DEPLOYR: a technical framework for deploying custom real-time machine learning models into the electronic medical record.

OBJECTIVE: Heatlhcare institutions are establishing frameworks to govern and promote the implementation of accurate, actionable, and reliable machine learning models that integrate with clinical workflow. Such governance frameworks require an accompanying technical framework to deploy models in a resource efficient, safe and high-quality manner. Here we present DEPLOYR, a technical framework for enabling real-time deployment and monitoring of researcher-created models into a widely used electronic medical record system. MATERIALS AND METHODS: We discuss core functionality and design decisions, including mechanisms to trigger inference based on actions within electronic medical record software, modules that collect real-time data to make inferences, mechanisms that close-the-loop by displaying inferences back to end-users within their workflow, monitoring modules that track performance of deployed models over time, silent deployment capabilities, and mechanisms to prospectively evaluate a deployed model's impact. RESULTS: We demonstrate the use of DEPLOYR by silently deploying and prospectively evaluating 12 machine learning models trained using electronic medical record data that predict laboratory diagnostic results, triggered by clinician button-clicks in Stanford Health Care's electronic medical record. DISCUSSION: Our study highlights the need and feasibility for such silent deployment, because prospectively measured performance varies from retrospective estimates. When possible, we recommend using prospectively estimated performance measures during silent trials to make final go decisions for model deployment. CONCLUSION: Machine learning applications in healthcare are extensively researched, but successful translations to the bedside are rare. By describing DEPLOYR, we aim to inform machine learning deployment best practices and help bridge the model implementation gap.

Duodenal gastrointestinal stromal tumor: A case report.

Introduction: Gastrointestinal tumor (GIT) is an uncommon gastrointestinal tumor most commonly arising in the stomach. Duodenum is an uncommon site accounting for only about 3-5% of cases. Case presentation: In this case report, we present a case of high-risk duodenal GIST and review its management strategies. Discussion: An abdominal mass and gastrointestinal (GI) bleeding are its usual presentation, however it may be lost among the long list of differentials of an abdominal mass and GI bleeding, if a high index of suspicion is not maintained. Surgery, with or without tyrosine kinase inhibitors like imatinib mesylate, has been the cornerstone in management of GIST. Conclusion: This case underlined the importance of duodenal GIST as a cause of GI bleed and abdominal mass as well as shone light upon historical developments, current updates and managements of GISTs.

Neurobrucellosis presenting with the features of meningoencephalitis: A case report from Nepal.

Introduction and importance: Brucellosis or Malta fever is a zoonotic disease caused by the Brucella species. Patients with neurobrucellosis may present with features of meningoencephalitis. Thus, a high degree of suspicion is required for the diagnosis in the endemic region. Case presentation: A 13-year old female with a history of exposure to domestic animals presented with the features of meningoencephalitis (intermittent fever with chills and rigor and generalized tonic-clonic seizure). Clinical findings and investigations: Examination revealed drowsy and lethargic patient with bilateral edema up to mid-shin. Neck rigidity was present. Lab findings include leukocytosis with neutrophilic and erythrocyte sedimentation rate (25 mm/hr). CECT of the brain revealed vasogenic edema. Routine CSF examination was insignificant for common bacterial, viral, fungal or tubercular etiology. CSF ELISA confirmed the presence of Brucella antibody. Conclusion: When patients present with undulant fever, lethargy, seizure, or other features of meningitis/encephalitis, the diagnosis of neurobrucellosis must be considered after common pathological causes are ruled out.

Tapia's syndrome in post-operative patient following orotracheal intubation.

Introduction: Tapia's syndrome is a rare condition that manifest due to unilateral extracranial nerve extension of cranial nerve 10 and 12 which occurred as a rare complication of Orotracheal Intubation in patient undergoing Laparoscopic appendectomy. Case presentation: A 30 year old male, a known case of normal variant Right bundle branch block and Gilbert syndrome underwent orotracheal intubation prior to general anesthesia for emergency laparoscopic appendectomy. Postoperatively while assessing the patient there was deviation of tongue on left side. Clinical findings and investigations: On examination of throat, atrophic and deviated uvula toward the right side was found. While protruding his tongue, tongue was deviated towards left side.Neurological examination revealed sluggish Gag Reflex. Brain Ct was done, which showed normal scan. Interventions and outcome: Tablet Prednisolone and logopedic therapy in combination helped in early recovery; which is almost 8 weeks. Patient was completely recovered in 2 month with gradual improvement of phonation, tongue tone and mobility. Relevance and impact: The intent of this report is to show how important it is for anesthesia providers and surgeons to understand Tapia's syndrome, its causes, and the fact that it can occur despite seemingly normal airway care and neck posture. We believe that by raising awareness of this uncommon issue, practitioners will be able to early identify this complication.

Sputum Smear Non-conversion at the End of Intensive Phase of Tuberculosis Treatment at a Tertiary Center: A Descriptive Cross-sectional study.

INTRODUCTION: Sputum non-conversion is smear positive tuberculosis despite anti-tubercular therapy. Various factors may lead to sputum non-conversion including resistance to anti-tubercular drugs, age, gender, disease severity, non-compliance, drugs unavailability etc. Little is known and studied about the contribution of these individual factors. Our study sought to determine the prevalence of sputum smear non-conversion in patients at the end of intensive phase of tuberculosis treatment visiting a tertiary-level institution in Nepal. METHODS: A descriptive cross-sectional study was conducted among recorded data of patients undergoing sputum Acid Fast Bacilli staining at the end of intensive phase at National Tuberculosis Control Center from April 2018 to April 2020. The study was approved by Nepal Health Research Council (Registration no: 76012020 P). The convenient sampling method was adopted. The data were analyzed using Microsoft Excel. Point estimate at 95% Confidence Interval was calculated along with frequency and proportion for binary data. RESULTS: Our study found that out of 830 samples that were tested by Acid Fast Bacilli stain at the end of intensive phase, 40 (4.82%) (3.37-6.28 at 95% Confidence Interval) were sputum smear non-converters. The mean age of sputum non-converters was 41.25±15.543 years. CONCLUSIONS: The study shows that a significant proportion of patients remain acid-fast stain positive despite the treatment. However, the proportion is low compared to other similar studies around the globe. This study provides program managers with evidence to support the development of more tailored tuberculosis care and need to conduct more intensive studies about various factors that may lead to non-conversion.