Improving the Utility of Tobacco-Related Problem List Entries Using Natural Language Processing.

We present findings on using natural language processing to classify tobacco-related entries from problem lists found within patient's electronic health records. Problem lists describe health-related issues recorded during a patient's medical visit; these problems are typically followed up upon during subsequent visits and are updated for relevance or accuracy. The mechanics of problem lists vary across different electronic health record systems. In general, they either manifest as pre-generated generic problems that may be selected from a master list or as text boxes where a healthcare professional may enter free text describing the problem. Using commonly-available natural language processing tools, we classified tobacco-related problems into three classes: active-user, former-user, and non-user; we further demonstrate that rule-based post-processing may significantly increase precision in identifying these classes (+32%, +22%, +35% respectively). We used these classes to generate tobacco time-spans that reconstruct a patient's tobacco-use history and better support secondary data analysis. We bundle this as an open-source toolkit with flow visualizations indicating how patient tobacco-related behavior changes longitudinally, which can also capture and visualize contradicting information such as smokers being flagged as having never smoked.

Level of accuracy of diagnoses recorded in discharge summaries: A cohort study in three respiratory wards.

RATIONALE: One of the key functions of the discharge summary is to convey accurate diagnostic description of patients. Inaccurate or missing diagnoses may result in a false clinical picture, inappropriate management, poor quality of care, and a higher risk of re-admission. While several studies have investigated the presence or absence of diagnoses within discharge summaries, there are very few published studies assessing the accuracy of these diagnoses. The aim of this study was to measure the accuracy of diagnoses recorded in sample summaries, and to determine if it was correlated with the type of diagnoses (eg, "respiratory" diagnoses), the number of diagnoses, or the length of patient stay. METHODS: A prospective cohort study was conducted in three respiratory wards in a large UK NHS Teaching Hospital. We determined the reference list of diagnoses (the closest to the true state of the patient based on consultant knowledge, patient records, and laboratory investigations) for comparison with the diagnoses recorded in a discharge summary. To enable objective comparison, all patient diagnoses were encoded using a standardized terminology (ICD-10). Inaccuracy of the primary diagnosis alone and all diagnoses in discharge summaries was measured and then correlated with type of diseases, number of diagnoses, and length of patient stay. RESULTS: A total of 107 of 110 consecutive discharge summaries were analysed. The mean inaccuracy rate per discharge summary was 55% [95% CI 52 to 58%]. Primary diagnoses were wrong, inaccurate, missing, or mis-recorded as a secondary diagnosis in half the summaries. The inaccuracy rate was correlated with the type of disease but not with number of diagnoses nor length of patient stay. CONCLUSION: Our study showed that diagnoses were not accurately recorded in discharge summaries, highlighting the need to measure and improve discharge summary quality.

PROBLEM-ORIENTED MEDICAL RECORD AS A CHALLENGE FOR NARRATOLOGICAL ANALYSIS.

The paper examines the narrative arrangement of the problem-oriented medical record (POMR) as an effective method of registering and assessing clinical data. The aim of the research is to examine the types of narrators and focalization, as well as the hierarchy and interaction of narrative levels in the analyzed discourse. The research has demonstrated the presence of several types of narrators within the analyzed discourse: (1) the omniscient hetero-extradiegetic narrator with transient internal focalization (the third-person narration, represented by the physician) and (2) homo-intradiegetic narration (patient's first-person narration) in the "Subjective Observation" section; (3) the "estranged" heterodiegetic narrator with external focalization (the "Objective Observation" part); (4) the "uncertain" type of narrator (the "Assessment" part); (5) and the imperative mode of narration (the "Plan" section). Each section of POMR is characterized by a specific type of narration, and each of them aims to "intertwine" the events, scattered in time and space, into one coherent narrative to ensure the effective communication between physicians and successful treatment of patients. It is highly important for future physicians to develop narrative competence and master the basic mechanisms of producing an effective POMR, in order to be able to accurately document the encounters with patients, elicit the relevant details from case histories, and select the appropriate strategy of treatment. Therefore, in the process of training future doctors, the analysis of the basic mechanisms of writing POMRs should be an integral part of the curricula in English for Specific Purposes at universities.

[The expert characteristic of the forensic medical documentation for the purpose of investigations of the injuries to the maxillofacial region]. / Ékspertnaia kharakteristika sudebno-meditsinskoi dokumentatsii pri issledovanii povrezhdenii cheliustno-litsevoi oblasti.

