ChatGPT's adherence to otolaryngology clinical practice guidelines.

OBJECTIVES: Large language models, including ChatGPT, has the potential to transform the way we approach medical knowledge, yet accuracy in clinical topics is critical. Here we assessed ChatGPT's performance in adhering to the American Academy of Otolaryngology-Head and Neck Surgery guidelines. METHODS: We presented ChatGPT with 24 clinical otolaryngology questions based on the guidelines of the American Academy of Otolaryngology. This was done three times (N = 72) to test the model's consistency. Two otolaryngologists evaluated the responses for accuracy and relevance to the guidelines. Cohen's Kappa was used to measure evaluator agreement, and Cronbach's alpha assessed the consistency of ChatGPT's responses. RESULTS: The study revealed mixed results; 59.7% (43/72) of ChatGPT's responses were highly accurate, while only 2.8% (2/72) directly contradicted the guidelines. The model showed 100% accuracy in Head and Neck, but lower accuracy in Rhinology and Otology/Neurotology (66%), Laryngology (50%), and Pediatrics (8%). The model's responses were consistent in 17/24 (70.8%), with a Cronbach's alpha value of 0.87, indicating a reasonable consistency across tests. CONCLUSIONS: Using a guideline-based set of structured questions, ChatGPT demonstrates consistency but variable accuracy in otolaryngology. Its lower performance in some areas, especially Pediatrics, suggests that further rigorous evaluation is needed before considering real-world clinical use.

Deep learning in voice analysis for diagnosing vocal cord pathologies: a systematic review.

OBJECTIVES: With smartphones and wearable devices becoming ubiquitous, they offer an opportunity for large-scale voice sampling. This systematic review explores the application of deep learning models for the automated analysis of voice samples to detect vocal cord pathologies. METHODS: We conducted a systematic literature review following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) reporting guidelines. We searched MEDLINE and Embase databases for original publications on deep learning applications for diagnosing vocal cord pathologies between 2002 and 2022. Risk of bias was assessed using Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2). RESULTS: Out of the 14 studies that met the inclusion criteria, data from a total of 3037 patients were analyzed. All studies were retrospective. Deep learning applications targeted Reinke's edema, nodules, polyps, cysts, unilateral cord paralysis, and vocal fold cancer detection. Most pathologies had detection accuracy above 90%. Thirteen studies (93%) exhibited a high risk of bias and concerns about applicability. CONCLUSIONS: Technology holds promise for enhancing the screening and diagnosis of vocal cord pathologies. While current research is limited, the presented studies offer proof of concept for developing larger-scale solutions.

Predictors and Adverse Outcomes of Acute Kidney Injury in Hospitalized Renal Transplant Recipients.

Data about in-hospital AKI in RTRs is lacking. We conducted a retrospective study of 292 RTRs, with 807 hospital admissions, to reveal predictors and outcomes of AKI during admission. In-hospital AKI developed in 149 patients (51%). AKI in a previous admission was associated with a more than twofold increased risk of AKI in subsequent admissions (OR 2.13, p < 0.001). Other major significant predictors for in-hospital AKI included an infection as the major admission diagnosis (OR 2.93, p = 0.015), a medical history of hypertension (OR 1.91, p = 0.027), minimum systolic blood pressure (OR 0.98, p = 0.002), maximum tacrolimus trough level (OR 1.08, p = 0.005), hemoglobin level (OR 0.9, p = 0.016) and albumin level (OR 0.51, p = 0.025) during admission. Compared to admissions with no AKI, admissions with AKI were associated with longer length of stay (median time of 3.83 vs. 7.01 days, p < 0.001). In-hospital AKI was associated with higher rates of mortality during admission, almost doubled odds for rehospitalization within 90 days from discharge and increased the risk of overall mortality in multivariable mixed effect models. In-hospital AKI is common and is associated with poor short- and long-term outcomes. Strategies to prevent AKI during admission in RTRs should be implemented to reduce re-admission rates and improve patient survival.

