Automating Clinical Trial Matches Via Natural Language Processing of Synthetic Electronic Health Records and Clinical Trial Eligibility Criteria.

Clinical trials are critical to many medical advances; however, recruiting patients remains a persistent obstacle. Automated clinical trial matching could expedite recruitment across all trial phases. We detail our initial efforts towards automating the matching process by linking realistic synthetic electronic health records to clinical trial eligibility criteria using natural language processing methods. We also demonstrate how the Sørensen-Dice Index can be adapted to quantify match quality between a patient and a clinical trial.

Predicting 5-year dementia conversion in veterans with mild cognitive impairment.

INTRODUCTION: Identifying mild cognitive impairment (MCI) patients at risk for dementia could facilitate early interventions. Using electronic health records (EHRs), we developed a model to predict MCI to all-cause dementia (ACD) conversion at 5 years. METHODS: Cox proportional hazards model was used to identify predictors of ACD conversion from EHR data in veterans with MCI. Model performance (area under the receiver operating characteristic curve [AUC] and Brier score) was evaluated on a held-out data subset. RESULTS: Of 59,782 MCI patients, 15,420 (25.8%) converted to ACD. The model had good discriminative performance (AUC 0.73 [95% confidence interval (CI) 0.72-0.74]), and calibration (Brier score 0.18 [95% CI 0.17-0.18]). Age, stroke, cerebrovascular disease, myocardial infarction, hypertension, and diabetes were risk factors, while body mass index, alcohol abuse, and sleep apnea were protective factors. DISCUSSION: EHR-based prediction model had good performance in identifying 5-year MCI to ACD conversion and has potential to assist triaging of at-risk patients. Highlights: Of 59,782 veterans with mild cognitive impairment (MCI), 15,420 (25.8%) converted to all-cause dementia within 5 years.Electronic health record prediction models demonstrated good performance (area under the receiver operating characteristic curve 0.73; Brier 0.18).Age and vascular-related morbidities were predictors of dementia conversion.Synthetic data was comparable to real data in modeling MCI to dementia conversion. Key Points: An electronic health record-based model using demographic and co-morbidity data had good performance in identifying veterans who convert from mild cognitive impairment (MCI) to all-cause dementia (ACD) within 5 years.Increased age, stroke, cerebrovascular disease, myocardial infarction, hypertension, and diabetes were risk factors for 5-year conversion from MCI to ACD.High body mass index, alcohol abuse, and sleep apnea were protective factors for 5-year conversion from MCI to ACD.Models using synthetic data, analogs of real patient data that retain the distribution, density, and covariance between variables of real patient data but are not attributable to any specific patient, performed just as well as models using real patient data. This could have significant implications in facilitating widely distributed computing of health-care data with minimized patient privacy concern that could accelerate scientific discoveries.

Jet stream related iatrogenic retinal breaks during vitreo-retinal surgery.

PURPOSE: To evaluate the causes of jet stream injury (JSI)-related iatrogenic retinal breaks (IRBs) during vitreoretinal surgery (VRS). METHODS: The precise surgical environment, which includes the indication and type of surgical procedure, retina status, details of instrumentation and fluidic parameters, and characteristics of the jet responsible for the IRB, was noted from case records. The nature of IRB and its healing and impact on anatomical and visual outcomes were analyzed. RESULTS: Five eyes of five patients with complete documentation of both the JSI and the IRB were included. Two cases were operated for macular hole, and one each for vitreous hemorrhage, retinal detachment, and endophthalmitis. One case had infusion-fluid-related JSI, while four developed it because of injection of surgical adjuncts (drugs, PFCL, and dye). JSI developed in two cases when the vitreous cavity was filled with fluid, while it was air-filled in three cases. In four cases, the fluid migrated into subretinal space, necessitating further maneuvers following which the breaks healed, but were directly responsible for vision loss in two cases. CONCLUSION: JSI related IRBs are rare but may be directly responsible for vision loss if they impact the macula. The balance between jet stream velocity, its distance from the retinal surface, the intervening media (vitreous cavity), and retinal health play an important role. It can occur because of both infusion as well as injection jets. Precautions must be taken in cases vulnerable to complications with suggested modifications in the surgical technique.

Retinal neovascularization in a patient with chronic central serous chorioretinopathy.

A 45-year-old male presented with diminution of vision in both eyes since the last 2 years. The best-corrected visual acuity was 20/200 in his right eye and 20/600 in left eye. BE fundi had changes of chronic CSCR with PED and NSD in the RE and subretinal fibrosis in the left eye. Both eyes had peripheral pigmentary changes. Multimodal imaging showed peripheral avascular retina in both eyes with neovascularization at disc in the right eye which promptly resolved with a single injection of anti-VEGF. Retinal neovascularization is an unusual finding in the setting of CSCR and has not been reported in the literature.

Primary tuberculous sternal osteomyelitis: a clinical rarity.

Primary tuberculous sternal osteomyelitis is a rare condition, presenting as painful swelling and discharging sinuses over the chest wall. Diagnosis is based on radiological findings and histological examination of debrided infected tissues, with specific cultures for mycobacteria. Two cases were successfully treated by surgical debridement and reconstruction using pectoralis major muscle flaps, followed by antituberculous therapy.

The application of the unified modeling language in object-oriented analysis of healthcare information systems.

This paper concerns itself with the beneficial effects of the Unified Modeling Language (UML), a nonproprietary object modeling standard, in specifying, visualizing, constructing, documenting, and communicating the model of a healthcare information system from the user's perspective. The author outlines the process of object-oriented analysis (OOA) using the UML and illustrates this with healthcare examples to demonstrate the practicality of application of the UML by healthcare personnel to real-world information system problems. The UML will accelerate advanced uses of object-orientation such as reuse technology, resulting in significantly higher software productivity. The UML is also applicable in the context of a component paradigm that promises to enhance the capabilities of healthcare information systems and simplify their management and maintenance.