[Coding in general practice-Will the ICD-11 be a step forward?]

Developing and testing a framework for coding general practitioners' free-text diagnoses in electronic medical records - a reliability study for generating training data in natural language processing

BACKGROUND

Diagnoses entered by general practitioners into electronic medical records have great potential for research and practice, but unfortunately, diagnoses are often in uncoded format, making them of little use. Natural language processing (NLP) could assist in coding free-text diagnoses, but NLP models require local training data to unlock their potential. The aim of this study was to develop a framework of research-relevant diagnostic codes, to test the framework using free-text diagnoses from a Swiss primary care database and to generate training data for NLP modelling.

METHODS

The framework of diagnostic codes was developed based on input from local stakeholders and consideration of epidemiological data. After pre-testing, the framework contained 105 diagnostic codes, which were then applied by two raters who independently coded randomly drawn lines of free text (LoFT) from diagnosis lists extracted from the electronic medical records of 3000 patients of 27 general practitioners. Coding frequency and mean occurrence rates (n and %) and inter-rater reliability (IRR) of coding were calculated using Cohen's kappa (Κ).

RESULTS

The sample consisted of 26,980 LoFT and in 56.3% no code could be assigned because it was not a specific diagnosis. The most common diagnostic codes were, 'dorsopathies' (3.9%, a code covering all types of back problems, including non-specific lower back pain, scoliosis, and others) and 'other diseases of the circulatory system' (3.1%). Raters were in almost perfect agreement (Κ ≥ 0.81) for 69 of the 105 diagnostic codes, and 28 codes showed a substantial agreement (K between 0.61 and 0.80). Both high coding frequency and almost perfect agreement were found in 37 codes, including codes that are particularly difficult to identify from components of the electronic medical record, such as musculoskeletal conditions, cancer or tobacco use.

CONCLUSION

The coding framework was characterised by a subset of very frequent and highly reliable diagnostic codes, which will be the most valuable targets for training NLP models for automated disease classification based on free-text diagnoses from Swiss general practice.

ICD-10-Coding of Medically Unexplained Physical Symptoms and Somatoform Disorders-A Survey With German GPs

Background: General practitioners (GPs) are reluctant to use codes that correspond to somatization syndromes. Aim: To quantify GPs' views on coding of medically unexplained physical symptoms (MUPS), somatoform disorders, and associated factors. Design and Setting: Survey with German GPs. Methods: We developed six survey items [response options "does not apply at all (1)"-"does fully apply (6)"], invited a random sample of 12.004 GPs to participate in the self-administered cross-sectional survey and analysed data using descriptive statistics and logistic regression analyses. Results: Response rate was 15.2% with N = 1,731 valid responses (54.3% female). Participants considered themselves familiar with ICD-10 criteria for somatoform disorders (M = 4.52; SD =.036) and considered adequate coding as essential prerequisite for treatment (M = 5.02; SD = 1.21). All other item means were close to the scale mean: preference for symptom or functional codes (M = 3.40; SD = 1.21), consideration of the possibility of stigmatisation (M = 3.30; SD = 1.35) and other disadvantages (M = 3.28; SD = 1.30) and coding only if psychotherapy is intended (M = 3.39; SD = 1.46). Exposure, guideline knowledge, and experience were most strongly associated with GPs' self-reported coding behaviour. Conclusions: Subjective exposure, guideline knowledge, and experience as a GP, but no sociodemographic variable being associated with GPs' subjective coding behaviour could indicate that GPs offer a relatively homogeneous approach to coding and handling of MUPS and somatoform disorders. Strengthening guideline knowledge and implementation, and practise with simulated patients could increase the subjective competence to cope with the challenge that patients with MUPS and somatoform disorders present.

A problem-oriented systems approach to primary care system development: development and initial testing of the problem-oriented primary care system development record

BACKGROUND

There is significant global policy interest related to enabling a data-driven approach for evidence-based primary care system development. This paper describes the development and initial testing of a prototype tool (the Problem-Oriented Primary Care System Development Record, or PCSDR) that enables a data-driven and contextualized approach to primary care system development.

METHODS

The PCSDR is an electronic record that enables the systematic input, classification, structuring, storage, processing and analysis of different types of data related to the structure, function and performance of primary care systems over time. Data inputted into the PCSDR was coded using the WHO's PHC-IMPACT framework and classification system. The PCSDR's functionalities were tested by using a case study of primary care system development in Tajikistan.

RESULTS

Tajikistan's case study demonstrated that the PCSDR is a potentially effective and conceptually-sound tool for the input, classification, structuring and storage of different data types from myriad sources. The PCSDR is therefore a basic data entry and data management system that enables query and analytics functions for health services research and evidence-based primary care system development functions.

CONCLUSIONS

The PCSDR is a data system that enables a contextualized approach to evidence-based primary care system development. It represents a coherent and effective synthesis of the fields of primary care system development and performance assessment. The PCSDR enables analysts to leverage primary care performance assessment frameworks for a broad range of functions related to health systems analysis, improvement and the development of learning health systems.