Background
-
What research objectives are answered in the included literature?
-
What recent methods have been used to identify sequences of care in health data?
-
How are the identified sequences represented?
Methods
Eligibility criteria
Data sources and search strategy
Study selection
Data extraction and synthesis
Results
Author | Title | Year | Ref. |
---|---|---|---|
Alharbi et al. | Towards Unsupervised Detection of Process Models in Healthcare | 2018 | [19] |
Baker et al. | Process mining routinely collected electronic health records to define real-life clinical pathways during chemotherapy | 2017 | [20] |
Bobroske et al. | The bird’ss-eye view: A data-driven approach to understanding patient journeys from claims data | 2020 | [21] |
Cerquitelli et al. | Exploiting clustering algorithms in a multiple-level fashion: A comparative study in the medical care scenario | 2016 | [22] |
Charles-Nelson et al. | Analysis of Trajectories of Care After Bariatric Surgery Using Data Mining Method and Health Administrative Information Systems | 2020 | [23] |
Chen et al. | A fusion framework to extract typical treatment patterns from electronic medical records | 2020 | [24] |
Chen et al. | A data-driven framework of typical treatment process extraction and evaluation | 2018 | [25] |
Cheng et al. | Medical Insurance Data Mining Using SPAM Algorithm | 2017 | [26] |
Cherrie et al. | Use of sequence analysis for classifying individual antidepressant trajectories to monitor population mental health | 2020 | [27] |
Chiudinelli et al. | Mining post-surgical care processes in breast cancer patients | 2020 | [28] |
Concaro et al. | Mining Health Care Administrative Data with Temporal Association Rules on Hybrid Events | 2011 | [29] |
Dagliati et al. | Careflow Mining Techniques to Explore Type 2 Diabetes Evolution | 2018 | [30] |
Dauxais et al. | Discriminant chronicles mining: Application to care pathways analytics | 2017 | [31] |
Egho et al. | A contribution to the discovery of multidimensional patterns in healthcare trajectories | 2014 | [32] |
Esmaili et al. | Multichannel micture models for time-series analysis and classification of engagement with multiple health services: An application to psychology and physiotherapy utlization patterns after traffic accidents | 2021 | [33] |
Estiri et al. | High-throughput phenotyping with temporal sequences | 2020 | [34] |
Han et al. | Hospitalization Pattern, Inpatient Service Utilization and Quality of Care in Patients With Alcohol Use Disorder: A Sequence Analysis of Discharge Medical Records | 2020 | [35] |
Hilton et al. | Uncovering Longitudinal Healthcare Behaviors for Millions of Medicaid Enrollees: A Multi-State Comparison of Pediatric Asthma Utilization | 2018 | [36] |
Honda et al. | Detection and visualization of variants in typical medical treatment sequences | 2017 | [37] |
Hur et al. | Facilitating the Development of Deep Learning Models with Visual Analytics for Electronic Health Records | 2020 | [38] |
Kempa-Liehr et al. | Healthcare pathway discovery and probabilistic machine learning | 2020 | [39] |
Ku et al. | Patient pathways of tuberculosis care-seeking and treatment: an individual-level analysis of National Health Insurance data in Taiwan | 2020 | [40] |
Lakshmanan et al. | Investigating clinical care pathways correlated with outcomes | 2013 | [10] |
Lambert-Coté et al. | Adherence trajectories of adjuvant endocrine therapy in the five years after its initiation among women with non-metastatic breast cancer: a cohort study using administrative databases | 2020 | [7] |
Le et al. | Analyzing Sequence Pattern Variants in Sequential Pattern Mining and Its Application to Electronic Medical Record Systems | 2019 | [41] |
Le Meur et al. | Mining care trajectories using health administrative information systems: the use of state sequence analysis to assess disparities in prenatal care consumption | 2015 | [42] |
Li et al. | Efficient Mining Template of predictive Temporal Clinical Event Patterns From Patient Electronic Medical Records | 2019 | [43] |
Meng et al. | Temporal phenotyping by mining healthcare data to derive lines of therapy for cancer | 2019 | [44] |
Najjar et al. | A two-step approach for mining patient treatment pathways in administrative healthcare databases | 2018 | [45] |
Nuemi et al. | Classification of hospital pathways in the management of cancer: Application to lung cancer in the region of burgundy | 2013 | [46] |