The injuries to the maxillofacial region (MFR) are among the most frequently occurring problems encountered if the forensic medical practice. The objective of the present study was the analysis of the quality of the medical record documentation of the victims of the injuries to the maxillofacial region for obtaining the information necessary for forensic medical experts to make the well-founded conclusions. We undertook the in-depth analysis of random samples from the materials stored in the archive of living subjects at the Saint-Petersburg Bureau of forensic medical expertise for the period from 2010 to 2014. The results of a total of 438 forensic medical examinations were available for the analysis. The study has demonstrated the generally low forensic medical value of the expert conclusions that frequently fail to conform to the requirements of the departmental instructions on the description of MFR injuries. In all the cases, neurologists and radiologists were counselled. The results of analysis of the drawbacks of forensic medical examinations give evidence that they originate first and foremost from subjective circumstances which opens up the promising prospects for the improvement of expertise quality based on the enhancement of the professional responsibility of the forensic medical experts.

Illness script development in pre-clinical education through case-based clinical reasoning training.

OBJECTIVES: To assess illness script richness and maturity in preclinical students after they attended a specifically structured instructional format, i.e., a case based clinical reasoning (CBCR) course. METHODS: In a within-subject experimental design, medical students who had finished the CBCR course participated in an illness script experiment. In the first session, richness and maturity of students' illness scripts for diseases discussed during the CBCR course were compared to illness script richness and maturity for similar diseases not included in the course. In the second session, diagnostic performance was tested, to test for differences between CBCR cases and non-CBCR cases. Scores on the CBCR course exam were related to both experimental outcomes. RESULTS: Thirty-two medical students participated. Illness script richness for CBCR diseases was almost 20% higher than for non-CBCR diseases, on average 14.47 (SD=3.25) versus 12.14 (SD=2.80), respectively (p<0.001). In addition, students provided more information on Enabling Conditions and less on Fault-related aspects of the disease. Diagnostic performance was better for the diseases discussed in the CBCR course, mean score 1.63 (SD=0.32) versus 1.15 (SD=0.29) for non-CBCR diseases (p<0.001). A significant correlation of exam results with recognition of CBCR cases was found (r=0.571, p<0.001), but not with illness script richness (r=-0.006, p=NS). CONCLUSIONS: The CBCR-course fosters early development of clinical reasoning skills by increasing the illness script richness and diagnostic performance of pre-clinical students. However, these results are disease-specific and therefore we cannot conclude that students develop a more general clinical reasoning ability.

Determinants of a successful problem list to support the implementation of the problem-oriented medical record according to recent literature.

BACKGROUND: A problem-oriented approach is one of the possibilities to organize a medical record. The problem-oriented medical record (POMR) - a structured organization of patient information per presented medical problem- was introduced at the end of the sixties by Dr. Lawrence Weed to aid dealing with the multiplicity of patient problems. The problem list as a precondition is the centerpiece of the problem-oriented medical record (POMR) also called problem-oriented record (POR). Prior to the digital era, paper records presented a flat list of medical problems to the healthcare professional without the features that are possible with current technology. In modern EHRs a POMR based on a structured problem list can be used for clinical decision support, registries, order management, population health, and potentially other innovative functionality in the future, thereby providing a new incentive to the implementation and use of the POMR. METHODS: On both 12 May 2014 and 1 June 2015 a systematic literature search was conducted. From the retrieved articles statements regarding the POMR and related to successful or non-successful implementation, were categorized. Generic determinants were extracted from these statements. RESULTS: In this research 38 articles were included. The literature analysis led to 12 generic determinants: clinical practice/reasoning, complete and accurate problem list, data structure/content, efficiency, functionality, interoperability, multi-disciplinary, overview of patient information, quality of care, system support, training of staff, and usability. CONCLUSIONS: Two main subjects can be distinguished in the determinants: the system that the problem list and POMR is integrated in and the organization using that system. The combination of the two requires a sociotechnical approach and both are equally important for successful implementation of a POMR. All the determinants have to be taken into account, but the weight given to each of the determinants depends on the organizationusing the problem list or POMR.

Evaluation of the delirium early monitoring system (DEMS).