Machine learning for optimal test admission in the presence of resource constraints.

Developing rapid tools for early detection of viral infection is crucial for pandemic containment. This is particularly crucial when testing resources are constrained and/or there are significant delays until the test results are available - as was quite common in the early days of Covid-19 pandemic. We show how predictive analytics methods using machine learning algorithms can be combined with optimal pre-test screening mechanisms, greatly increasing test efficiency (i.e., rate of true positives identified per test), as well as to allow doctors to initiate treatment before the test results are available. Our optimal test admission policies account for imperfect accuracy of both the medical test and the model prediction mechanism. We derive the accuracy required for the optimized admission policies to be effective. We also show how our policies can be extended to re-testing high-risk patients, as well as combined with pool testing approaches. We illustrate our techniques by applying them to a large data reported by the Israeli Ministry of Health for RT-PCR tests from March to September 2020. Our results demonstrate that in the context of the Covid-19 pandemic a pre-test probability screening tool with conventional RT-PCR testing could have potentially increased efficiency by several times, compared to random admission control.

A Five-Decade Text Mining Analysis of Cochlear Implant Research: Where We Started and Where We Are Heading.

Background and Objectives: Since its invention in the 1970s, the cochlear implant (CI) has been substantially developed. We aimed to assess the trends in the published literature to characterize CI. Materials and Methods: We queried PubMed for all CI-related entries published during 1970-2022. The following data were extracted: year of publication, publishing journal, title, keywords, and abstract text. Search terms belonged to the patient's age group, etiology for hearing loss, indications for CI, and surgical methodological advancement. Annual trends of publications were plotted. The slopes of publication trends were calculated by fitting regression lines to the yearly number of publications. Results: Overall, 19,428 CIs articles were identified. Pediatric-related CI was the most dominant sub-population among the age groups, with the highest rate and slope during the years (slope 5.2 ± 0.3, p < 0.001), while elderly-related CIs had significantly fewer publications. Entries concerning hearing preservation showed the sharpest rise among the methods, from no entries in 1980 to 46 entries in 2021 (slope 1.7 ± 0.2, p < 0.001). Entries concerning robotic surgery emerged in 2000, with a sharp increase in recent years (slope 0.5 ± 0.1, p < 0.001). Drug-eluting electrodes and CI under local-anesthesia have been reported only in the past five years, with a gradual rise. Conclusions: Publications regarding CI among pediatrics outnumbered all other indications, supporting the rising, pivotal role of CI in the rehabilitation of children with sensorineural hearing loss. Hearing-preservation publications have recently rapidly risen, identified as the primary trend of the current era, followed by a sharp rise of robotic surgery that is evolving and could define the next revolution.

Obesity as a mortality risk factor in the medical ward: a case control study.

BACKGROUND: Research regarding the association between severe obesity and in-hospital mortality is inconsistent. We evaluated the impact of body mass index (BMI) levels on mortality in the medical wards. The analysis was performed separately before and during the COVID-19 pandemic. METHODS: We retrospectively retrieved data of adult patients admitted to the medical wards at the Mount Sinai Health System in New York City. The study was conducted between January 1, 2011, to March 23, 2021. Patients were divided into two sub-cohorts: pre-COVID-19 and during-COVID-19. Patients were then clustered into groups based on BMI ranges. A multivariate logistic regression analysis compared the mortality rate among the BMI groups, before and during the pandemic. RESULTS: Overall, 179,288 patients were admitted to the medical wards and had a recorded BMI measurement. 149,098 were admitted before the COVID-19 pandemic and 30,190 during the pandemic. Pre-pandemic, multivariate analysis showed a "J curve" between BMI and mortality. Severe obesity (BMI > 40) had an aOR of 0.8 (95% CI:0.7-1.0, p = 0.018) compared to the normal BMI group. In contrast, during the pandemic, the analysis showed a "U curve" between BMI and mortality. Severe obesity had an aOR of 1.7 (95% CI:1.3-2.4, p < 0.001) compared to the normal BMI group. CONCLUSIONS: Medical ward patients with severe obesity have a lower risk for mortality compared to patients with normal BMI. However, this does not apply during COVID-19, where obesity was a leading risk factor for mortality in the medical wards. It is important for the internal medicine physician to understand the intricacies of the association between obesity and medical ward mortality.

