Added value of an artificial intelligence algorithm in reducing the number of missed incidental acute pulmonary embolism in routine portal venous phase chest CT.

OBJECTIVES: The purpose of this study was to evaluate the incremental value of artificial intelligence (AI) compared to the diagnostic accuracy of radiologists alone in detecting incidental acute pulmonary embolism (PE) on routine portal venous contrast-enhanced chest computed tomography (CT). METHODS: CTs of 3089 consecutive patients referred to the radiology department for a routine contrast-enhanced chest CT between 27-5-2020 and 31-12-2020, were retrospectively analysed by a CE-certified and FDA-approved AI algorithm. The diagnostic performance of the AI was compared to the initial report. To determine the reference standard, discordant findings were independently evaluated by two readers. In case of disagreement, another experienced cardiothoracic radiologist with knowledge of the initial report and the AI output adjudicated. RESULTS: The prevalence of acute incidental PE in the reference standard was 2.2% (67 of 3089 patients). In 25 cases, AI detected initially unreported PE. This included three cases concerning central/lobar PE. Sensitivity of the AI algorithm was significantly higher than the outcome of the initial report (respectively 95.5% vs. 62.7%, p < 0.001), whereas specificity was very high for both (respectively 99.6% vs 99.9%, p = 0.012). The AI algorithm only showed a slightly higher amount of false-positive findings (11 vs. 2), resulting in a significantly lower PPV (85.3% vs. 95.5%, p = 0.047). CONCLUSION: The AI algorithm showed high diagnostic accuracy in diagnosing incidental PE, detecting an additional 25 cases of initially unreported PE, accounting for 37.3% of all positive cases. CLINICAL RELEVANCE STATEMENT: Radiologist support from AI algorithms in daily practice can prevent missed incidental acute PE on routine chest CT, without a high burden of false-positive cases. KEY POINTS: • Incidental pulmonary embolism is often missed by radiologists in non-diagnostic scans with suboptimal contrast opacification within the pulmonary trunk. • An artificial intelligence algorithm showed higher sensitivity detecting incidental pulmonary embolism on routine portal venous chest CT compared to the initial report. • Implementation of artificial intelligence support in routine daily practice will reduce the number of missed incidental pulmonary embolism.

Retrospective batch analysis to evaluate the diagnostic accuracy of a clinically deployed AI algorithm for the detection of acute pulmonary embolism on CTPA.

PURPOSE: To generate and extend the evidence on the clinical validity of an artificial intelligence (AI) algorithm to detect acute pulmonary embolism (PE) on CT pulmonary angiography (CTPA) of patients suspected of PE and to evaluate the possibility of reducing the risk of missed findings in clinical practice with AI-assisted reporting. METHODS: Consecutive CTPA scan data of 3316 patients referred because of suspected PE between 24-2-2018 and 31-12-2020 were retrospectively analysed by a CE-certified and FDA-approved AI algorithm. The output of the AI was compared with the attending radiologists' report. To define the reference standard, discordant findings were independently evaluated by two readers. In case of disagreement, an experienced cardiothoracic radiologist adjudicated. RESULTS: According to the reference standard, PE was present in 717 patients (21.6%). PE was missed by the AI in 23 patients, while the attending radiologist missed 60 PE. The AI detected 2 false positives and the attending radiologist 9. The sensitivity for the detection of PE by the AI algorithm was significantly higher compared to the radiology report (96.8% vs. 91.6%, p < 0.001). Specificity of the AI was also significantly higher (99.9% vs. 99.7%, p = 0.035). NPV and PPV of the AI were also significantly higher than the radiology report. CONCLUSION: The AI algorithm showed a significantly higher diagnostic accuracy for the detection of PE on CTPA compared to the report of the attending radiologist. This finding indicates that missed positive findings could be prevented with the implementation of AI-assisted reporting in daily clinical practice. CRITICAL RELEVANCE STATEMENT: Missed positive findings on CTPA of patients suspected of pulmonary embolism can be prevented with the implementation of AI-assisted care. KEY POINTS: The AI algorithm showed excellent diagnostic accuracy detecting PE on CTPA. Accuracy of the AI was significantly higher compared to the attending radiologist. Highest diagnostic accuracy can likely be achieved by radiologists supported by AI. Our results indicate that implementation of AI-assisted reporting could reduce the number of missed positive findings.

Prospective cohort study of high-volume transanal irrigation in patients with constipation and/or faecal incontinence.

