Late Bleeding Research Articles

PREDICTORS OF LATE BLEEDING IN THE TAVR POPULATION

Background: TAVR patients are often elderly with multiple comorbidities increasing their susceptibility to late bleeding. Post-TAVR anticoagulation is without data for guidance. To provide insight, the relationships between late bleeding, comorbidities and discharge medications were assesed.

Computational methods using genome-wide association studies to predict radiotherapy complications and to identify correlative molecular processes

The biological cause of clinically observed variability of normal tissue damage following radiotherapy is poorly understood. We hypothesized that machine/statistical learning methods using single nucleotide polymorphism (SNP)-based genome-wide association studies (GWAS) would identify groups of patients of differing complication risk, and furthermore could be used to identify key biological sources of variability. We developed a novel learning algorithm, called pre-conditioned random forest regression (PRFR), to construct polygenic risk models using hundreds of SNPs, thereby capturing genomic features that confer small differential risk. Predictive models were trained and validated on a cohort of 368 prostate cancer patients for two post-radiotherapy clinical endpoints: late rectal bleeding and erectile dysfunction. The proposed method results in better predictive performance compared with existing computational methods. Gene ontology enrichment analysis and protein-protein interaction network analysis are used to identify key biological processes and proteins that were plausible based on other published studies. In conclusion, we confirm that novel machine learning methods can produce large predictive models (hundreds of SNPs), yielding clinically useful risk stratification models, as well as identifying important underlying biological processes in the radiation damage and tissue repair process. The methods are generally applicable to GWAS data and are not specific to radiotherapy endpoints.

Intensity-Modulated Radiation Therapy with Stereotactic Body Radiation Therapy Boost for Unfavorable Prostate Cancer: A Report on 3-Year Toxicity.

Recent data suggest that intensity-modulated radiation therapy (IMRT) plus brachytherapy boost for unfavorable prostate cancer provides improved biochemical relapse-free survival over IMRT alone. Stereotactic body radiation therapy (SBRT) may be a less invasive alternative to brachytherapy boost. Here, we report the 3-year gastrointestinal (GI) and genitourinary (GU) toxicities of IMRT plus SBRT boost. Between March 2008 and September 2012, patients with prostate cancer were treated with robotic SBRT (19.5 Gy in three fractions) followed by fiducial-guided IMRT (45-50.4 Gy) on an institutional protocol. Toxicity was prospectively graded using the common terminology criteria for adverse events version 4.0 (CTCAEv.4) at the start of and at 1- to 6-month intervals after therapy. Rectal telangiectasias were graded using the Vienna Rectoscopy Score (VRS). At a median follow-up of 4.2 years (2.4-7.5), 108 patients (4 low-, 45 intermediate-, and 59 high-risk) with a median age of 74 years (55-92) were treated with SBRT plus IMRT, with 8% on anticoagulation and an additional 48% on antiplatelet therapy at the start of therapy. The cumulative incidence of late ≥grade 2 GI toxicity was 12%. Of these, 7% were due to late rectal bleeding, with six patients requiring up to two coagulation procedures. One patient with rectal telangiectasias was treated with hyperbaric oxygen (grade 3 toxicity). No rectal fistulas or stenoses were observed. Ten patients had multiple non-confluent telangiectasias (VRS grade 2), and three patients had multiple confluent telangiectasias (VRS grade 3). The cumulative incidence of late grade 3 GU toxicity was 6%. Most late toxicities were due to hematuria requiring bladder fulguration. There were no late ≥grade 4 GU toxicities. Rates of clinically significant GI and GU toxicities are modest following IMRT plus SBRT boost. Future studies should compare cancer control, quality of life, and toxicity with other treatment modalities for patients with high-risk prostate cancer.

Clinical and dosimetric predictors of late rectal bleeding of prostate cancer after TomoTherapy intensity modulated radiation therapy.

