (highlighted by the dotted lines in Figure 3). Because the time length of different pathways can vary considerably, it was important for the plot to be interactive, allowing zoom and rescale, as well as mechanisms for graphical conflict resolution (ie, avoiding overlapping elements). Figures 4 and 5 show sample output from the visualization software and a patient pathway and related information, including the pathway data format. The analysis engine can be used by the CaP VIS software to compute statistics for the pathways, but it can also be used on its own to develop algorithms that work with the pathways data. The subsection “Assessing Completeness Using Biomarker Information” demonstrates the use of the analysis engine in computing completeness scores for the PSA values in pathways. The analysis engine consists of a set of functions and libraries that are built in to main software, written in Python. In order to access the engine and perform operations, Python scripts can be written to access relevant functions that read information from pathways, generate graphical representations, compute PSA kinetics, or other statistics.


Building Data-Driven Pathways From Routinely Collected Hospital Data: A Case Study on Prostate Cancer.

Bettencourt-Silva JH, Clark J, Cooper CS, Mills R, Rayward-Smith VJ, de la Iglesia B - JMIR Med Inform (2015)

The CaP VIS system showing the left side of the screen with the graphical representation of a castration resistant patient pathway. The patient was first treated with hormone therapy and had a subsequent palliative prostatic resection. The plotted pathway shows the trend of the PSA biomarker together with diagnosis line and treatments.
© Copyright Policy - open-access
Related In: Results  -  Collection

License 1 - License 2
Show All Figures
getmorefigures.php?uid=PMC4526987&req=5

figure4: The CaP VIS system showing the left side of the screen with the graphical representation of a castration resistant patient pathway. The patient was first treated with hormone therapy and had a subsequent palliative prostatic resection. The plotted pathway shows the trend of the PSA biomarker together with diagnosis line and treatments.
Mentions: The main process responsible for producing the pathways starts from the ODS and follows steps 1a to 5a in Figure 3. Datasets were extracted from the ODS in the pathway format defined in the subsection “Defining a Pathway”, and used to build the pathway dictionary (as described in the subsection “Building the Pathway Dictionary and Database”), and the raw pathways database (following steps 1a and 2a). The pathways engine, which works with the information stored in the raw pathways database (step 3a), is responsible for the segmentation, summarization, cleansing, and indexing of the raw pathways. Such operations together allow for the mapping, selection, and retrieval of individual or groups of similar paths using regular expressions or ad-hoc algorithms. The detailed pathways are organized by patient identifier and stored as “plots” (following step 4a) that allow an interpreter and the visualization software (CaP VIS) to produce a detailed graphical representation (step 5a). The interpreter will parse each activity from a pathway and, based on the dictionary and a set of rules determined for each element code, plot the corresponding graphical representation. An important feature of the visualization system is to integrate the pathways with histopathological or further clinical information. A coding lookup table was added in order to translate and present diagnosis (International Classification of Diseases, ICD) and procedures (Office of Population Censuses and Surveys) codes (highlighted by the dotted lines in Figure 3). Because the time length of different pathways can vary considerably, it was important for the plot to be interactive, allowing zoom and rescale, as well as mechanisms for graphical conflict resolution (ie, avoiding overlapping elements). Figures 4 and 5 show sample output from the visualization software and a patient pathway and related information, including the pathway data format. The analysis engine can be used by the CaP VIS software to compute statistics for the pathways, but it can also be used on its own to develop algorithms that work with the pathways data. The subsection “Assessing Completeness Using Biomarker Information” demonstrates the use of the analysis engine in computing completeness scores for the PSA values in pathways. The analysis engine consists of a set of functions and libraries that are built in to main software, written in Python. In order to access the engine and perform operations, Python scripts can be written to access relevant functions that read information from pathways, generate graphical representations, compute PSA kinetics, or other statistics.

Bottom Line: The extent and uses of such data rely on its quality, which is not consistently checked, nor fully understood.The proposed framework and pathway formalism enable the summarization, visualization, and querying of complex patient-centric clinical information, as well as the computation of quality indicators and dimensions.This is an important development for the reuse of big data in hospitals.

View Article: PubMed Central - HTML - PubMed

Affiliation: School of Computing Sciences, University of East Anglia, Norwich, United Kingdom. jhbs@cmp.uea.ac.uk.

ABSTRACT

Background: Routinely collected data in hospitals is complex, typically heterogeneous, and scattered across multiple Hospital Information Systems (HIS). This big data, created as a byproduct of health care activities, has the potential to provide a better understanding of diseases, unearth hidden patterns, and improve services and cost. The extent and uses of such data rely on its quality, which is not consistently checked, nor fully understood. Nevertheless, using routine data for the construction of data-driven clinical pathways, describing processes and trends, is a key topic receiving increasing attention in the literature. Traditional algorithms do not cope well with unstructured processes or data, and do not produce clinically meaningful visualizations. Supporting systems that provide additional information, context, and quality assurance inspection are needed.

Objective: The objective of the study is to explore how routine hospital data can be used to develop data-driven pathways that describe the journeys that patients take through care, and their potential uses in biomedical research; it proposes a framework for the construction, quality assessment, and visualization of patient pathways for clinical studies and decision support using a case study on prostate cancer.

Methods: Data pertaining to prostate cancer patients were extracted from a large UK hospital from eight different HIS, validated, and complemented with information from the local cancer registry. Data-driven pathways were built for each of the 1904 patients and an expert knowledge base, containing rules on the prostate cancer biomarker, was used to assess the completeness and utility of the pathways for a specific clinical study. Software components were built to provide meaningful visualizations for the constructed pathways.

Results: The proposed framework and pathway formalism enable the summarization, visualization, and querying of complex patient-centric clinical information, as well as the computation of quality indicators and dimensions. A novel graphical representation of the pathways allows the synthesis of such information.

Conclusions: Clinical pathways built from routinely collected hospital data can unearth information about patients and diseases that may otherwise be unavailable or overlooked in hospitals. Data-driven clinical pathways allow for heterogeneous data (ie, semistructured and unstructured data) to be collated over a unified data model and for data quality dimensions to be assessed. This work has enabled further research on prostate cancer and its biomarkers, and on the development and application of methods to mine, compare, analyze, and visualize pathways constructed from routine data. This is an important development for the reuse of big data in hospitals.

No MeSH data available.


Related in: MedlinePlus