Alerting on mortality among patients discharged from the emergency department: a machine learning model.

OBJECTIVES: Physicians continuously make tough decisions when discharging patients. Alerting on poor outcomes may help in this decision. This study evaluates a machine learning model for predicting 30-day mortality in emergency department (ED) discharged patients. METHODS: We retrospectively analysed visits of adult patients discharged from a single ED (1/2014-12/2018). Data included demographics, evaluation and treatment in the ED, and discharge diagnosis. The data comprised of both structured and free-text fields. A gradient boosting model was trained to predict mortality within 30 days of release from the ED. The model was trained on data from the years 2014-2017 and validated on data from the year 2018. In order to reduce potential end-of-life bias, a subgroup analysis was performed for non-oncological patients. RESULTS: Overall, 363 635 ED visits of discharged patients were analysed. The 30-day mortality rate was 0.8%. A majority of the mortality cases (65.3%) had a known oncological disease. The model yielded an area under the curve (AUC) of 0.97 (95% CI 0.96 to 0.97) for predicting 30-day mortality. For a sensitivity of 84% (95% CI 0.81 to 0.86), this model had a false positive rate of 1:20. For patients without a known malignancy, the model yielded an AUC of 0.94 (95% CI 0.92 to 0.95). CONCLUSIONS: Although not frequent, patients may die following ED discharge. Machine learning-based tools may help ED physicians identify patients at risk. An optimised decision for hospitalisation or palliative management may improve patient care and system resource allocation.

COVID-19 lockdown impact on quality of treatment and outcomes of STEMI and stroke patients in a large tertiary medical center: an observational study.

BACKGROUND: The coronavirus 2019 (COVID-19) pandemic affected health-care systems worldwide, leading to fewer admissions and raising concerns about the quality of care. The objective of this study was to investigate the early effects of the COVID-19 pandemic on quality of care among stroke and ST-elevation myocardial infarction (STEMI) patients, focusing on clinical outcomes and direct treatment costs. METHOD: This retrospective, observational study was based on the 10-week period that included the first wave of the COVID-19 pandemic in Israel (15 February 2020-30 April 2020). Emergency department admissions for stroke and STEMI were compared with parallel periods in 2017-2019, focusing on demographics, risk and severity scores, and the effect of clinical outcomes on hospitalization costs. RESULTS: The 634 stroke and 186 STEMI cases comprised 16% and 19% fewer admissions, respectively, compared to 2019. No significant changes were detected in demographics, most disease management parameters, readmission and mortality outcomes. The mean door-to-balloon time increased insignificantly by 33%, lowering the health quality indicator (HQI) for treatment in <90 min from 94.7% in 2017-2019 to 83% in 2020 (P = 0.022). Among suspected stroke patients, 97.2% underwent imaging, with 28% longer median time from admission (P = 0.05). Consequently, only 24.3% met the HQI of imaging in <29 min, compared to 45.5% in 2017-2019 (P < 0.01). Increased length of stay and more intensive care unit admissions were the leading causes of 6.5% increased mean cost of STEMI patients' initial hospitalization, which totaled $29 300 in the COVID-19 period (P = 0.008). CONCLUSION: The initial pandemic period caused a decline in HQIs linked to diagnostic and treatment protocols, without changes in outcomes, but with increased hospitalization costs. Medical information and awareness of life-threatening conditions among patients and caregivers should be increased to enable proper diagnosis and management.

A Practical Clinical Score Predicting Respiratory Failure in COVID-19 Patients.