IntroductionRectal bleeding after radiotherapy impacts the quality of life of long‐term surviving prostate cancer patients. We sought to identify factors associated with late rectal bleeding following intensity modulated radiation therapy (IMRT) using TomoTherapy for prostate cancer.MethodsWe retrospectively analysed 82 patients with localised prostate cancer treated with TomoTherapy. Most patients (95.1%) received neoadjuvant and concurrent hormone therapy. Forty‐two patients (51.2%) graded as high risk using D'Amico's classification underwent radiotherapy involving the pelvic nodal area. Late bleeding complications were quantified using the Common Terminology Criteria for Adverse Events v4.0. Multiple clinical and dosimetric factors were considered with reference to rectal bleeding.ResultsThe median follow‐up period was 538 (range, 128–904) days. Grades 1, 2 and 3 rectal bleeding were observed in 14 (17.1%), four (4.9%) and one (1.2%) patient respectively. In multivariate analysis, the following factors were significantly associated with Grade ≥1 late rectal bleeding: volume, mean dose (P = 0.012) and rectal V30 (P = 0.025), V40 (P = 0.011), V50 (P = 0.017) and V60 (P = 0.036). When exclusively considering Grade 2–3 rectal bleeding, significant associations were observed with the use of anticoagulants or antiaggregates (P = 0.007), rectal V30 (P = 0.021) and V40 (P = 0.041) in univariate analysis.ConclusionsOur results suggested that the intermediate rectal dose‐volume (V30–V60) was a significant predictor for mild to severe late rectal bleeding (Grade ≥1). Rectal dose‐volumes >V70, which represented the volume of the highest doses, were not predictive in this study.

MynxGrip for Closure of Antegrade Puncture After Peripheral Interventions With Same-Day Discharge.

This was the first prospective study to assess the safety and efficiency of MynxGrip vascular closure device (VCD) in peripheral interventions with antegrade access. We enrolled 66 consecutive patients from 1 center. All patients were discharged home on the day of procedure and were observed for adverse events at 1 and 30 days of follow-up. No major complications were observed. The rate of minor complications (conversion to manual or mechanical compression) was 7.6%. Postdischarge, 3% of patients experienced minor complications-small abscess, ipsilateral deep vein thrombosis. In 1 patient, a second VCD was deployed after device failure. The derived device failure rate was 5.9%. No patients required hospitalization. No late bleeding and no hematomas >6 cm were noted. The mean time to discharge was 4 hours and 5 minutes. The MynxGrip was safe and effective in sealing access sites after antegrade femoral artery puncture with same-day discharge.

Evaluation of the effects of montelukast, mometasone furoate, and combined therapyon adenoid size: a randomized, prospective, clinical trial with objective data

Background/aim: The incidence of adenoid hypertrophy is 2%-3% in children. Adenoidectomy is a commonly performed procedure in children that may cause complications such as early or late bleeding (4%-5%), recurrence of adenoid tissue (10%-20%), and postoperative respiratory problems (27%). Therefore, medical therapy alternatives to adenoidectomy are important and must be tried before surgery. In this study, we investigated the efficacy of mometasone furoate, montelukast, and a combination of these drugs in pediatric patients with adenoid hypertrophy who were scheduled for reduction with medical therapy after not being recommended for surgery.Materials and methods: The study included 120 children with adenoid hypertrophy aged between 4 and 10 years. The patients were randomized into 4 separate groups, with 30 in each group. Group 1 received 100 μg of mometasone furoate per day, group 2 received 4/5 mg (for age) montelukast per day, and group 3 received mometasone furoate + montelukast. Medical therapy continued for 3 months in the treatment groups. Group 4, which comprised patients with mild symptoms, received no treatment and was the control group. The pre- and posttreatment adenoid tissue ratios in lateral neck radiographs were recorded in the four groups. Results: When radiologic measurements of adenoid-to-air passage were calculated, an improvement of 21.76% was observed in group 1 after treatment. The rate of improvement was 22.51% in group 2. There was a 21.79% reduction in adenoid size in group 3 after 3 months? treatment and 12.46% in the control group. There were statistically significant differences between pre- and posttreatment values in every single group administered corticosteroids, montelukast, and combined therapy (P < 0.05).Conclusion: According to our results, both montelukast and mometasone furoate therapies were similarly successful in treating adenoid hypertrophy. Combined therapy has no superiority over single-therapy treatment.

