Gimme 3 Steps (With a Nod to an American Rock Song from the 1970s)

2016 ◽  
Vol 19 (2) ◽  
pp. 080
Author(s):  
Curt G Tribble
Keyword(s):  
Electronic Medical Records ◽  
National Survey ◽  
Medical Records ◽  
Hospitalized Patients ◽  
Physician Burnout ◽  
Recent Comment ◽  
Percent Increase ◽  
Hearts And Minds ◽  
Recent National Survey ◽  
Practicing Physicians

The message that patients are frequently dissatisfied with their interactions with their physicians is a common one. And, articles about physician burnout are plentiful [Shanafelt 2015]. Indeed, a recent national survey showed a nearly 9 percent increase in burnout rates over just the last 3 years [Peckham 2015]. Many factors contribute to this problem, not the least of which is the push to use electronic medical records systems, as evidenced by the recent comment from the acting administrator of the Centers for Medicare and Medicaid, Mr. Andy Slavitt, who said “we have to get the hearts and minds of physicians back. I think we’ve lost them” [McKnight 2016]. <br />While many of the factors contributing to physician dissatisfaction are, and will be, difficult to control, there is at least one source of satisfaction that is within the relatively easy purview of virtually all practicing physicians, and that source is the patients for whom all physicians care.  Fortunately, there are some straightforward, simple, and efficient ways to improve the view patients have of their physicians and the satisfaction that physicians can derive from caring for their patients. Three simple steps that can make both physicians and their patients more satisfied with the interactions between patients and physicians are outlined here. These suggestions are primarily oriented toward physicians in training caring for hospitalized patients, though they are most certainly applicable to all physicians. These suggestions are based on what younger physicians can say to, ask of, or do for a patient under their care, all of which can be easily and efficiently accomplished.

scholarly journals Low ALT values amongst hospitalized patients are associated with increased risk of hypoglycemia and overall mortality: a retrospective, big-data analysis of 51 831 patients

QJM ◽  
2020 ◽  
Author(s):  
E Itelman ◽  
A Segev ◽  
L Ahmead ◽  
E Leibowitz ◽  
M Agbaria ◽  
...  
Keyword(s):  
Electronic Medical Records ◽  
Medical Records ◽  
Cohort Analysis ◽  
Surrogate Marker ◽  
Tertiary Hospital ◽  
Big Data Analysis ◽  
Hospitalized Patients ◽  
Retrospective Cohort Analysis ◽  
Increased Risk ◽  
Overall Mortality

Summary Background Sarcopenia and frailty influence clinical patients’ outcomes. Low alanine aminotransferase (ALT) serum activity is a surrogate marker for sarcopenia and frailty. In-hospital hypoglycemia is associated, also with worse clinical outcomes. Aim We evaluated the association between low ALT, risk of in-hospital hypoglycemia and subsequent mortality. Design This was a retrospective cohort analysis. Methods We included patients hospitalized in a tertiary hospital between 2007 and 2019. Patients’ data were retrieved from their electronic medical records. Results The cohort included 51 831 patients (average age 70.88). The rate of hypoglycemia was 10.8% (amongst diabetics 19.4% whereas in non-diabetics 8.3%). The rate of hypoglycemia was higher amongst patients with ALT &lt; 10 IU/l in the whole cohort (14.3% vs. 10.4%, P &lt; 0.001) as well as amongst diabetics (24.6% vs. 18.8%, P &lt; 0.001). Both the overall and in-hospital mortality were higher in the low ALT group (57.7% vs. 39.1% P &lt; 0.001 and 4.3% vs. 3.2%, P &lt; 0.001). A propensity score matching, after which a regression model was performed, showed that patients with ALT levels &lt; 10 IU/l had higher risk of overall mortality (HR = 1.21, CI 1.13–1.29, P &lt; 0.001). Conclusions Low ALT values amongst hospitalized patients are associated with increased risk of in-hospital hypoglycemia and overall mortality.

scholarly journals Long-term risk of hepatocellular carcinoma mortality in 23220 hospitalized patients treated with micafungin or other parenteral antifungals

2019 ◽  
Vol 75 (1) ◽  
pp. 221-228 ◽  
Author(s):  
Sebastian Schneeweiss ◽  
Peggy L Carver ◽  
Kausik Datta ◽  
Alicia Galar ◽  
Melissa D Johnson ◽  
...  
Keyword(s):  
Hepatocellular Carcinoma ◽  
Electronic Medical Records ◽  
Medical Records ◽  
Patient Characteristics ◽  
Hospitalized Patients ◽  
Liver Tumours ◽  
Event Rates ◽  
Multicentre Cohort