AIM: The aim of this work was to determine the clinical efficacy of high-volume transanal irrigation (TAI) in patients with constipation and/or faecal incontinence using validated symptom and quality of life questionnaires. METHOD: This was a prospective cohort study of 114 consecutive patients with constipation and/or faecal incontinence (Rome IV defined) who started TAI. A comprehensive questionnaire was completed at baseline and 4, 12, 26 and 52 weeks' follow-up. The primary objective was significant symptom reduction [≥30%; Cleveland Clinic Constipation Score (CCCS) and St Marks Incontinence Score (SMIS)] in those who continued TAI at 52 weeks. Secondary objectives were (1) continuation rates of TAI, (2) effect on quality of life (QoL) and (3) identification of predictors for continuation. RESULTS: A total of 59 (51.8%) patients with constipation, 26 (22.8%) with faecal incontinence and 29 (25.4%) with coexistent symptoms were included. At 52 weeks, 41 (36.0%) patients continued TAI, 63 (55.2%) stopped and 10 (8.8%) patients were lost to follow-up. In those who continued TAI at 52 weeks (n = 41), no reduction of constipation symptoms was observed. Median Patient Assessment of Constipation Quality of Life scores decreased on most domains, indicating QoL improvement. Reduction of faecal incontinence occurred in 5/9 (55.6%) patients with faecal incontinence and in 3/10 (30.0%) patients with coexistent symptoms. The median SMIS per-individual decreased in patients with coexistent symptoms (2; interquartile range 0-4; p = 0.023). Median Fecal Incontinence Quality of Life scores increased in most domains, indicating improved QoL. No clinical characteristics predicted continuation. CONCLUSION: One-third (n = 41) of patients continued TAI at 52 weeks. In those who continued TAI at 52 weeks, symptoms of faecal incontinence (SMIS) were reduced but not constipation (CCCS). QoL related to both constipation and faecal incontinence improved. No clinical characteristics predicted continuation.

Antibiotic Treatment foLlowing surgical drAinage of perianal abScess (ATLAS): protocol for a multicentre, double-blind, placebo-controlled, randomised trial.

INTRODUCTION: Perianal fistula is a burdening disease with an annual incidence of 6-12/100 000 in Western countries. More than 90% of crypto-glandular fistulas originate from perianal abscess. Despite adequate drainage, up to 83% recur or result in an anal fistula, the majority developing within 12 months. There is some evidence that gut-derived bacteria play a role in the development of perianal fistula. Up till now, it is not common practice to routinely administer prophylactic antibiotics to prevent anal fistula development. There is a need for a study to establish whether adding antibiotic treatment to surgical drainage of perianal abscess results in a reduction in perianal fistulas. METHODS AND ANALYSIS: This multicentre, double-blind, randomised, placebo-controlled trial investigates whether addition of antibiotics (ciprofloxacin and metronidazole) to surgical drainage of a perianal abscess is beneficial compared with surgical drainage alone. The primary outcome is the development of a perianal fistula within 1 year. Secondary outcomes include quality of life, treatment costs, need for repeated drainage, patient-reported outcomes and other clinical outcomes. Participants are recruited in one academic and seven peripheral Dutch clinics. To demonstrate a reduction of perianal fistula from 30% to 15% when treated with adjuvant antibiotics with a two-sided alpha of 0.05, a power of 80% and taking a 10% loss to follow-up percentage into account, the total sample size will be 298 participants. Data will be analysed according to the intention-to-treat principle. ETHICS AND DISSEMINATION: The study protocol has been approved by the Medical Ethics Review Committee of the Amsterdam University Medical Centers (nr. 2021_010). Written consent is obtained from each participant prior to randomisation into the study. The results of this trial will be submitted for publication in international peer-reviewed journals, presented at conferences and spread to coloproctological associations. TRIAL REGISTRATION NUMBERS: 2020-004449-35; NCT05385887.

Management of chronic anal fissure: results of a national survey among gastrointestinal surgeons in the Netherlands.