USG Evaluation of Postpartum Complications

Immediate postpartum complications are vaginal bleeding and genial tract tear. Ultrasound is greatly helpful for evaluation of the causes, the location and the severity of these immediate complications. Deep vein thrombosis, which can lead to pulmonary artery embolism, is not so infrequent postpartum period, especially after Cesarean section. Now the most useful diagnostic modality for deep vein thrombosis is ultrasonography. Post-partum period ends 6 weeks after birth. This period is vulnerable for genital, pelvic infections. Late postpartum bleeding also can occur due to retained placenta. H-mole and arterio-venous malformations are not frequent but possible in this period. Ultrasonography is useful to detect and evaluate these complications.

Bleeding after Gastric Bypass Surgery: The Possibility of using of Postoperative Balloon Enteroscopy

In the majority of cases late postoperative bleedings are intraluminal ones, showing clinical manifestations of high gastrointestinal hemorrhage. Among all bariatric procedures, this complication develops more commonly after Rouxen- Y gastric bypass. The most likely cause of such bleedings being peptic ulcer, conservative therapy with proton pump inhibitors is well justified at the initial stages of treatment. Upper endoscopy is the treatment of choice for bleeding ulcers localized in the pouch and 80% of bleedings in the pouch or gastroenteroanastomosis can be controlled in this way. If the bleeding is localized in the remnant stomach or duodenum and small intestine, more advanced endoscopic procedures are needed. Balloon enteroscopy is one of such techniques, although its efficacy in the treatment of bleeding resulting from biliopancreatic limb is extremely variable and depends mainly on specialist’s skills, length of intestinal loop as well as severity of adhesions in the abdominal cavity. The article describes our experience of enteroscopy used to control bleeding from duodenal ulcer after Roux-en-Y gastric bypass intervention.

Niemann-pick type a: A rare case presenting with late onset bleeding due to Vitamin K deficiency

K vitamini eksikligine bagli kanama (KVEBK) nadir gorulmekle birlikte erken sut cocuklugu doneminde hayati tehdit edebilir. Kanamanin gorulme zamanina gore erken (0-1 gun), klasik (1-7 gun) ve gec (8 gun-6 ay) KVEBK olarak siniflandirilir. Kanamanin en sik 3-8 hafta arasinda basladigi gec tipte genellikle daha once tani konmamis kolestaz mevcuttur. Niemann Pick hastaligi, sfingomyelin birikimi sonucu kopuksu histiyositleri andiran ozel depo hucreleriyle iliskili bir grup lizozomal depo hastaligidir. Hastaligin A ve C tipinde yenidogan doneminde kendiliginden gerileyen kolestaz gelisebilecegi bilinmektedir. Bir ayliktan itibaren uc defa gobeginden kanama olmasi nedeniyle tarafimiza basvuran iki aylik hastanin tetkiklerinde PT ve PTT uzamasi mevcuttu. Gec tip KVEBK icin bir risk faktoru olan kolestaz arastirildi ve saptandi. K vitamini uygulamasi sonrasi kanama tekrarlamadi. Takiplerinde kolestazi gerileyen ancak karaciger ve dalak boyutlari artan hastanin ileri incelemeleri sonucunda SMPD1 geninde homozigot yeni bir mutasyon gosterilerek Niemann-Pick tip A tanisi kondu. Bu yazida K vitamini eksikligine bagli gobek kanamasi ile gelen ve ilk defa bildirilen Nieman-Pick hastaligi tip A tanili olgu sunuldu.

