Symbolic Classification Methods for Patient Discharge Summaries Encoding into ICD

Kevers, Laurent; Medori, Julia

doi:10.1007/978-3-642-14770-8_23

Cited by 3 publications

(4 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other studies exist that used SNOMED-CT (Cornet and de Keizer, 2008;Lussier et al, 2001), UMLS (Friedman et al, 2004), ICF (Kukafka et al, 2006) and procedure classification (ICD-10-PCS) (Subotin and Davis, 2014). The corpora of clinical records used in previous studies ranged from admission notes (Gundersen et al, 1996) to radiology or pathology reports (Aronson et al, 2007;Crammer et al, 2007;Farkas and Szarvas, 2008;Goldstein et al, 2007;Matykiewicz et al, 2006;Oleynik et al, 2017;Rizzo et al, 2015;Suominen et al, 2008;Zhang, 2008), discharge summaries (Delamarre et al, 1995;Dinwoodie and Howell, 1973;Franz et al, 2000;Friedman et al, 2004;Kevers and Medori, 2010;Kukafka et al, 2006;Larkey and Croft, 1995;Li et al, 2011;Lussier et al, 2000,0;Medori and Fairon, 2010), death certificates (Koopman et al, 2015,1) and entire medical records (Kavuluru et al, 2015;Lita et al, 2008;Morris et al, 2000;Pakhomov et al, 2006;Ruch et al, 2008), with variable structure and level of curation. Moreover, the majority of studies has been based on English texts, with the exception of particular studies in French (Kevers and Medori, 2010;Medori and Fairon, 2010;Pereira et al, 2006;Ruch et al, 2008), Spanish (Pérez et al, 2015), Italian …”

Section: Review Of Studiesmentioning

confidence: 99%

“…Moreover, the majority of studies has been based on English texts, with the exception of particular studies in French (Kevers and Medori, 2010;Medori and Fairon, 2010;Pereira et al, 2006;Ruch et al, 2008), Spanish (Pérez et al, 2015), Italian (Chiaravalloti et al, 2014;Rizzo et al, 2015) or German (Franz et al, 2000), while information extraction from Portuguese medical texts is still emmerging (Ferreira, 2011;Rijo et al, 2014). The scope of clinical conditions comprised in each study also varied greatly, ranging from limited sets of respiratory (Farkas and Szarvas, 2008), cerebrovascular (Li et al, 2011) or coronarography exams (Delamarre et al, 1995) to heterogeneous episodes (Kevers and Medori, 2010). Such variable scope has also been reflected on the range of codes considered -one (principal diagnosis) (Avillach et al, 2008), five (Lita et al, 2008), six (Li et al, 2011), twenty (Yan et al, 2010) or fifty (Xu et al, 2007) codes, with only one study considering a significantly larger number of codes (more than 1,400 codes) (Medori and Fairon, 2010).…”

Section: Review Of Studiesmentioning

confidence: 99%

See 1 more Smart Citation

Can structured EHR data support clinical coding? A data mining approach

et al. 2020

View full text Add to dashboard Cite

Structured data formats are gaining momentum in electronic health record systems and can be leveraged for decision support and research. Nevertheless, such structured data formats have not been explored for clinical coding, which is an essential process requiring significant manual workload in health organizations. This article explores the extent to which fully structured clinical data can support the assignment of clinical codes to inpatient episodes, through the design and application of a methodology that tackles high dimensionality issues, addresses the multi-label nature of coding and optimizes model parameters. The methodology encompasses transforming database entries to define a feature set and build a data matrix representation, and testing combinations of filter feature selection methods with machine learning models to predict code assignment. The methodology is tested with a real hospital dataset, with results showing varying predictive power across codes but demonstrating the potential of leveraging structuring data to reduce workload and increase efficiency in clinical coding.