BACKGROUND: Chronic anal fissure (CAF) is a common, bothersome condition frequently accompanied by pelvic floor complaints. Despite current guidelines, optimal management is challenging. The aim of this study is to evaluate current management of CAF among gastrointestinal surgeons in the Netherlands. METHODS: Dutch gastrointestinal surgeons and residents were sent a survey invitation by email, which was available online between June 2021 and September 2021. The questionnaire consisted of 21 questions concerning work experience, physical examination, diagnostic and surgical techniques, and follow-up. RESULTS: Overall, 106 (33%) respondents completed the survey. Most respondents (59%) had at least 10 years of experience in treating CAF. Only 23% always addressed pelvic floor complaints. Fifty-one percent performed digital rectal examination and 22% always, or almost always, examined the pelvic floor muscles. Most respondents started treatment with fibers and/or laxatives and ointment (96%). Diltiazem was in 90% the preferred ointment. Twenty-two percent referred patients for pelvic floor physical therapy. Botulinum toxin was in 54% performed under general or spinal anesthesia or sedation. The surgical procedure of choice was fissurectomy (71%) followed by lateral internal sphincterotomy (27%). Fissurectomy was in 51% always combined with botulinum toxin. Fifty-seven percent of the respondents preferred a physical follow-up appointment. CONCLUSION: Guideline recommendations are largely followed in the Netherlands, starting with conservative measures followed by surgical procedures. Surgeons do not consistently assess pelvic floor complaints, nor do they routinely examine the pelvic floor muscles. Awareness of pelvic floor dysfunctions is important to refer patients for pelvic floor physical therapy.

Hemorrhoidectomy versus rubber band ligation in grade III hemorrhoidal disease: a large retrospective cohort study with long-term follow-up.

PURPOSE: Standard therapy for grade III hemorrhoids is rubber band ligation (RBL) and hemorrhoidectomy. The long-term clinical and patient-reported outcomes of these treatments in a tertiary referral center for proctology were evaluated. METHODS: A retrospective analysis was performed in all patients with grade III hemorrhoids who were treated between January 2013 and August 2018. Medical history, symptoms, reinterventions, complications, and patient-reported outcome measurements (PROM) were retrieved from individual electronic patient files, which were prospectively entered as standard questionnaires in our clinic. RESULTS: Overall, 327 patients (163 males) were treated by either RBL (n=182) or hemorrhoidectomy (n=145). The median follow-up was 44 months. The severity of symptoms and patient preference led to the treatment of choice. The most commonly experienced symptoms were prolapse (83.2%) and blood loss (69.7%). Hemorrhoidectomy was effective in 95.9% of the cases as a single procedure, while a single RBL procedure was only effective in 51.6%. In the RBL group, 34.6% received a second RBL session. Complications were not significantly different, 11 (7.6%) after hemorrhoidectomy versus 6 (3.3%) after RBL. However, 4 fistulas developed after hemorrhoidectomy and none after RBL (P<0.05). The pre-procedure PROM score was higher in the hemorrhoidectomy group whereas the post-procedure PROM score did not significantly differ between the groups. CONCLUSION: Treatment of grade III hemorrhoids usually requires more than one session RBL whereas 1-time hemorrhoidectomy suffices. Complications were more common after hemorrhoidectomy. The patient-related outcome did not differ between procedures.

A mixed psychiatric and somatic care unit for trauma patients: 10 years of experience in an urban level I trauma center in the Netherlands.

BACKGROUND: A medical-psychiatric unit (MPU) is a special ward where staff is trained in caring for patients with psychiatric or behavioural problems that need hospitalisation for physical health problems. It is well known that these patients are at higher risk of complications and have a longer length of stay resulting in higher costs than patients without psychiatric comorbidity. The objective of this study was to analyse the trauma patient population of the first 10 years of existence of the MPU in a level I trauma center. PATIENTS AND METHODS: A retrospective analysis was performed in 2-year cohorts from 2006 to 2016. All trauma patients admitted to the MPU were compared with the overall trauma patient population in VUmc. Data (psychiatric diagnosis, substance abuse, trauma scores, surgical interventions, complications, mortality) were extracted from individual patient notes and the Regional Trauma Registry. RESULTS: 258 patients were identified. 36% of all patients had a history of previous psychiatric admission and 30% had attempted suicide at least once in their lifetime. Substance abuse was the most common psychiatric diagnosis (39%), with psychotic disorder (28%) in second place. The median hospital stay was 21 days. Median MPU length of stay was 10 days (range 1-160). Injuries were self-inflicted in 57%. The most common mechanism of injury was fall from height with intentional jumping in second place. Penetrating injury rate was 24% and 33% had an ISS ≥ 16, compared to 5% and 15%, respectively, in the overall trauma patient population. The most common injuries were those of the head and neck. Complication rate was 49%. CONCLUSION: Trauma patients that were admitted to the MPU of an urban level I trauma center had serious psychiatric comorbidity as well as high injury severity. Penetrating injury was much more common than in the overall trauma patient population. A high complication rate was noted. The high psychiatric comorbidity and the complicated care warrants combined psychiatric and somatic (nursing) care for this subpopulation of trauma patients. This should be taken into account in the prehospital triage to a trauma center. The institution of a MPU in level I trauma centers is recommended.