BACKGROUND: Despite awareness of the negative health and financial outcomes of delirium, systems to routinely assess and manage the condition are absent in clinical practice. We report the development and pilot evaluation of a Delirium Early Monitoring System (DEMS), designed to be completed by non-medical staff to influence clinical processes within inpatient settings. Two versions of the DEMS are described based on a modified Confusion Assessment Method (DEMS-CAM) and Delirium Observation Screening Scale (DEMS-DOSS). METHODS: Both versions of DEMS were piloted on a 20-bedded Psychogeriatric ward over 6 weeks. Training was administered to ward staff on the use of each version of the DEMS and data were collected via electronic medical records and completed assessment sheets. The primary outcome was patterns of DEMS use and the secondary outcome was the initiation of delirium management protocols. Data regarding the use of the DEMS DOSS and DEMS CAMS were analyzed using χ 2 tests. RESULTS: Completion rates for the DEMS CAM and DEMS DOSS were 79% and 68%, respectively. Non-medical staff were significantly more likely to use the DEMS-CAM as part of daily practice as opposed to the DEMS-DOSS (p<0.001). However, there was no difference between the use of the DEMS-CAM and DEMS-DOSS in triggering related actions such as documentation of assessment scores in patients' medical records and implementation of delirium management protocols. CONCLUSIONS: This real world evaluation revealed that non-medical staff were able to incorporate delirium monitoring into their practice, on the majority of occasions, as part of their daily working routine. Further research is necessary to determine if the routine use of the DEMS can lead to improved understandings and practice of non-medical staff regarding delirium detection.

Assessment of hospital inpatient discharge summaries, written for general practitioners, from a department of medicine for the elderly service in a large teaching hospital.

BACKGROUND: The discharge document summarising an acute inpatient stay in hospital is often the only means of communication between secondary and primary care. This is especially important in the elderly population who have multiple morbidities and are often on many medications. AIMS: This study aimed to assess if information important to general practitioners is being included in inpatient hospital discharge summaries for patients of the medicine for the elderly service in a large teaching hospital. METHODS: After a thorough literature review, a "gold standard" letter was defined as having included a discharge diagnosis, medications on discharge and follow-up plans. Forty computerised discharge summaries were retrospectively assessed for inclusion of these parameters. The study group consisted of the first eight sequentially discharged patients under the care of each of the five consultants during a 1-month period (1 September 2011-30 September 2011). RESULTS: A discharge diagnosis was included in 37 of the 40 summaries (92.5 %), medications on discharge were included in 39 summaries (97.5 %) and follow-up was recorded in 35 summaries (87.5 %). CONCLUSIONS: This study showed that the information assessed was available in the vast majority of discharge summaries for patients admitted acutely under the care of this medicine for the elderly service. Improvements can be made, including documentation of follow-up plans.

Medical Record Documentation in a Learning Disability In-patient Unit.

INTRODUCTION: Consistency in clinical structure and content is an important aspect of clinical practice. The rising demands on healthcare systems and associated costs require a much more efficient and transparent means of recording and accessing reliable clinical information in order to manage and deliver good quality care to patients. AIMS: The audit has been completed with an aim to highlight the local standards set for medical record documentation and to assess if the outlined standards are being met in a learning disability in-patient psychiatric setting, the Coppice. METHODOLOGY: Criteria based on GMC Good Medical practice guidelines (2013), RCPsych Good Psychiatric Practice (2009) and Records Management Policy. CONCLUSIONS: Good practice was maintained for most parameters. Mild inaccuracies were noted with date of birth/ward name, timing and signatures. RECOMMENDATIONS: This was presented locally and measures put in place to address the gaps. A re-audit should be performed within a year in order to complete the audit cycle and to ensure that the recommendations and action plan have been followed through.

Pro Re Nata (PRN) prescription in an Inpatient Low Secure Learning Disability Unit.

INTRODUCTION: Pro Re Nata (PRN) prescribing in psychiatry is a common and valuable facility to be used in acutely distressed patients. It is open to misuse and PRN prescribing may be unnecessary/inappropriate. AIM: The aim of the audit is to ensure safe and effective prescription of PRN medication. AUDIT STANDARDS: The standards were set in congruence with the guidance from the local trust policy. METHODOLOGY: All of the inpatient records at Wood Lea clinic were studied over a 2 month period. CONCLUSIONS: Most of the standards against which the clinical notes were assessed gave evidence of good medical practice. Patient demographics demonstrated a 100% record of the NHS number but the patient's name and ward fell short. RECOMMENDATIONS: This was presented locally and measures put in place to address gaps. Re-audit should be performed within a year in order to complete the audit cycle and to ensure that recommendations/action plan have been followed through.

Problem list completeness in electronic health records: A multi-site study and assessment of success factors.