Who will benefit most from hydrogel rectum spacer implantation in prostate cancer radiotherapy? A model-based approach for patient selection

Background and purposePrevious studies confirmed that implantable rectum spacers (IRS) decreased acute gastro-intestinal (GI) toxicity in a significant percentage of prostate cancer patients undergoing intensity modulated radiation therapy (IMRT). We developed decision rules based on clinical risk factors (CRFs) to select those patients who are expected to benefit most from IRS implantation. Materials and methodsFor 26 patients dose distributions with (IMRT+IRS) and without (IMRT−IRS) IRS were calculated. Validated nomograms based on CRFs and dosimetric criteria (anorectal V40Gy and V75Gy) were used to predict probabilities for grade 2–3 (G2–3) acute GI toxicity, G2–3 late rectal bleeding (LRB), G3 LRB, and G2–3 faecal incontinence (FI) for IMRT+IRS and IMRT−IRS. All permutations of CRFs were generated to identify most benefit scenarios (MBS) in which a predicted toxicity reduction of ⩾5% points in ⩾25% of the cohort was present due to IRS implantation. ResultsIMRT+IRS revealed a significant reduction in V40Gy (p=0.0357) and V75Gy (p<0.0001) relative to IMRT−IRS. For G2-3 acute GI toxicity and G2–3 LRB, the predicted toxicity rates decreased in 17/26 (65%) and 20/26 (77%) patients, and decision rules were derived for 22/32 (69%) and 12/64 (19%) MBS, respectively. From the decision rules, it follows that diabetes status has no impact on G2–3 acute toxicity, and in absence of pre-RT abdominal surgery, the implantation of an IRS is predicted to show no clinically relevant benefit for G2–3 LRB. ConclusionsProstate cancer patients who are expected to benefit most from IRS implantation can be identified prior to IMRT based on their CRFs profile.

Complicaciones hemorrágicas tras el tratamiento endoscópico de reducción del volumen pulmonar con espiral: estudio observacional retrospectivo

IntroductionEndoscopic lung volume reduction coil (LVRC) treatment is an option for selected patients with severe emphysema. This study was conducted to determine the incidence of bleeding complications after LVRC treatment, to identify risk factors and to discuss treatment options in case of hemoptysis which does not resolve spontaneously. MethodsRetrospective observational study conducted in the Department of Respiratory Medicine at the University Medical Center Hamburg-Eppendorf in all subjects in whom LVRC treatment was performed between April 1, 2012 and September 30, 2015. ResultsDuring the study period, 101 LVRC procedures were performed in 62 subjects. Early post-procedural bleeding was encountered in 65.3% of cases. Hemoptysis was significantly more likely to occur in patients receiving acetylsalicylic acid (P=.005). Hemoptysis resolved spontaneously in 98.5% of cases. In the one case (1.5%) with persistent hemoptysis, bronchial artery embolization was successful in terminating bleeding. Hospital stay was significantly prolonged in subjects with hemoptysis (P=.01). No significant differences were found between subjects with or without hemoptysis in terms of chronic obstructive pulmonary disease exacerbations within four weeks after LVRC treatment (P=.18). Late bleeding complications were observed in 3 subjects (3.0%). In 2 of these cases, bronchial artery embolization was performed and bleeding was successfully terminated. ConclusionsSelf-limiting low volume bleeding is a common finding in the first days after LVRC treatment. However, persistent bleeding may occur in the early post-procedural phase and late after LVRC treatment. In these cases, bronchial artery embolization was a feasible and successful approach to terminating bleeding.

Management of laryngoceles by transoral robotic surgery.