BACKGROUND: The coronavirus disease 2019 (COVID-19) pandemic resulted in repeated surges of patients, sometimes challenging triage protocols and appropriate control of patient flow. Available models, such as the National Early Warning Score (NEWS), have shown significant limitations. Still, they are used by some centers to triage COVID-19 patients due to the lack of better tools. OBJECTIVES: To establish a practical and automated triage tool based on readily available clinical data to rapidly determine a distinction between patients who are prone to respiratory failure. METHODS: The electronic medical records of COVID-19 patients admitted to the Sheba Medical Center March-April 2020 were analyzed. Population data extraction and exploration were conducted using a MDClone (Israel) big data platform. Patients were divided into three groups: non-intubated, intubated within 24 hours, and intubated after 24 hours. The NEWS and our model where applied to all three groups and a best fit prediction model for the prediction of respiratory failure was established. RESULTS: The cohort included 385 patients, 42 of whom were eventually intubated, 15 within 24 hours or less. The NEWS score was significantly lower for the non-intubated patients compared to the two other groups. Our improved model, which included NEWS elements combined with other clinical data elements, showed significantly better performance. The model's receiver operating characteristic curve had area under curve (AUC) of 0.92 with of sensitivity 0.81, specificity 0.89, and negative predictive value (NPV) 98.4% compared to AUC of 0.63 with NEWS. As patients deteriorate and require further support with supplemental O2, the need for re-triage emerges. Our model was able to identify those patients on supplementary O2 prone to respiratory failure with an AUC of 0.86 sensitivity 0.95, and specificity 0.7 NPV 98.9%, whereas NEWS had an AUC of 0.76. For both groups positive predictive value was approximately 35. CONCLUSIONS: Our model, based on readily available and simple clinical parameters, showed an excellent ability to predict negative outcome among patients with COVID-19 and therefore might be used as an initial screening tool for patient triage in emergency departments and other COVID-19 specific areas of the hospital.

Sick Euthyroid Syndrome on Presentation of Patients With COVID-19: A Potential Marker for Disease Severity.

OBJECTIVE: Precise risk stratification and triage of coronavirus disease 2019 (COVID-19) patients are essential in the setting of an overwhelming pandemic burden. Clinical observation has shown a somewhat high prevalence of sick euthyroid syndrome among patients with COVID-19. This study aimed to evaluate the predictive value of free triiodothyronine (FT3) at the clinical presentation of COVID-19 for disease severity and death. METHODS: This retrospective cohort study was based on electronic medical records. The study was conducted at Sheba Medical Centre, a tertiary hospital where several acute and chronic wards have been dedicated to the treatment of patients with COVID-19. The primary outcome measure was death during hospitalization; secondary outcomes included hospitalization in intensive care, mechanical ventilation, and length of hospitalization. RESULTS: Of a total of 577 polymerase chain reaction-positive patients with COVID-19 hospitalized between February 27 and July 30, 2020, 90 had at least 1 measurement of thyroid-stimulating hormone, free thyroxine, and FT3 within 3 days of presentation. After applying strict exclusion criteria, 54 patients were included in the study. Patients in the lowest tertile of FT3 had significantly higher rates of mortality (40%, 5.9%, and 5.9%, P = .008), mechanical ventilation (45%, 29.4%, and 0.0%; P = .007) and intensive care unit admission (55%, 29.4%, and 5.9%, P = .006). In multivariate analyses adjusted for age, Charlson comorbidity index, creatinine, albumin, and white blood cell count. FT3 remained a significant independent predictor of death. CONCLUSION: FT3 levels can serve as a prognostic tool for disease severity in the early presentation of COVID-19.

Normal-range emergency department serum phosphorus levels and all-cause mortality.