Abstract Background Liver tumours observed in rats exposed to micafungin led to a black box warning upon approval in Europe in 2008. Micafungin’s risk for liver carcinogenicity in humans has not been investigated. We sought to describe the risk of fatal hepatocellular carcinoma (HCC) among persons who received micafungin and other parenteral antifungals (PAFs) with up to 12 years of follow-up. Methods We assembled a US multicentre cohort of hospitalized patients who received micafungin or other PAFs between 2005 and 2012. We used propensity score (PS) matching on patient characteristics from electronic medical records to compare rates of HCC mortality identified through the National Death Index though to the end of December 2016. We computed HRs and 95% CIs. Results A total of 40110 patients who received a PAF were identified; 6903 micafungin recipients (87% of those identified) were successfully matched to 16317 comparator PAF users. Ten incident HCC deaths, one in the micafungin-exposed group and nine among comparator PAF users, occurred in 71285 person-years of follow-up. The HCC mortality rate was 0.05 per 1000 person-years in micafungin patients and 0.17 per 1000 person-years in comparator PAF patients. The PS-matched HR for micafungin versus comparator PAF was 0.29 (95% CI 0.04–2.24). Conclusions Both micafungin and comparator PAFs were associated with HCC mortality rates of &lt;0.2 per 1000 person-years. Given the very low event rates, any potential risk for HCC should not play a role in clinical decisions regarding treatment with micafungin or other PAFs investigated in this study.

scholarly journals Predicting Antibiotic Resistance in Hospitalized Patients by Applying Machine Learning to Electronic Medical Records

2020 ◽  
Author(s):  
Ohad Lewin-Epstein ◽  
Shoham Baruch ◽  
Lilach Hadany ◽  
Gideon Y Stein ◽  
Uri Obolski
Keyword(s):  
Machine Learning ◽  
Antibiotic Resistance ◽  
Electronic Medical Records ◽  
Medical Records ◽  
Bacterial Infections ◽  
Bacterial Species ◽  
Empiric Therapy ◽  
Hospitalized Patients ◽  
Empiric Antibiotic Therapy ◽  
Computerized Decision Support

Abstract Background Computerized decision support systems are becoming increasingly prevalent with advances in data collection and machine learning (ML) algorithms. However, they are scarcely used for empiric antibiotic therapy. Here, we predict the antibiotic resistance profiles of bacterial infections of hospitalized patients using ML algorithms applied to patients’ electronic medical records (EMRs). Methods The data included antibiotic resistance results of bacterial cultures from hospitalized patients, alongside their EMRs. Five antibiotics were examined: ceftazidime (n = 2942), gentamicin (n = 4360), imipenem (n = 2235), ofloxacin (n = 3117), and sulfamethoxazole-trimethoprim (n = 3544). We applied lasso logistic regression, neural networks, gradient boosted trees, and an ensemble that combined all 3 algorithms, to predict antibiotic resistance. Variable influence was gauged by permutation tests and Shapely Additive Explanations analysis. Results The ensemble outperformed the separate models and produced accurate predictions on test set data. When no knowledge regarding the infecting bacterial species was assumed, the ensemble yielded area under the receiver-operating characteristic (auROC) scores of 0.73–0.79 for different antibiotics. Including information regarding the bacterial species improved the auROCs to 0.8–0.88. Variables’ effects on predictions were assessed and found to be consistent with previously identified risk factors for antibiotic resistance. Conclusions We demonstrate the potential of ML to predict antibiotic resistance of bacterial infections of hospitalized patients. Moreover, we show that rapidly gained information regarding the infecting bacterial species can improve predictions substantially. Clinicians should consider the implementation of such systems to aid correct empiric therapy and to potentially reduce antibiotic misuse.

scholarly journals Clinical and laboratory profile of hospitalized patients affected by pressure injury

2020 ◽  
Author(s):  
Marcela Gama Santana Moreira ◽  
Silvia de Magalhães Simões ◽  
Caíque Jordan Nunes Ribeiro
Keyword(s):  
Electronic Medical Records ◽  
Medical Records ◽  
Protein Energy Malnutrition ◽  
Hospitalized Patients ◽  
Mechanical Ventilator ◽  
Pi Method ◽  
Protein Energy ◽  
Preventive Actions ◽  
Pressure Injury ◽  
Laboratory Profile

Objective: To characterize the clinical and laboratory profile of hospitalized patients affected by pressure injury (PI). Method: Retrospective and descriptive study, which included data from electronic medical records of 95 patients affected by PI during hospitalization. Results: There was a predominance of females (52.6%), mean age 74.8 ± 14 years, mean hospital stay was 76.9 ± 88.8 days. Most were admitted to the intensive care unit, with an average of 17.86 ± 36.58 days. Regarding the clinical condition, 60% were using a mechanical ventilator when they developed PI, 37.9% needed hemodialysis, 30.4% were diagnosed with some degree of protein-energy malnutrition and 54.7% progressed to death. The most frequent comorbidities were hypertension (63.16%), diabetes (43.16%) and neuropathy (33.68%). As for the laboratory profile, hypoalbuminemia (97.3%), hyperglycemia (87.8%), anemia (84.4%) and hyperuremia (78.9%) were present in more than two thirds of the sample. Conclusion: This study allowed to know the profile of patients affected by PI during hospitalization, which can serve as a basis for developing scientifically based effective preventive actions.

scholarly journals Predicting antibiotic resistance in hospitalized patients by applying machine learning to electronic medical records