OBJECTIVE: To assess problem list completeness using an objective measure across a range of sites, and to identify success factors for problem list completeness. METHODS: We conducted a retrospective analysis of electronic health record data and interviews at ten healthcare organizations within the United States, United Kingdom, and Argentina who use a variety of electronic health record systems: four self-developed and six commercial. At each site, we assessed the proportion of patients who have diabetes recorded on their problem list out of all patients with a hemoglobin A1c elevation>=7.0%, which is diagnostic of diabetes. We then conducted interviews with informatics leaders at the four highest performing sites to determine factors associated with success. Finally, we surveyed all the sites about common practices implemented at the top performing sites to determine whether there was an association between problem list management practices and problem list completeness. RESULTS: Problem list completeness across the ten sites ranged from 60.2% to 99.4%, with a mean of 78.2%. Financial incentives, problem-oriented charting, gap reporting, shared responsibility, links to billing codes, and organizational culture were identified as success factors at the four hospitals with problem list completeness at or near 90.0%. DISCUSSION: Incomplete problem lists represent a global data integrity problem that could compromise quality of care and put patients at risk. There was a wide range of problem list completeness across the healthcare facilities. Nevertheless, some facilities have achieved high levels of problem list completeness, and it is important to better understand the factors that contribute to success to improve patient safety. CONCLUSION: Problem list completeness varies substantially across healthcare facilities. In our review of EHR systems at ten healthcare facilities, we identified six success factors which may be useful for healthcare organizations seeking to improve the quality of their problem list documentation: financial incentives, problem oriented charting, gap reporting, shared responsibility, links to billing codes, and organizational culture.

["Do-not-rescuscitate"--Results of introducing a standardized order sheet on documentation quality]. / "Do not rescuscitate"--Auswirkungen der Einführung eines standardisierten Formulars auf Therapiebegrenzungen in der klinischen Praxis.

INTRODUCTION: DNR orders have been used internationally since the 1970 s. Despite the growing importance of patient preference in German law, there is little data on DNR orders in Germany Methods: The prevalence of DNR orders was assessed on the hospital wards. Healthcare were asked about their experiences and opinions in two polls. The charts of all deceased patients were reviewed for DNR notes for 9 month before and after introduction of the new DNR order sheets. RESULTS: The prevalence of DNR orders remained constant at 8% of patients. In 12,4% of these DNR status was not known by the nursing staff. After introduction of the order sheet, the percentage of orders with comprehensive documentation increased from 5.9 to 65.4% of orders (p < 0.001). In the polls the healthcare workers saw a significant improvement in information content of DNR orders after introduction of the new order sheets. The chart review documented an improved documentation of DNR status going up from 28.8 to 40.8% of deceased patients (p < 0.001). The fraction of comprehensive orders increased from 32% to 84.6% (p < 0.001). CONCLUSION: INTRODUCTION of DNR order sheets in a German hospital lead to objective improvements in the quality of end-of life care documentation while the prevalence of DNR orders remained unchanged.

In pursuit of excellence: an integrated care pathway for C1 inhibitor deficiency.

There are estimated to be approximately 1500 people in the United Kingdom with C1 inhibitor (C1INH) deficiency. At BartsHealth National Health Service (NHS) Trust we manage 133 patients with this condition and we believe that this represents one of the largest cohorts in the United Kingdom. C1INH deficiency may be hereditary or acquired. It is characterized by unpredictable episodic swellings, which may affect any part of the body, but are potentially fatal if they involve the larynx and cause significant morbidity if they involve the viscera. The last few years have seen a revolution in the treatment options that are available for C1 inhibitor deficiency. However, this occurs at a time when there are increased spending restraints in the NHS and the commissioning structure is being overhauled. Integrated care pathways (ICP) are a tool for disseminating best practice, for facilitating clinical audit, enabling multi-disciplinary working and for reducing health-care costs. Here we present an ICP for managing C1 inhibitor deficiency.

The readiness of SNOMED problem list concepts for meaningful use of electronic health records.

