Assessing perceived effectiveness of career development efforts led by the women in American Medical Informatics Association Initiative.

OBJECTIVE: We sought to ascertain perceived factors affecting women's career development efforts in the American Medical Informatics Association (AMIA) and to provide recommendations for improvements. MATERIALS AND METHODS: Data were collected using a 27-item survey administered via the AMIA newsletter and other social channels. Survey questions comprised 3 demographics, 15 Likert-scale, and 9 open-ended items. Likert-scale responses were summarized across respondent ages, career stages, and career domains, and open-ended responses were thematically analyzed. RESULTS: We received survey responses from 109 AMIA women members. Our findings demonstrate that AMIA had made strides in promoting career development, and the most effective AMIA efforts included social events (83%), panel discussions (80%), and scientific sessions (79%). However, despite these efforts, women members perceived that gender-specific challenges persisted within AMIA, and recognized the need for increased networking opportunities (96%), raising awareness of gender-specific challenges (95%), and encouraging gender proportional representation in leadership (92%). DISCUSSION: International and national biomedical informatics professional communities have put forth efforts to address gender-specific issues in career development. Yet, our study identified that some of these, including the deep-rooted gender power hierarchy and bias, are still perceived as profound in AMIA. CONCLUSION: Even though existing career development efforts for women are highly effective, important perceived gender-specific career development issues require further attention and investigation to improve existing AMIA activities.

Hospital Readmission and Social Risk Factors Identified from Physician Notes.

OBJECTIVE: To evaluate the prevalence of seven social factors using physician notes as compared to claims and structured electronic health records (EHRs) data and the resulting association with 30-day readmissions. STUDY SETTING: A multihospital academic health system in southeastern Massachusetts. STUDY DESIGN: An observational study of 49,319 patients with cardiovascular disease admitted from January 1, 2011, to December 31, 2013, using multivariable logistic regression to adjust for patient characteristics. DATA COLLECTION/EXTRACTION METHODS: All-payer claims, EHR data, and physician notes extracted from a centralized clinical registry. PRINCIPAL FINDINGS: All seven social characteristics were identified at the highest rates in physician notes. For example, we identified 14,872 patient admissions with poor social support in physician notes, increasing the prevalence from 0.4 percent using ICD-9 codes and structured EHR data to 16.0 percent. Compared to an 18.6 percent baseline readmission rate, risk-adjusted analysis showed higher readmission risk for patients with housing instability (readmission rate 24.5 percent; p < .001), depression (20.6 percent; p < .001), drug abuse (20.2 percent; p = .01), and poor social support (20.0 percent; p = .01). CONCLUSIONS: The seven social risk factors studied are substantially more prevalent than represented in administrative data. Automated methods for analyzing physician notes may enable better identification of patients with social needs.

Implementation, evaluation, and recommendations for extension of AHRQ Common Formats to capture patient- and carepartner-generated safety data.

OBJECTIVES: The Common Formats, published by the Agency for Healthcare Research and Quality, represent a standard for safety event reporting used by Patient Safety Organizations (PSOs). We evaluated its ability to capture patient-reported safety events. MATERIALS AND METHODS: We formally evaluated gaps between the Common Formats and a safety concern reporting system for use by patients and their carepartners (ie friends/families) at Brigham and Women's Hospital. RESULTS: Overall, we found large gaps between Common Formats (versions 1.2, 2.0) and our patient/carepartner reporting system, with only 22-30% of the data elements matching. DISCUSSION: We recommend extensions to the Common Formats, including concepts that capture greater detail about the submitter and safety categories relevant to unsafe conditions and near misses that patients and carepartners routinely observe. CONCLUSION: Extensions to the Common Formats could enable more complete safety data sets and greater understanding of safety from key stakeholder perspectives, especially patients, and carepartners.

Modeling Contextual Knowledge for Clinical Decision Support.