We herein report our experience with the management of laryngoceles using transoral robotic surgery (TORS). A bicentric retrospective study was conducted from November 2009 to September 2015. The inclusion criteria were treatment of a laryngocele by TORS and no malignancy on definitive histopathology. Surgery was performed using the Da Vinci (Intuitive®) surgical robot. Surgical methods and post-operative outcomes were evaluated. Eight patients (four men and four women) presenting with a laryngocele (one bilateral case) were included (mean age 61.8years). There was one covering tracheotomy. The average post-operative stay was 3.75days. Three patients treated for a combined laryngocele had a nasogastric feeding tube inserted for 5days. One patient experienced late laryngeal bleeding that required surgical treatment. TORS may offer an efficient treatment option for laryngoceles. The use of precise and flexible instruments and a three-dimensional camera allow fine dissection of these tumours, preserving the glottic space and vocal function, even for combined laryngoceles extending deep within the neck.Evidence level: 4.

Frequency and predictors of bleeding events after 2nd generation drug-eluting stent implantation differ depending on time after implantation

BackgroundAntiplatelet therapy is required after drug-eluting stent (DES) implantation, but bleeding events occur unexpectedly. We aimed to assess whether bleeding event predictors after 2nd generation DES (2nd DES) implantation differed by time after implantation. MethodsWe studied 1912 consecutive patients who underwent successful 2nd DES implantation (70±10 years, 72% male). Bleeding events were recorded as early (≤1 year) and late (>1 year). Major bleeding events were defined as a composite of type 5, 3, and 2 bleeding in the Bleeding Academic Research Consortium criteria. Predictors were assessed using a Cox proportional hazard model. ResultsBleeding event rates were 3.3%, 5.1%, and 6.7% at 1, 2, and 3 years, respectively, with the highest 1-year rate in year 1 (p<0.001). Cause and severity of bleeding events were similar between early and late bleeding events. Prior history of gastrointestinal bleeding, non-steroidal anti-inflammatory drug use, and triple antithrombotic therapy [adjusted risk ratio (RR): 3.68, 3.21, 4.57, respectively; p<0.01] were independent predictors of early bleeding events. Age >80 years and severe renal dysfunction (adjusted RR: 2.27, 2.02, respectively; p<0.01) were independent predictors of late bleeding events. Survival rate was significantly lower in patients with bleeding events compared with patients without bleeding events (82.4% vs 90.1%; p<0.001). ConclusionFrequency and predictors of bleeding events after 2nd DES implantation differ by time after implantation. Treatment strategies corresponding to individual patients are required.

Bleeding Complications After Endoscopic Lung Volume Reduction Coil Treatment: A Retrospective Observational Study

IntroductionEndoscopic lung volume reduction coil (LVRC) treatment is an option for selected patients with severe emphysema. This study was conducted to determine the incidence of bleeding complications after LVRC treatment, to identify risk factors and to discuss treatment options in cases of hemoptysis which does not resolve spontaneously. MethodsRetrospective observational study conducted in the Department of Respiratory Medicine at the University Medical Center Hamburg-Eppendorf in all subjects in whom LVRC treatment was performed between April 1, 2012 and September 30, 2015. ResultsDuring the study period, 101 LVRC procedures were performed in 62 subjects. Early post-procedural bleeding was encountered in 65.3% of cases. Hemoptysis was significantly more likely to occur in patients receiving acetylsalicylic acid (P=0.005). Hemoptysis resolved spontaneously in 98.5% of cases. In the one case (1.5%) with persistent hemoptysis, bronchial artery embolization was successful in terminating bleeding. Hospital stay was significantly prolonged in subjects with hemoptysis (P=0.01). No significant differences were found between subjects with or without hemoptysis in terms of chronic obstructive pulmonary disease exacerbations within four weeks after LVRC treatment (P=0.18). Late bleeding complications were observed in 3 subjects (3.0%). In 2 of these cases, bronchial artery embolization was performed successfully terminating the bleeding. ConclusionsSelf-limiting low volume bleeding is a common finding in the first days after LVRC treatment. However, persistent bleeding may occur in the early post-procedural phase and late after LVRC treatment. In these cases, bronchial artery embolization was a feasible and successful approach to terminating bleeding.