PURPOSE OF THE STUDY: Hypophosphataemia and hyperphosphataemia are frequently encountered in hospitalised patients and are associated with significant clinical consequences. However, the prognostic value of normal-range phosphorus levels on all-cause mortality and hospitalisations is not well established. Therefore, we examined the association between normal-range phosphorus levels, all-cause mortality and hospitalisations in patients presenting to the emergency department of a tertiary medical centre in Israel. STUDY DESIGN: A retrospective analysis of patients presenting to the Chaim Sheba Medical Center emergency department between 2012 and 2018. The cohort was divided into quartiles based on emergency department phosphorus levels: 'very-low-normal' (p ≥ 2 mg/dL and p ≤ 2.49 mg/dL), 'low-normal' (p ≥ 2.5 mg/dL and p ≤ 2.99 mg/dL), 'high-normal' (p≥  3 mg/dL and p≤3.49 mg/dL) and 'very-high-normal' (p ≥  3.5 mg/dL and p ≤ 4 mg/dL). We analysed the association between emergency department phosphorus levels, hospitalisation rate and 30-day and 90-day all-cause mortality. RESULTS: Our final analysis included 223 854 patients with normal-range phosphorus levels. Patients with 'very-low-normal' phosphorus levels had the highest mortality rate. Compared with patients with 'high-normal' phosphorus levels, patients with 'very-low-normal' levels had increased 30-day all-cause mortality (OR 1.3, 95% CI 1.1 to 1.4, p<0.001), and increased 90-day all-cause mortality (OR 1.2, 95% CI 1.1 to 1.3, p<0.001). Lower serum phosphorus levels were also associated with a higher hospitalisation rate, both for the internal medicine and general surgery wards (p<0.001). CONCLUSIONS: Lower phosphorus levels, within the normal range, are associated with higher 30-day and 90-day all-cause mortality and hospitalisation rate.

Patient and clinician experience with a rapidly implemented large-scale video consultation program during COVID-19.

BACKGROUND: The coronavirus disease 2019 (COVID-19) pandemic has forced health-care providers to find creative ways to allow continuity of care in times of lockdown. Telemedicine enables provision of care when in-person visits are not possible. Sheba Medical Center made a rapid transition of outpatient clinics to video consultations (VC) during the first wave of COVID-19 in Israel. OBJECTIVE: Results of a survey of patient and clinician user experience with VC are reported. METHODS: Satisfaction surveys were sent by text messages to patients, clinicians who practice VC (users) and clinicians who do not practice VC (non-users). Questions referred to general satisfaction, ease of use, technical issues and medical and communication quality. Questions and scales were based on surveys used regularly in outpatient clinics of Sheba Medical Center. RESULTS: More than 1200 clinicians (physicians, psychologists, nurses, social workers, dietitians, speech therapists, genetic consultants and others) provided VC during the study period. Five hundred and forty patients, 162 clinicians who were users and 50 clinicians who were non-users completed the survey. High level of satisfaction was reported by 89.8% of patients and 37.7% of clinician users. Technical problems were experienced by 21% of patients and 80% of clinician users. Almost 70% of patients but only 23.5% of clinicians found the platform very simple to use. Over 90% of patients were very satisfied with clinician's courtesy, expressed a high sense of trust, thought that clinician's explanations and recommendations were clear and estimated that the clinician understood their problems and 86.5% of them would recommend VC to family and friends. Eighty-seven percent of clinician users recognize the benefit of VC for patients during the COVID-19 pandemic but only 68% supported continuation of the service after the pandemic. CONCLUSION: Our study reports high levels of patient satisfaction from outpatient clinics VC during the COVID-19 pandemic. Lower levels of clinician satisfaction can mostly be attributed to technical and administrative challenges related to the newly implemented telemedicine platform. Our findings support the continued future use of VC as a means of providing patient-centered care. Future steps need to be taken to continuously improve the clinical and administrative application of telemedicine services.

[ASSIMILATING PROMS DURING AND POST-HOSPITALIZATION OF COPD PATIENTS DUE TO DISEASE EXACERBATION MAY IMPROVE THEIR CLINICAL FOLLOW-UP - A CLINICAL, PROSPECTIVE, OBSERVATIONAL STUDY].