In theory, the logic of decision rules should be atomic. In practice, this is not always possible; initially simple logic statements tend to be overloaded with additional conditions restricting the scope of such rules. By doing so, the original logic soon becomes encumbered with contextual knowledge. Contextual knowledge is re-usable on its own and could be modeled separately from the logic of a rule without losing the intended functionality. We model constraints to explicitly define the context where knowledge of decision rules is actionable. We borrowed concepts from Semantic Web, Complex Adaptive Systems, and Contextual Reasoning. The proposed approach provides the means for identifying and modeling contextual knowledge in a simple, sound manner. The methodology presented herein facilitates rule authoring, fosters consistency in rules implementation and maintenance; facilitates developing authoritative knowledge repositories to promote quality, safety and efficacy of healthcare; and paves the road for future work in knowledge discovery.

Identifying Patients with Depression Using Free-text Clinical Documents.

About 1 in 10 adults are reported to exhibit clinical depression and the associated personal, societal, and economic costs are significant. In this study, we applied the MTERMS NLP system and machine learning classification algorithms to identify patients with depression using discharge summaries. Domain experts reviewed both the training and test cases, and classified these cases as depression with a high, intermediate, and low confidence. For depression cases with high confidence, all of the algorithms we tested performed similarly, with MTERMS' knowledge-based decision tree slightly better than the machine learning classifiers, achieving an F-measure of 89.6%. MTERMS also achieved the highest F-measure (70.6%) on intermediate confidence cases. The RIPPER rule learner was the best performing machine learning method, with an F-measure of 70.0%, and a higher precision but lower recall than MTERMS. The proposed NLP-based approach was able to identify a significant portion of the depression cases (about 20%) that were not on the coded diagnosis list.

Modeling decision support rule interactions in a clinical setting.

Traditionally, rule interactions are handled at implementation time through rule task properties that control the order in which rules are executed. By doing so, knowledge about the behavior and interactions of decision rules is not captured at modeling time. We argue that this is important knowledge that should be integrated in the modeling phase. In this project, we build upon current work on a conceptual schema to represent clinical knowledge for decision support in the form of if then rules. This schema currently captures provenance of the clinical content, context where such content is actionable (i.e. constraints) and the logic of the rule itself. For this project, we borrowed concepts from both the Semantic Web (i.e., Ontologies) and Complex Adaptive Systems (CAS), to explore a conceptual approach for modeling rule interactions in an enterprise-wide clinical setting. We expect that a more comprehensive modeling will facilitate knowledge authoring, editing and update; foster consistency in rules implementation and maintenance; and develop authoritative knowledge repositories to promote quality, safety and efficacy of healthcare.

Rapid identification of myocardial infarction risk associated with diabetes medications using electronic medical records.

OBJECTIVE To assess the ability to identify potential association(s) of diabetes medications with myocardial infarction using usual care clinical data obtained from the electronic medical record. RESEARCH DESIGN AND METHODS We defined a retrospective cohort of patients (n = 34,253) treated with a sulfonylurea, metformin, rosiglitazone, or pioglitazone in a single academic health care network. All patients were aged >18 years with at least one prescription for one of the medications between 1 January 2000 and 31 December 2006. The study outcome was acute myocardial infarction requiring hospitalization. We used a cumulative temporal approach to ascertain the calendar date for earliest identifiable risk associated with rosiglitazone compared with that for other therapies. RESULTS Sulfonylurea, metformin, rosiglitazone, or pioglitazone therapy was prescribed for 11,200, 12,490, 1,879, and 806 patients, respectively. A total of 1,343 myocardial infarctions were identified. After adjustment for potential myocardial infarction risk factors, the relative risk for myocardial infarction with rosiglitazone was 1.3 (95% CI 1.1-1.6) compared with sulfonylurea, 2.2 (1.6-3.1) compared with metformin, and 2.2 (1.5-3.4) compared with pioglitazone. Prospective surveillance using these data would have identified increased risk for myocardial infarction with rosiglitazone compared with metformin within 18 months of its introduction with a risk ratio of 2.1 (95% CI 1.2-3.8). CONCLUSIONS Our results are consistent with a relative adverse cardiovascular risk profile for rosiglitazone. Our use of usual care electronic data sources from a large hospital network represents an innovative approach to rapid safety signal detection that may enable more effective postmarketing drug surveillance.

STROBE-based methodology for detection of adverse events across multiple communities.

Partners Healthcare is one of five institutions in conjunction with eHealth Initiative (eHI) and the FDA that is collaborating in a nation-wide effort to develop novel health information technology tools to create an active drug safety surveillance system across the U.S. The STROBE statement serves as the standard for the definition of a structured, systematic, reproducible approach for detecting both the risks and benefits of drug treatments in multiple settings.