2020 ◽  
Author(s):  
Ohad Lewin-Epstein ◽  
Shoham Baruch ◽  
Lilach Hadany ◽  
Gideon Y Stein ◽  
Uri Obolski
Keyword(s):  
Machine Learning ◽  
Antibiotic Resistance ◽  
Electronic Medical Records ◽  
Medical Records ◽  
Bacterial Infections ◽  
Bacterial Species ◽  
Hospitalized Patients ◽  
Machine Learning Algorithms ◽  
Ensemble Model ◽  
Machine Learning Models

AbstractBackgroundComputerized decision support systems are becoming increasingly prevalent with advances in data collection and machine learning algorithms. However, they are scarcely used for empiric antibiotic therapy. Here we accurately predict the antibiotic resistance profiles of bacterial infections of hospitalized patients using machine learning algorithms applied to patients’ electronic medical records.MethodsThe data included antibiotic resistance results of bacterial cultures from hospitalized patients, alongside their electronic medical records. Five antibiotics were examined: Ceftazidime (n=2942), Gentamicin (n=4360), Imipenem (n=2235), Ofloxacin (n=3117) and Sulfamethoxazole-Trimethoprim (n=3544). We applied lasso logistic regression, neural networks, gradient boosted trees, and an ensemble combining all three algorithms, to predict antibiotic resistance. Variable influence was gauged by permutation tests and Shapely Additive Explanations analysis.ResultsThe ensemble model outperformed the separate models and produced accurate predictions on a test set data. When no knowledge regarding the infecting bacterial species was assumed, the ensemble model yielded area under the receiver-operating-characteristic (auROC) scores of 0.73-0.79, for different antibiotics. Including information regarding the bacterial species improved the auROCs to 0.8-0.88. The effects of different variables on the predictions were assessed and found consistent with previously identified risk factors for antibiotic resistance.ConclusionsOur study demonstrates the potential of machine learning models to accurately predict antibiotic resistance of bacterial infections of hospitalized patients. Moreover, we show that rapid information regarding the infecting bacterial species can improve predictions substantially. The implementation of such systems should be seriously considered by clinicians to aid correct empiric therapy and to potentially reduce antibiotic misuse.40-word summaryMachine learning models were applied to large and diverse datasets of medical records of hospitalized patients, to predict antibiotic resistance profiles of bacterial infections. The models achieved high accuracy predictions and interpretable results regarding the drivers of antibiotic resistance.

scholarly journals Methods of defining hypertension in electronic medical records: validation against national survey data

2015 ◽  
Vol 38 (3) ◽  
pp. e392-e399 ◽  
Author(s):  
Mingkai Peng ◽  
Guanmin Chen ◽  
Gilaad G. Kaplan ◽  
Lisa M. Lix ◽  
Neil Drummond ◽  
...  
Keyword(s):  
Survey Data ◽  
Electronic Medical Records ◽  
National Survey ◽  
Medical Records

Allergic Reactions in Hospitalized Patients With a Self-Reported Penicillin Allergy Who Receive a Cephalosporin or Meropenem

2016 ◽  
Vol 30 (1) ◽  
pp. 42-48 ◽  
Author(s):  
Danielle Joset Crotty ◽  
Xian Jie Cindy Chen ◽  
Marco R. Scipione ◽  
Yanina Dubrovskaya ◽  
Eddie Louie ◽  
...  
Keyword(s):  
Confidence Interval ◽  
Allergic Reaction ◽  
Electronic Medical Records ◽  
Broad Spectrum ◽  
Medical Records ◽  
Odds Ratio ◽  
Hospitalized Patients ◽  
Penicillin Allergy ◽  
Allergic Reactions ◽  
Individual Study

Background: Cefepime and meropenem are used frequently in hospitalized patients for broad-spectrum empiric coverage, however, practitioners are often reluctant to prescribe these antibiotics for patients with a self-reported nonsevere, nontype I allergic reaction to penicillin. Methods: Retrospective review of electronic medical records of adults with a self-reported allergy to penicillin who received at least 1 dose of cefepime, ceftriaxone, cefoxitin, cephalexin, or meropenem to assess incidence and type of allergic reactions. Results: Of 175 patients included, 10 (6%) patients experienced an allergic reaction. The incidence for individual study drugs were cefepime 6% (6 of 96), meropenem 5% (3 of 56), cefoxitin 8% (1 of 13), ceftriaxone 0% (0 of 69), and cephalexin 0% (0 of 8). The majority of patients experienced a rash with or without pruritus and fever. Patients with a concomitant “sulfa” allergy (odds ratio [OR] 5.4, 95% confidence interval [CI] 1.4-21, P = .02) or ≥3 other drug allergies (OR 6.4, 95% CI 1.3-32, P = .025) were more likely to have an allergic reaction. Conclusions: In one of the largest retrospective reviews of hospitalized patients who received full dose therapy with cefepime, ceftriaxone, and meropenem, the incidence of allergic reactions was low and reactions were mild. Cefepime, ceftriaxone, and meropenem can be considered for use in patients with a self-reported nontype I penicillin allergy.

Sign in / Sign up

Export Citation Format

Share Document