BACKGROUND: Chronic obstructive pulmonary disease (COPD) exacerbations necessitating hospitalization are known to have a negative impact on post-discharge clinical outcomes. In the present study, we evaluated the potential benefits in applying Patient-Reported-Outcome-Measures (PROMS) in order to better these patients' post-hospitalization prognostication. METHODS: This was a prospective, observational study. RESULTS: Ninety-nine COPD patients were recruited (aged 9.7±73 years, 61.6% males). All patients filled two separate PROMS (EXACT & PROMIS GLOBAL 10) while 69 of them also filled a second battery of PROMS within 3 months post discharge. The median follow-up time was 14.3 months. The patients' characteristics found to have a statistically significant association with increased risk for 90-days re-hospitalization were: permanent use of oxygen at home [55.2% vs. 32.8%, p=0.045]; significant change in the dyspnea score of the EXACT [54(40-71) vs. 38(11-60), OR=1.115; 95CI 1.006-1.236, p=0.038] and significant change in the cough and sputum, score section of the EXACT [0 (-19-25) vs. -14 (-31-0), OR=1.095; 95CI 1.011-1.187, p=0.027]. Patients' characteristics found to have a statistically significant association with increased risk for 90-days mortality were: age [83±8.43 vs. 72.46±9.53, p=0.047], diagnosis of pneumonia during index hospitalization [60% vs. 14.9%, P=0.034] and low ALT blood activity [10IU (5.5-13.8) vs. 17IU (13-22.8), p=0.016]. Significant change in the EXACT score was associated with increased risk of long-term mortality [-3 (-8.8-9.5) vs. -9 (-21.5-0), OR=1.047; CI95% 1.005-1.091, p=0.03]. CONCLUSIONS: Assimilating PROMS, during and post-hospitalization due to COPD exacerbation could improve our prediction for negative clinical outcomes, both short- and long-term. This may offer better therapeutic interventions in the future. We recommend usage of the EXACT as part of the post-discharge follow-up of COPD patients.

A Gradient Boosting Machine Learning Model for Predicting Early Mortality in the Emergency Department Triage: Devising a Nine-Point Triage Score.

BACKGROUND: Emergency departments (ED) are becoming increasingly overwhelmed, increasing poor outcomes. Triage scores aim to optimize the waiting time and prioritize the resource usage. Artificial intelligence (AI) algorithms offer advantages for creating predictive clinical applications. OBJECTIVE: Evaluate a state-of-the-art machine learning model for predicting mortality at the triage level and, by validating this automatic tool, improve the categorization of patients in the ED. DESIGN: An institutional review board (IRB) approval was granted for this retrospective study. Information of consecutive adult patients (ages 18-100) admitted at the emergency department (ED) of one hospital were retrieved (January 1, 2012-December 31, 2018). Features included the following: demographics, admission date, arrival mode, referral code, chief complaint, previous ED visits, previous hospitalizations, comorbidities, home medications, vital signs, and Emergency Severity Index (ESI). The following outcomes were evaluated: early mortality (up to 2 days post ED registration) and short-term mortality (2-30 days post ED registration). A gradient boosting model was trained on data from years 2012-2017 and examined on data from the final year (2018). The area under the curve (AUC) for mortality prediction was used as an outcome metric. Single-variable analysis was conducted to develop a nine-point triage score for early mortality. KEY RESULTS: Overall, 799,522 ED visits were available for analysis. The early and short-term mortality rates were 0.6% and 2.5%, respectively. Models trained on the full set of features yielded an AUC of 0.962 for early mortality and 0.923 for short-term mortality. A model that utilized the nine features with the highest single-variable AUC scores (age, arrival mode, chief complaint, five primary vital signs, and ESI) yielded an AUC of 0.962 for early mortality. CONCLUSION: The gradient boosting model shows high predictive ability for screening patients at risk of early mortality utilizing data available at the time of triage in the ED.