The tell-tale heart: population-based surveillance reveals an association of rofecoxib and celecoxib with myocardial infarction.

BACKGROUND: COX-2 selective inhibitors are associated with myocardial infarction (MI). We sought to determine whether population health monitoring would have revealed the effect of COX-2 inhibitors on population-level patterns of MI. METHODOLOGY/PRINCIPAL FINDINGS: We conducted a retrospective study of inpatients at two Boston hospitals, from January 1997 to March 2006. There was a population-level rise in the rate of MI that reached 52.0 MI-related hospitalizations per 100,000 (a two standard deviation exceedence) in January of 2000, eight months after the introduction of rofecoxib and one year after celecoxib. The exceedence vanished within one month of the withdrawal of rofecoxib. Trends in inpatient stay due to MI were tightly coupled to the rise and fall of prescriptions of COX-2 inhibitors, with an 18.5% increase in inpatient stays for MI when both rofecoxib and celecoxib were on the market (P<0.001). For every million prescriptions of rofecoxib and celecoxib, there was a 0.5% increase in MI (95%CI 0.1 to 0.9) explaining 50.3% of the deviance in yearly variation of MI-related hospitalizations. There was a negative association between mean age at MI and volume of prescriptions for celecoxib and rofecoxib (Spearman correlation, -0.67, P<0.05). CONCLUSIONS/SIGNIFICANCE: The strong relationship between prescribing and outcome time series supports a population-level impact of COX-2 inhibitors on MI incidence. Further, mean age at MI appears to have been lowered by use of these medications. Use of a population monitoring approach as an adjunct to pharmacovigilence methods might have helped confirm the suspected association, providing earlier support for the market withdrawal of rofecoxib.

Usefulness of intracranial EEG in the decision process for epilepsy surgery.

BACKGROUND AND PURPOSE: In patients with discordant results, non-localizing EEG, or bitemporal seizure onset, intracranial monitoring is done to confirm the seizure onset. Our aim was to assess the yield of intracranial recordings in patients with different clinical scenarios. METHODS: The records of all patients who underwent prolonged intracranial EEG monitoring (IEM) at the London Health Sciences Centre, University of Western Ontario, Canada, between 1993 and 1999, identified using our EEG patient database in continuous use since December 1972, were reviewed. Patients were analyzed in the following groups according to perceived increasing degrees of uncertainty of epileptic zone localization-group 1: lesion on MRI congruent with focal ictal and interictal scalp EEG, but findings are subtle and of low level of certainty (n=13), group 2: focal MRI, focal ictal and multifocal interictal scalp EEG (n=11), group 3: focal MRI, non-localizing or incongruent scalp EEG (n=73), group 4: normal of multifocal MRI, focal ictal scalp EEG (n=11), group 5: multifocal MRI, non-localizing scalp EEG (n=18), and group 6: normal MRI, multifocal scalp EEG (n=36). RESULTS: One hundred and seventy one patients underwent IEM at the London Health Sciences Centre between 1993 and 1999. All patients had localization-related epilepsy, plus or minus secondary generalization. IEM was helpful overall in 86% of patients, in 69% of group 1, 36% of group 2, 90% of group 3, 81% of group 4, 100 of group 5 and 92% of group 6. CONCLUSIONS: Our study shows that the yield of the IEM was higher in the groups of patients with lack of congruence between the MRI and the scalp EEG. The yield was lower in patients with congruent but subtle or uncertain scalp EEG and MRI findings.

Caregiver burden in Parkinson's disease.

Parkinson's disease (PD) is a neurodegenerative disorder that imposes an important burden upon the patient's caregiver. This study aims at assessing caregiver burden (CB) and analyzing its relationship with sociodemographic, emotional, and functional factors, as well as health-related quality of life (HRQoL). The following measures were applied to 80 patients with PD: the Hospital Anxiety and Depression Scale (HADS); the EuroQoL (for HRQoL); and PD-specific measures (Hoehn and Yahr staging and SCOPA-Motor ADL subscale). Patients' main caregivers completed the HADS, SF-36, EuroQoL, and Zarit CB Inventory (ZCBI). The ZCBI was found to be a valid and reliable measure in the context of PD. There was a significant association between CB and caregivers' HRQoL (r = -0.29 to -0.64). Mental aspects of caregivers' HRQoL and burden were affected by disability and disease severity. The presence of caregivers' depression had a significant negative effect on both CB and HRQoL. The main predictors of CB were caregivers' psychological well-being, patients' mood and clinical aspects of PD (disability and severity), and HRQoL of patients and caregivers. This study underscores the need to consider the impact of PD on caregivers' well-being.