OBJECTIVE: By 2015, SNOMED CT (SCT) will become the USA's standard for encoding diagnoses and problem lists in electronic health records (EHRs). To facilitate this effort, the National Library of Medicine has published the "SCT Clinical Observations Recording and Encoding" and the "Veterans Health Administration and Kaiser Permanente" problem lists (collectively, the "PL"). The PL is studied in regard to its readiness to support meaningful use of EHRs. In particular, we wish to determine if inconsistencies appearing in SCT, in general, occur as frequently in the PL, and whether further quality-assurance (QA) efforts on the PL are required. METHODS AND MATERIALS: A study is conducted where two random samples of SCT concepts are compared. The first consists of concepts strictly from the PL and the second contains general SCT concepts distributed proportionally to the PL's in terms of their hierarchies. Each sample is analyzed for its percentage of primitive concepts and for frequency of modeling errors of various severity levels as quality measures. A simple structural indicator, namely, the number of parents, is suggested to locate high likelihood inconsistencies in hierarchical relationships. The effectiveness of this indicator is evaluated. RESULTS: PL concepts are found to be slightly better than other concepts in the respective SCT hierarchies with regards to the quality measure of the percentage of primitive concepts and the frequency of modeling errors. There were 58% primitive concepts in the PL sample versus 62% in the control sample. The structural indicator of number of parents is shown to be statistically significant in its ability to identify concepts having a higher likelihood of inconsistencies in their hierarchical relationships. The absolute number of errors in the group of concepts having 1-3 parents was shown to be significantly lower than that for concepts with 4-6 parents and those with 7 or more parents based on Chi-squared analyses. CONCLUSION: PL concepts suffer from the same issues as general SCT concepts, although to a slightly lesser extent, and do require further QA efforts to promote meaningful use of EHRs. To support such efforts, a structural indicator is shown to effectively ferret out potentially problematic concepts where those QA efforts should be focused.

Quality of discharge summaries prepared by first year internal medicine residents.

BACKGROUND: Patients are particularly susceptible to medical error during transitions from inpatient to outpatient care. We evaluated discharge summaries produced by incoming postgraduate year 1 (PGY-1) internal medicine residents for their completeness, accuracy, and relevance to family physicians. METHODS: Consecutive discharge summaries prepared by PGY-1 residents for patients discharged from internal medicine wards were retrospectively evaluated by two independent reviewers for presence and accuracy of essential domains described by the Joint Commission for Hospital Accreditation. Family physicians rated the relevance of a separate sample of discharge summaries on domains that family physicians deemed important in previous studies. RESULTS: Ninety discharge summaries were assessed for completeness and accuracy. Most items were completely reported with a given item missing in 5% of summaries or fewer, with the exception of the reason for medication changes, which was missing in 15.9% of summaries. Discharge medication lists, medication changes, and the reason for medication changes--when present--were inaccurate in 35.7%, 29.5%, and 37.7% of summaries, respectively. Twenty-one family physicians reviewed 68 discharge summaries. Communication of follow-up plans for further investigations was the most frequently identified area for improvement with 27.7% of summaries rated as insufficient. CONCLUSIONS: This study found that medication details were frequently omitted or inaccurate, and that family physicians identified lack of clarity about follow-up plans regarding further investigations and visits to other consultants as the areas requiring the most improvement. Our findings will aid in the development of educational interventions for residents.

Simple prescribing errors and allergy documentation in medical hospital admissions in Australia and New Zealand.

This study aimed to quantify and compare the prevalence of simple prescribing errors made by clinicians in the first 24 hours of a general medical patient's hospital admission. Four public or private acute care hospitals across Australia and New Zealand each audited 200 patients' drug charts. Patient demographics, pharmacist review and pre-defined prescribing errors were recorded. At least one simple error was present on the medication charts of 672/715 patients, with a linear relationship between the number of medications prescribed and the number of errors (r = 0.571, p < 0.001). The four sites differed significantly in the prevalence of different types of simple prescribing errors. Pharmacists were more likely to review patients aged > or = 75 years (39.9% vs 26.0%; p < 0.001) and those with more than 10 drug prescriptions (39.4% vs 25.7%; p < 0.001). Patients reviewed by a pharmacist were less likely to have inadequate documentation of allergies (13.5% vs 29.4%, p < 0.001). Simple prescribing errors are common, although their nature differs from site to site. Clinical pharmacists target patients with the most complex health situations, and their involvement leads to improved documentation.

[High-quality hospital discharge summaries - general practitioners expectations]. / Welche Anforderungen stellt der Hausarzt an einen guten Spitalaustrittsbericht?

Hospital discharge summaries ensure treatment continuity after hospital discharge. In Switzerland discharge letters are a celebrated custom and a tool for training young colleagues. The primary purpose is to guarantee high-quality care of patients treated by hospital staff and general practitioners. From the perspective of the patient's general practitioner discharge summaries should convey current and accurate medically important patient data to the physician responsible for follow-up care. In the era of highly developed electronic data transfer and introduction of diagnose related groups (DRGs), it will be necessary to transmit hospital discharge information selectively to different target groups. Nevertheless data protection and medical secret must be complied with.