Comparison of deep learning models for natural language processing-based classification of non-English head CT reports.

PURPOSE: Natural language processing (NLP) can be used for automatic flagging of radiology reports. We assessed deep learning models for classifying non-English head CT reports. METHODS: We retrospectively collected head CT reports (2011-2018). Reports were signed in Hebrew. Emergency department (ED) reports of adult patients from January to February for each year (2013-2018) were manually labeled. All other reports were used to pre-train an embedding layer. We explored two use cases: (1) general labeling use case, in which reports were labeled as normal vs. pathological; (2) specific labeling use case, in which reports were labeled as with and without intra-cranial hemorrhage. We tested long short-term memory (LSTM) and LSTM-attention (LSTM-ATN) networks for classifying reports. We also evaluated the improvement of adding Word2Vec word embedding. Deep learning models were compared with a bag-of-words (BOW) model. RESULTS: We retrieved 176,988 head CT reports for pre-training. We manually labeled 7784 reports as normal (46.3%) or pathological (53.7%), and 7.1% with intra-cranial hemorrhage. For the general labeling, LSTM-ATN-Word2Vec showed the best results (AUC = 0.967 ± 0.006, accuracy 90.8% ± 0.01). For the specific labeling, all methods showed similar accuracies between 95.0 and 95.9%. Both LSTM-ATN-Word2Vec and BOW had the highest AUC (0.970). CONCLUSION: For a general use case, word embedding using a large cohort of non-English head CT reports and ATN improves NLP performance. For a more specific task, BOW and deep learning showed similar results. Models should be explored and tailored to the NLP task.

Promoting head CT exams in the emergency department triage using a machine learning model.

PURPOSE: In this study, we aimed to develop a novel prediction model to identify patients in need of a non-contrast head CT exam during emergency department (ED) triage. METHODS: We collected data of all adult ED visits in our institution for five consecutive years (1/2013-12/2017). Retrieved variables included the following: demographics, mode of arrival to the ED, comorbidities, home medications, structured and unstructured chief complaints, vital signs, pain scale score, emergency severity index, ED wing assignment, documentation of previous ED visits, hospitalizations and CTs, and current visit non-contrast head CT usage. A machine learning gradient boosting model was trained on data from the years 2013-2016 and tested on data from 2017. Area under the curve (AUC) was used as metrics. Single-variable AUCs were also determined. Youden's index evaluated optimal sensitivity and specificity of the models. RESULTS: The final cohort included 595,561 ED visits. Non-contrast head CT usage rate was 11.8%. Each visit was coded into an input vector of 171 variables. Single-variable analysis showed that chief complaint had the best single predictive analysis (AUC = 0.87). The best model showed an AUC of 0.93 (95% CI 0.931-0.936) for predicting non-contrast head CT usage at triage level. The model had a sensitivity of 88.1% and specificity of 85.7% for non-contrast head CT utilization. CONCLUSION: The developed model can identify patients that need to undergo head CT exam already in the ED triage level and by that allow faster diagnosis and treatment.

Patterns of multimorbidity associated with 30-day readmission: a multinational study.

BACKGROUND: Multimorbidity is associated with higher healthcare utilization; however, data exploring its association with readmission are scarce. We aimed to investigate which most important patterns of multimorbidity are associated with 30-day readmission. METHODS: We used a multinational retrospective cohort of 126,828 medical inpatients with multimorbidity defined as ≥2 chronic diseases. The primary and secondary outcomes were 30-day potentially avoidable readmission (PAR) and 30-day all-cause readmission (ACR), respectively. Only chronic diseases were included in the analyses. We presented the OR for readmission according to the number of diseases or body systems involved, and the combinations of diseases categories with the highest OR for readmission. RESULTS: Multimorbidity severity, assessed as number of chronic diseases or body systems involved, was strongly associated with PAR, and to a lesser extend with ACR. The strength of association steadily and linearly increased with each additional disease or body system involved. Patients with four body systems involved or nine diseases already had a more than doubled odds for PAR (OR 2.35, 95%CI 2.15-2.57, and OR 2.25, 95%CI 2.05-2.48, respectively). The combinations of diseases categories that were most strongly associated with PAR and ACR were chronic kidney disease with liver disease or chronic ulcer of skin, and hematological malignancy with esophageal disorders or mood disorders, respectively. CONCLUSIONS: Readmission was associated with the number of chronic diseases or body systems involved and with specific combinations of diseases categories. The number of body systems involved may be a particularly interesting measure of the risk for readmission in multimorbid patients.