Epilepsy surgery involving the sensory-motor cortex.

Our aim was to assess the outcome with regard to seizures and neurological function in unselected patients undergoing resective surgery involving the perirolandic area, with or without multiple subpial transections (MSTs). All patients who underwent perirolandic cortical resection or MSTs from 1979 to 2003 at the London Health Sciences Centre were identified. Patients were included if they had seizures originating in the perirolandic area, recorded with subdural electrodes, or if they had scalp recorded seizures and a congruent discrete epileptogenic lesion on MRI in the perirolandic area. Most patients had electrocorticography (ECoG) at the time of surgery. Data collected include pre-operative and post-operative neurological deficits, MRI findings, interictal and ictal scalp EEG, interictal and ictal subdural data, ECoG findings, type and extent of surgery, neuropathologic diagnoses, and seizure outcomes. We studied 52 patients (22 females). The average age at the time of surgery was 33 years, and the average post-operative follow-up was 4.2 years. The most frequent aetiologies were neoplastic in 26 patients (50%), vascular in eight (15%), malformations of cortical development in six (12%), Rasmussen's encephalitis in three (6%) and other aetiologies in nine (17%). Surgery involved the pre-central gyrus in 17 patients, pre- and post-central gyrus in 13, the inferior central region in 11, the post-central gyrus in 7, and the pre-central gyrus and mesial frontal area in 2. At last follow-up 16 patients were in Engel class I (31%), 8 (15%) in class II, 14 (27%) in class III and 14 (27%) in class IV. Residual neurological deficits were present in 26 patients (50%), occurred more frequently in patients > or =25 years old (P < 0.05) and were mild in 14 (54%) patients. In univariate analyses, better seizure outcomes (P < 0.05) occurred in patients whose ECoG showed infrequent post-resectional spikes and no spikes distant to the resection margin, and in resections involving the pre-central and inferior rolandic cortex. In unselected patients with intractable perirolandic epilepsy, many of whom have large, complex epileptogenic lesions, various levels of seizure improvement can be achieved in almost 75% through well-planned surgical resections. New, severe post-operative neurological deficits can occur in 23% of these patients and appear to be more frequent in older patients. Whereas scalp EEG provided limited information to guide surgery, findings on interictal ECoG predicted seizure outcome.

Extracting principal diagnosis, co-morbidity and smoking status for asthma research: evaluation of a natural language processing system.

BACKGROUND: The text descriptions in electronic medical records are a rich source of information. We have developed a Health Information Text Extraction (HITEx) tool and used it to extract key findings for a research study on airways disease. METHODS: The principal diagnosis, co-morbidity and smoking status extracted by HITEx from a set of 150 discharge summaries were compared to an expert-generated gold standard. RESULTS: The accuracy of HITEx was 82% for principal diagnosis, 87% for co-morbidity, and 90% for smoking status extraction, when cases labeled "Insufficient Data" by the gold standard were excluded. CONCLUSION: We consider the results promising, given the complexity of the discharge summaries and the extraction tasks.

A suite of natural language processing tools developed for the I2B2 project.

Textual medical records contain a wealth of information that needs to be extracted and / or indexed in order to be analyzed and interpreted by the automated tools. We have developed a collection of natural language processing (NLP) tools to extract various types of information from unstructured medical records. The generic NLP components, when assembled in pipelines and initialized with custom configuration parameters, become a powerful medical data mining instrument. We have successfully extracted such medical concepts as diagnoses, comorbidities, discharge medications, and smoking status from various types of medical records.

Feasibility of an intelligent tutoring system for laboratory medicine.

