Participatory medicine: A home score for streptococcal pharyngitis enabled by real-time biosurveillance: a cohort study

Artificial intelligence method to classify ophthalmic emergency severity based on symptoms: a validation study

OBJECTIVES

We investigated the usefulness of machine learning artificial intelligence (AI) in classifying the severity of ophthalmic emergency for timely hospital visits.

STUDY DESIGN

This retrospective study analysed the patients who first visited the Armed Forces Daegu Hospital between May and December 2019. General patient information, events and symptoms were input variables. Events, symptoms, diagnoses and treatments were output variables. The output variables were classified into four classes (red, orange, yellow and green, indicating immediate to no emergency cases). About 200 cases of the class-balanced validation data set were randomly selected before all training procedures. An ensemble AI model using combinations of fully connected neural networks with the synthetic minority oversampling technique algorithm was adopted.

PARTICIPANTS

A total of 1681 patients were included.

MAJOR OUTCOMES

Model performance was evaluated using accuracy, precision, recall and F1 scores.

RESULTS

The accuracy of the model was 99.05%. The precision of each class (red, orange, yellow and green) was 100%, 98.10%, 92.73% and 100%. The recalls of each class were 100%, 100%, 98.08% and 95.33%. The F1 scores of each class were 100%, 99.04%, 95.33% and 96.00%.

CONCLUSIONS

We provided support for an AI method to classify ophthalmic emergency severity based on symptoms.

Comparison of Centor and McIsaac scores in primary care: a meta-analysis over multiple thresholds

Background

Centor and McIsaac scores are both used to diagnose group A beta-haemolytic streptococcus (GABHS) infection, but have not been compared through meta-analysis.

Aim

To compare the performance of Centor and McIsaac scores at diagnosing patients with GABHS presenting to primary care with pharyngitis.

Design and setting

A meta-analysis of diagnostic test accuracy studies conducted in primary care was performed using a novel model that incorporates data at multiple thresholds.

Method

MEDLINE, EMBASE, and PsycINFO were searched for studies published between January 1980 and February 2019. Included studies were: cross-sectional; recruited patients with sore throats from primary care; used the Centor or McIsaac score; had GABHS infection as the target diagnosis; used throat swab culture as the reference standard; and reported 2 × 2 tables across multiple thresholds. Selection and data extraction were conducted by two independent reviewers. QUADAS-2 was used to assess study quality. Summary receiver operating characteristic (SROC) curves were synthesised. Calibration curves were used to assess the transferability of results into practice.

Results

Ten studies using the Centor score and eight using the McIsaac score were included. The prevalence of GABHS ranged between 4% and 44%. The areas under the SROC curves for McIsaac and Centor scores were 0.7052 and 0.6888, respectively. The P-value for the difference (0.0164) was 0.419, suggesting the SROC curves for the tests are equivalent. Both scores demonstrated poor calibration.

Conclusion

Both Centor and McIsaac scores provide only fair discrimination of those with and without GABHS, and appear broadly equivalent in performance. The poor calibration for a positive test result suggests other point-of-care tests are required to rule in GABHS; however, with both Centor and McIsaac scores, a score of ≤0 may be sufficient to rule out infection.

A feasibility service evaluation of screening and treatment of group A streptococcal pharyngitis in community pharmacies

OBJECTIVES

The UK 5 year antimicrobial resistance strategy recognizes the role of point-of-care diagnostics to identify where antimicrobials are required, as well as to assess the appropriateness of the diagnosis and treatment. A sore throat test-and-treat service was introduced in 35 community pharmacies across two localities in England during 2014-15.

METHODS

Trained pharmacy staff assessed patients presenting with a sore throat using the Centor scoring system and patients meeting three or all four of the criteria were offered a throat swab test for Streptococcus pyogenes, Lancefield group A streptococci. Patients with a positive throat swab test were offered antibiotic treatment.

RESULTS

Following screening by pharmacy staff, 149/367 (40.6%) patients were eligible for throat swab testing. Of these, only 36/149 (24.2%) were positive for group A streptococci. Antibiotics were supplied to 9.8% (n = 36/367) of all patients accessing the service. Just under half of patients that were not showing signs of a bacterial infection (60/123, 48.8%) would have gone to their general practitioner if the service had not been available.

CONCLUSIONS

This study has shown that it is feasible to deliver a community-pharmacy-based screening and treatment service using point-of-care testing. This type of service has the potential to support the antimicrobial resistance agenda by reducing unnecessary antibiotic use and inappropriate antibiotic consumption.

Patient and Parent-Reported Signs and Symptoms for Group A Streptococcal Pharyngitis

BACKGROUND AND OBJECTIVES

Identifying symptomatic patients who are at low risk for group A streptococcal (GAS) pharyngitis could reduce unnecessary visits and antibiotic use. The accuracy with which patients and parents report signs and symptoms of GAS has not been studied. Our objectives were to measure agreement between patient or parent and physician-reported signs and symptoms of GAS and to evaluate the performance of a modified Centor score, based on patient or parent and physician reports, for identifying patients at low risk for GAS pharyngitis.