Bénéfice attendu du curage ganglionnaire et de l’exérèse des vésicules séminales pour diminuer la toxicité de la radiothérapie des tumeurs prostatiques de haut risque

PurposeIn case of pelvic lymph node and seminal vesicle dissection followed by prostate cancer intensity-modulated radiotherapy, the objective of the study was to evaluate the dosimetric benefit of reducing the target volume. Patients and methodsA total of 25 patients with high-risk prostate cancer had surgery first followed by intensity-modulated radiotherapy and androgen deprivation. Four treatment planning were simulated for each patient, based on two CT scans performed before and after surgery. The target volumes were: prostate–seminal vesicles–lymph nodes, prostate–lymph nodes, prostate–seminal vesicles and prostate only. The total dose was 46Gy in the seminal vesicles and lymph nodes, and 80Gy in the prostate. ResultsCompared to prostate target volume only, the addition of seminal vesicles and lymph nodes multiplied by a factor of 1.6 and 6.5 the target volume, respectively. Decreasing the target volume from prostate–seminal vesicles–lymph nodes to prostate–seminal vesicles, to prostate only decreased the rectal wall mean dose from 49Gy to 42Gy, to 36Gy, and the risk of late rectal bleeding from 4.4% to 3.2%, to 2.4% (P<0.05), respectively. The bladder wall mean dose decreased from 51Gy to 40Gy, to 35Gy (P<0,05), respectively. Not irradiating the lymph nodes decreased the absolute risk of diarrhea by 11%. ConclusionLymph node and seminal vesicle dissection before prostate cancer intensity-modulated radiotherapy allows decreasing moderately the risk of digestive toxicity.

PTU-033 Endoscopic Mucosal Resection of Adenomas and Sessile Serrated Polyps, is there a Difference in Complication Rates?

Introduction Introduction: within a regional, DGH based, EMR service, we evaluated whether there is a difference in the complication rate of EMR of adenomas and SSA/P’s. Methods Method: from January 2007 to February 2016 we prospectively collected data for a single endoscopist (a consultant gastroenterologist, within our institution), for EMR of all large (>19mm) non-pedunculated polyps. A standard EMR technique was used in all patients, a lifting solution consisting of colloid, methylene blue and adrenaline was injected into the submucosal plane. Appropriately lifting lesions were removed with the use of diathermy through a range of standard snare’s. A CONMED diathermy unit using Endocut setting was used for all EMR’s. Lesions were removed either en bloc or piecemeal dependent upon the safety of either resection technique. Following snare resection any residual polyp tissue was treated with APC. Following uncomplicated EMR’s patients were discharged home with two follow up telephone interviews with a sister in the endoscopy unit scheduled for day 1 and 14 post procedure assessing for complications. Adverse events recorded included perforation, late bleeding or admission. A “site check” was routinely performed at 3 months and if clear at 12 months following the EMR, to assess for recurrence. Histological analysis was carried out by a GI pathologist at our hospital, sessile serrated lesions were classified as per the WHO (2010) classification: 1 SSA/P’s without cytological dysplasia, SSA/P’s with cytological dysplasia, traditional serrated adenomas and hyperplastic polyps. Results A single endoscopist attempted 386 adenoma resections, completing 379 of these. 3 (0.8%) perforations were diagnosed. 20 (5.2%) late bleeds occurred in the adenoma group, 12 (3.1%) of patients with late bleeding required admission. Recurrence in the adenoma group was 10.9% at 12 months(249 patients have completed there 1 year follow up to date). During the same period the same endoscopist attempted the resection of 19 SSP’s. In this group 3 (16.7%) perforations were diagnosed, there was the same number of patients with delayed bleeding but only 2 (11.1%) patients required admission for bleeding. Recurrence of SSP’s at 12 months 0%(5 patients have completed their 1 year follow up colonoscopy to date). Conclusion Though a clear difference in size of the cohorts, our data demonstrates a strikingly higher rate of perforations in the SSP group. We note no significant difference in complication rates was observed in a large prospective, multicentre study of 2000 lesions. 2 References 1 Snover DC, et al . Serrated polyps of the colon and rectum. WHO Classification Tumours of Digestive System. 2010:160–165. 2 Pellise M, et al . EMR for large serrated lesions in comparison with adenomas: a prospective multicentre study of 2000 lesions. Gut online first, January 2016. Disclosure of Interest None Declared