Laboratory medicine is not adequately addressed in most medical school curricula. A review of the literature was performed to evaluate the feasibility of an intelligent tutoring system to enhance laboratory medicine training. This appraisal suggests that such a system must integrate basic science and clinical training. A system equipped with a clinical knowledgebase, in the form of an expert system, and a pathophysiology knowledgebase, in the form of multiple semantic networks, could provide such integration.

National and regional prevalence of self-reported epilepsy in Canada.

PURPOSE: To assess the point prevalence of self-described epilepsy in the general population nationally, provincially, and in different groups of interest. METHODS: We analyzed data from two national health surveys, the National Population Health Survey (NPHS, N=49,000) and the Community Health Survey (CHS, N=130,882). Both surveys captured sociodemographic information, as well as age, sex, education, ethnicity, household income, and labor force status of participants. Epilepsy was ascertained with only one question in both surveys. "Do you have epilepsy diagnosed by a health professional?" (NPHS) and "Do you have epilepsy?" (CHS). Prevalences were age-adjusted by using national standard populations at the time of each survey. Exact 95% confidence intervals were obtained. RESULTS: In the NPHS, 241 of 49,026 subjects described themselves as having been diagnosed with epilepsy, yielding a weighted point prevalence of 5.2 per 1,000 [95% confidence interval (CI), 4.9-5.4]. In the CHS, 835 of 130,822 subjects described themselves as having epilepsy, yielding a weighted point prevalence of 5.6 per 1,000 (95% CI, 5.1-6.0). Trends in differences in prevalence among some Canadian provinces were observed. Prevalence was statistically significantly higher in groups with the lowest educational level, lowest income, and in those unemployed in the previous year. Prevalence also was higher in nonimmigrants than in immigrants. CONCLUSIONS: The overall and group-specific results are in keeping with those obtained in other developed countries by using different ascertainment methods. We discuss methodologic aspects related to the ascertainment of epilepsy in both surveys, and to the validity and implications of our findings.

Description and status update on GELLO: a proposed standardized object-oriented expression language for clinical decision support.

A major obstacle to sharing computable clinical knowledge is the lack of a common language for specifying expressions and criteria. Such a language could be used to specify decision criteria, formulae, and constraints on data and action. Al-though the Arden Syntax addresses this problem for clinical rules, its generalization to HL7's object-oriented data model is limited. The GELLO Expression language is an object-oriented language used for expressing logical conditions and computations in the GLIF3 (GuideLine Interchange Format, v. 3) guideline modeling language. It has been further developed under the auspices of the HL7 Clinical Decision Support Technical Committee, as a proposed HL7 standard., GELLO is based on the Object Constraint Language (OCL), because it is vendor-independent, object-oriented, and side-effect-free. GELLO expects an object-oriented data model. Although choice of model is arbitrary, standardization is facilitated by ensuring that the data model is compatible with the HL7 Reference Information Model (RIM).

Design of a standards-based external rules engine for decision support in a variety of application contexts: report of a feasibility study at Partners HealthCare System.

This project explored functional requirements for an institution-wide method, at Partners HealthCare, for interpreting clinical knowledge for decision support. Such knowledge is currently incorporated in a variety of clinical applications, yet the methods of representation and of execution vary and the ability to author/edit the rules by human experts is limited. We expanded on a 2002 "Knowledge Inventory" at Partners to evaluate feasibility of designing a single representation approach entailing: (a) exploration of specific needs of different applications, in terms of kinds of response required (synchronous/asynchronous, time criticality, etc.), context (e.g., implied patient, time frame, or episode), and kinds of actions to be triggered; (b) kind of representation of knowledge and feasibility of casting knowledge in the form of if em leader then statements; and (c) data and knowledge resources used (implied data model, and particular knowledge sources and terminology sources). The result of analysis was to design an architecture to accomplish this goal. We also did preliminary analysis of requirements for authoring for such a representation, and for implementation.

GELLO: an object-oriented query and expression language for clinical decision support.

GELLO is a purpose-specific, object-oriented (OO) query and expression language. GELLO is the result of a concerted effort of the Decision Systems Group (DSG) working with the HL7 Clinical Decision Support Technical Committee (CDSTC) to provide the HL7 community with a common format for data encoding and manipulation. GELLO will soon be submitted for ballot to the HL7 CDSTC for consideration as a standard.