show abstract

Section: Review Of Studiesmentioning

confidence: 99%

Section: Review Of Studiesmentioning

confidence: 99%

Can structured EHR data support clinical coding? A data mining approach

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Current automated clinical coding approaches for patient discharge files and radiology reports can be divided into handcrafted, 8,9 machine learning, and hybrid approaches, 10,11 with handcrafted and hybrid approaches being the most successful. 12 A literature review conducted by Stanfill et al 13 concluded that, while some systems show excellent results, most of them are used in controlled settings, often using normalized data and keeping a limited scope (eg, radiology reports).…”

Section: Introductionmentioning

confidence: 99%

Data integration of structured and unstructured sources for assigning clinical codes to patient stays

Scheurwegs

Luyckx

Luyten

et al. 2015

Journal of the American Medical Informatics Association

View full text Add to dashboard Cite

show abstract

“…Unless coding is done by the discharging physician, there is a certain backlog (of days or weeks, and sometimes months) between patient discharge and coding. Although semi-automated ICD coding systems have been proposed [188][189][190][191][192][193] …”

Section: Independent Variables Excluded a Priorimentioning

confidence: 99%

Design and evaluation of analytical tools for emergency department management based on machine learning techniques

Enaliev¹

View full text Add to dashboard Cite

The Spanish National Healthcare System (NHS) is mostly publicly funded and provided. It is considered highly cost-efficient according to international studies based on World Health Organization (WHO) data. However, the contention of healthcare costs increases while maintaining adequate levels of quality of care, is still a largely unsolved problem. In recent years, Emergency Departments (EDs) of specialized care hospitals have been subjected to budget restrictions, increased visits and increased clinical complexity of these visits. These circumstances require new approaches to ED management, which could benefit from decision support tools.In this Ph.D. thesis, we propose machine learning solutions for two problems common to most EDs of specialized care hospitals: ED census forecasting and real-time prediction of probabilities of inpatient admission for all triaged patients in the ED. These solutions could be used as decision support systems. Data for the development of these solutions were The first topic of this Ph.D. thesis is the development of models for ED census forecasting (i.e. prediction of the number of patients present at the ED at a given time). One of the uses of ED census forecasting is nursing personnel allocation, based on national and international recommendations. We chose an 8-hour granularity for our forecasts since many resources (such as nursing personnel) in the ED are organized in 8-hour shifts. Our aim was to generate forecasts for two dependent variables: average ED census levels and maximum ED census levels. Maximum ED census forecasts within 8-hour shifts could be used for nursing personnel allocation, while average ED census forecasts within 8-hour shifts could be used for the other needs (such as allocation of administrative personnel).We used a generalized regression approach to time series forecasting with several machine learning algorithms: M5P, Alternating Model Trees (AMT) and Support Vector Regression (SVR). We compared these to a series of benchmarks: usual nursing staffing levels (and usual resource allocation policies), stratified average (averages stratified by the three 8-10 hour shifts of a day), linear regression and Seasonal Autoregressive Integrated Moving Average (SARIMA) models. Forecasts were generated for both dependent variables: average ED census levels and maximum ED census levels. Four forecast horizons were tested: 1 week, 2 weeks, 4 weeks and 8 weeks. Underestimation risks, overestimation risks and approximations to monetary costs of resource allocations policies were defined for both average and maximum ED census forecasts. Maximum ED census forecasts were transformed into nursing personnel levels, and underestimation and overestimation risks for maximum ED census forecasts were transformed into understaffing and overstaffing risks. A custom training and evaluation scheme was used, with increasingly larger train sets and fixed-length test sets. The same scheme but with fixed-length train sets of 1 year and fixed-length test sets was also used. The ...

show abstract

Symbolic Classification Methods for Patient Discharge Summaries Encoding into ICD

Cited by 3 publications

References 4 publications

Can structured EHR data support clinical coding? A data mining approach

Can structured EHR data support clinical coding? A data mining approach

Data integration of structured and unstructured sources for assigning clinical codes to patient stays

Design and evaluation of analytical tools for emergency department management based on machine learning techniques

Contact Info

Product

Resources

About