Oh et al. | Type 2 Diabetes Mellitus Trajectories and Associated Risks | 2016 | [47] |
Ou-Yang et al. | Mining Sequential Patterns of Diseases Contracted and Medications Prescribed before the Development of Stevens-Johnson Syndrome in Taiwan | 2019 | [48] |
Perer et al. | Mining and exploring care pathways from electronic medical records with visual analytics | 2015 | [49] |
Pokharel et al. | Representing EHRs with Temporal Tree and Sequential Pattern Mining for Similarity Computing | 2020 | [50] |
Rama et al. | AliClu - Temporal sequence alignment for clustering longitudinal clinical data | 2019 | [51] |
Rao A. et al. | Sequence Analysis of Long-Term Readmissions among High-Impact Users of Cerebrovascular Patients | 2017 | [52] |
Rao A. et al. | Common Sequences of Emergency Readmissions among High-Impact Users following AAA Repair | 2018 | [53] |
Rao G. et al. | Identifying, Analyzing, and Visualizing Diagnostic Paths for Patients with Nonspecific Abdominal Pain | 2018 | [54] |
Righolt et al. | Classification of drug use patterns | 2020 | [55] |
Roux et al. | Use of state sequence analysis for care pathway analysis: The example of multiple sclerosis | 2018 | [6] |
Solomon et al. | The sequence of disease-modifying anti-rheumatic drugs: pathways to and predictors of tocilizumab monotherapy | 2020 | [56] |
Sun et al. | Mining information dependency in outpatient encounters for chronic disease care | 2013 | [57] |
Vanasse et al. | Healthcare utilization after a first hospitalization for COPD: a new approach of State Sequence Analysis based on the ?6W? multidimensional model of care trajectories | 2020 | [5] |
Vogt et al. | Applying sequence clustering techniques to explore practice-based ambulatory care pathways in insurance claims data | 2017 | [58] |
Wang et al. | A framework for mining signatures from event sequences and its applications in healthcare data | 2013 | [59] |
Wright et al. | The use of sequential pattern mining to predict next prescribed medications | 2005 | [60] |
Yan et al. | Learning Clinical Workflows to Identify Subgroups of Heart Failure Patients | 2016 | [8] |
Zhang et al. | On Learning and Visualizing Practice-based Clinical Pathways for Chronic Kidney Disease | 2014 | [61] |
Zhang et al. | Innovations in Chronic Care Delivery Using Data-Driven Clinical Pathways | 2015 | [62] |
Zhang et al. | On clinical pathway discovery from electronic health record data | 2015 | [9] |
Zhang et al. | Paving the COWpath: Learning and visualizing clinical pathways from electronic health record data | 2015 | [66] |
General characteristics of identified studies
Data source and data information
Population and sample size
Chapter | Description of Chapter according to ICD-10 classification | N (%) | Ref. |
---|---|---|---|
1 | Certain infectious and parasitic diseases | 2 (4 %) | |
2 | Neoplasms | 8 (16 %) | |
4 | Endocrine, nutritional and metabolic diseases | 10 (20 %) | |
5 | Mental, Behavioral and Neurodevelopmental disorders | 2 (4 %) | |
6 | Diseases of the nervous system | 2 (4 %) | |
9 | Diseases of the circulatory system | 10 (20 %) | |
10 | Diseases of the respiratory system | 2 (4 %) | |
12 | Diseases of the skin and subcutaneous tissue | 1 (2 %) | [48] |
13 | Diseases of the musculoskeletal system and connective tissue | 3 (6 %) | |
14 | Diseases of the genitourinary system | 4 (16 %) | |
15 | Pregnancy, childbirth and the puerperium | 2 (4 %) | |
18 | Symptoms, signs and abnormal clinical and laboratory findings, not elsewhere classified | 2 (4 %) | |
20 | External causes of morbidity | 1 (1 %) | [33] |
– | other criterion for inclusion of individual data sets | 2 (4 %) |
Use of variables
What research questions are stated in the identified literature?
Stated aim in article | N | Publications | |
Proposal of method | 27 | ||
Trajectory | 28 | ||
Patterns | 20 | ||
Phenotyping | 9 | ||
Prediction | 11 | ||
Stated method in article | N (%) | Publications | |
Clustering | 16 (31 %) | ||
Hierarchical | 7 | ||
Partitioning | 5 | ||
Other Clustering | 4 | ||
Pattern Mining (PM) | 16 (31 %) | ||
PM + Clustering | 3 | ||
Markov Model | 10 (20 %) | ||
MM + Clustering | 7 | ||
Other | 9 (18 %) | ||
Presentation of results | N | Publications | |
Visualization | 36 | ||
Trajectory | 28 | ||
Patterns | 8 | ||
Weighted | 8 / 4 | ||
Sankey | 5 / 1 | Patterns: [49] | |
Timeline | 10 / 1 | Patterns: [24] | |
Tabular | 22 | ||
Trajectory | 5 | ||
Patterns | 17 | ||
Weighted | 2/14 |