METHODS

Children 3 to 21 years old presenting to a single tertiary care emergency department between October 2013 and January 2015 were included if they complained of a sore throat and were tested for GAS. Patients or parents and physicians completed surveys assessing signs and symptoms to determine a modified age-adjusted Centor score for GAS. We evaluated the overall agreement and κ between patient or parent and physician-reported signs and symptoms and compared the performance of the scores based on assessments by patients or parents and physicians and the risk of GAS.

RESULTS

Of 320 patients enrolled, 107 (33%) tested GAS positive. Agreement was higher for symptoms (fever [agreement = 82%, κ = 0.64] and cough [72%, 0.45]) than for signs (exudate [80%, 0.41] and tender cervical nodes [73%, 0.18]). Agreement was highest when no signs and symptoms contained in the Centor score were present (94%, κ = 0.61). The proportion of patients testing GAS positive rose as the modified Centor score increased.

CONCLUSIONS

For identifying GAS pharyngitis, patients or parents and physicians showed moderate to substantial agreement for 3 of 4 key pharyngitis signs and symptoms.

Clinical practice guideline: tonsillitis I. Diagnostics and nonsurgical management

More than 120,000 patients are treated annually in Germany to resolve repeated episodes of acute tonsillitis. Therapy is aiming at symptom regression, avoidance of complications, reduction in the number of disease-related absences in school or at work, increased cost-effectiveness and improved quality of life. The purpose of this part of the guideline is to provide clinicians in any setting with a clinically focused multi-disciplinary guidance through different conservative treatment options in order to reduce inappropriate variation in clinical care, improve clinical outcome and reduce harm. Surgical management in terms of intracapsular as well as extracapsular tonsillectomy (i.e. tonsillotomy) is the subject of part II of this guideline. To estimate the probability of tonsillitis caused by β-hemolytic streptococci, a diagnostic scoring system according to Centor or McIsaac is suggested. If therapy is considered, a positive score of ≥3 should lead to pharyngeal swab or rapid test or culture in order to identify β-hemolytic streptococci. Routinely performed blood tests for acute tonsillitis are not indicated. After acute streptococcal tonsillitis, there is no need to repeat a pharyngeal swab or any other routine blood tests, urine examinations or cardiological diagnostics such as ECG. The determination of the antistreptolysin O-titer (ASLO titer) and other antistreptococcal antibody titers do not have any value in relation to acute tonsillitis with or without pharyngitis and should not be performed. First-line therapy of β-hemolytic streptococci consists of oral penicillin. Instead of phenoxymethylpenicillin–potassium (penicillin V potassium), also phenoxymethlpenicillin–benzathine with a clearly longer half-life can be used. Oral intake for 7 days of one of both the drugs is recommended. Alternative treatment with oral cephalosporins (e.g. cefadroxil, cefalexin) is indicated only in cases of penicillin failure, frequent recurrences, and whenever a more reliable eradication of β-hemolytic streptococci is desirable. In cases of allergy or incompatibility of penicillin, cephalosporins or macrolides (e.g. Erythromycin-estolate) are valuable alternatives.

Evaluation of symptom checkers for self diagnosis and triage: audit study

OBJECTIVE

To determine the diagnostic and triage accuracy of online symptom checkers (tools that use computer algorithms to help patients with self diagnosis or self triage).

DESIGN

Audit study.

SETTING

Publicly available, free symptom checkers.

PARTICIPANTS

23 symptom checkers that were in English and provided advice across a range of conditions. 45 standardized patient vignettes were compiled and equally divided into three categories of triage urgency: emergent care required (for example, pulmonary embolism), non-emergent care reasonable (for example, otitis media), and self care reasonable (for example, viral upper respiratory tract infection).

MAIN OUTCOME MEASURES

For symptom checkers that provided a diagnosis, our main outcomes were whether the symptom checker listed the correct diagnosis first or within the first 20 potential diagnoses (n=770 standardized patient evaluations). For symptom checkers that provided a triage recommendation, our main outcomes were whether the symptom checker correctly recommended emergent care, non-emergent care, or self care (n=532 standardized patient evaluations).

RESULTS

The 23 symptom checkers provided the correct diagnosis first in 34% (95% confidence interval 31% to 37%) of standardized patient evaluations, listed the correct diagnosis within the top 20 diagnoses given in 58% (55% to 62%) of standardized patient evaluations, and provided the appropriate triage advice in 57% (52% to 61%) of standardized patient evaluations. Triage performance varied by urgency of condition, with appropriate triage advice provided in 80% (95% confidence interval 75% to 86%) of emergent cases, 55% (47% to 63%) of non-emergent cases, and 33% (26% to 40%) of self care cases (P<0.001). Performance on appropriate triage advice across the 23 individual symptom checkers ranged from 33% (95% confidence interval 19% to 48%) to 78% (64% to 91%) of standardized patient evaluations.

CONCLUSIONS

Symptom checkers had deficits in both triage and diagnosis. Triage advice from symptom checkers is generally risk averse, encouraging users to seek care for conditions where self care is reasonable.