Personalized diabetes management recommendations at hospital discharge based on a computerized, pre-hospitalization clinical profile analysis: A prospective, electronic health records-based study.

BACKGROUND: While glycemic control of hospitalized diabetic patients is straightforward, personalization of management at discharge is challenging. Treatment guidelines base recommendations on the clinical profile of patients. We checked the feasibility of implementing discharge recommendations, based on the clinical profile in the patients' electronic health records (EHR). METHODS: A decision-making algorithm was devised according to current guidelines. It was incorporated into the EHR. A prospective follow-up of eligible diabetes patients was done. RESULTS: During 15 months, 835 patients (HbA1c was 6.9% [6.2%-7.8%]) met our inclusion criteria. The rate of HbA1c acquisition increased from 55% during Q1 to 85%, 86%, 88%, and 87% thereafter. Also, the rate of incorporating personalized management recommendations to discharge letters increased: from 14.9% during Q1 to 42.9%, 43.0%, 47.2%, and 53.4% thereafter. Fifty-eight (17.3%) of patients who got personalized recommendations upon discharge were found to have HbA1c values that were over 1% deviating from suggested target HbA1c. They got the most stringent recommendations. Twenty-nine (50%) of them had available follow-up HbA1c values showing a significant drop in HbA1c: from 9.1% (8.4%-10.2%) to 8.5% (7.4%-9.5%), P = .03. CONCLUSIONS: Personalized, EHR algorithm-based, management recommendations for diabetes upon discharge from hospitalization are feasible and beneficial.

Incidence and Risk Factors for Anastomotic Leakage in Colorectal Surgery: A Historical Cohort Study.

BACKGROUND: Anastomotic leakage (AL) is a major complication following colorectal surgery, with many risk factors established to date. The incidence of AL varies in the medical literature and is dependent on research inclusion criteria and diagnostic criteria. OBJECTIVES: To determine the incidence of and the potential risk factors for AL following colorectal surgery at a single academic medical center. METHODS: We retrospectively reviewed all operative reports of colorectal procedures that included bowel resection and primary bowel anastomosis performed at Sheba Medical Center during 2012. AL was defined according to the 1991 United Kingdom Surgical Infection Study Group criteria. Data were assessed for leak incidence within 30 days. In addition, 17 possible risk factors for leakage were analyzed. A literature review was conducted. RESULTS: This cohort study comprised 260 patients, and included 261 procedures performed during the study period. The overall leak rate was 8.4%. In a univariate analysis, male sex (odds ratio [OR] 3.37, 95% confidence interval [95%CI] 1.21-9.43), pulmonary disease (OR 3.99, 95%CI 1.49-10.73), current or past smoking (OR 2.93, 95%CI 1.21-7.10), and American Society of Anesthesiologist score ≥ 3 (OR 3.08, 95%CI 1.16-8.13) were associated with an increased risk for anastomotic leakage. In a multivariate analysis, male gender (OR 3.62, 95%CI 1.27-10.33) and pulmonary disease (OR 4.37, 95%CI 1.58-12.10) were associated with a greater risk. CONCLUSIONS: The incidence of AL in the present study is similar to that found in comparable series. Respiratory co-morbidity and male sex were found to be the most significant risk factors.