Late postoperative massive bleeding in septorhinoplasty: A prospective study

Background There are various complications that can occur in septorhinoplasty, most of which are related to postoperative failure to achieve the desired aesthetic result. However, there are also many other complications, including postoperative bleeding, which is one of the most common nonaesthetic-related complications. Objective The present study was a prospective analysis involving a total of 750 septorhinoplasty patients, and included individuals who experienced massive bleeding after postoperative day 8. Results The incidence of bleeding was 2% among all patients. One percent of cases with bleeding occurred between postoperative days 8 and 14. None of the patients exhibited an abnormality in preoperative or postoperative coagulation tests. Mean blood loss was approximately 1 unit. In all patients, clots in the nose were cleaned, bleeding was subsequently controlled by placement of a polyvinyl alcohol sponge tampon soaked in adrenalin and tranexamic acid, and intravenous administration of 250 mg tranexamic acid in isotonic saline solution. This treatment was sufficient for all cases. None of the patients expereinced recurrent bleeding nor did they require a blood transfusion. Conclusion Late bleeding in septorhinoplasty is rare. It may be prevented by completely filling the nasal cavity so that there is no dead space between the septal mucosal membranes and the drainage opening. If bleeding occurs, it can be treated by placement of a tampon soaked in adrenalin and tranexamic acid plus intravenous administration of 250 mg tranexamic acid.

SU‐D‐204‐06: Integration of Machine Learning and Bioinformatics Methods to Analyze Genome‐Wide Association Study Data for Rectal Bleeding and Erectile Dysfunction Following Radiotherapy in Prostate Cancer

Purpose:We investigated whether integration of machine learning and bioinformatics techniques on genome‐wide association study (GWAS) data can improve the performance of predictive models in predicting the risk of developing radiation‐induced late rectal bleeding and erectile dysfunction in prostate cancer patients.Methods:We analyzed a GWAS dataset generated from 385 prostate cancer patients treated with radiotherapy. Using genotype information from these patients, we designed a machine learning‐based predictive model of late radiation‐induced toxicities: rectal bleeding and erectile dysfunction. The model building process was performed using 2/3 of samples (training) and the predictive model was tested with 1/3 of samples (validation). To identify important single nucleotide polymorphisms (SNPs), we computed the SNP importance score, resulting from our random forest regression model. We performed gene ontology (GO) enrichment analysis for nearby genes of the important SNPs.Results:After univariate analysis on the training dataset, we filtered out many SNPs with p&gt;0.001, resulting in 749 and 367 SNPs that were used in the model building process for rectal bleeding and erectile dysfunction, respectively. On the validation dataset, our random forest regression model achieved the area under the curve (AUC)=0.70 and 0.62 for rectal bleeding and erectile dysfunction, respectively. We performed GO enrichment analysis for the top 25%, 50%, 75%, and 100% SNPs out of the select SNPs in the univariate analysis. When we used the top 50% SNPs, more plausible biological processes were obtained for both toxicities. An additional test with the top 50% SNPs improved predictive power with AUC=0.71 and 0.65 for rectal bleeding and erectile dysfunction. A better performance was achieved with AUC=0.67 when age and androgen deprivation therapy were added to the model for erectile dysfunction.Conclusion:Our approach that combines machine learning and bioinformatics techniques enabled designing better models and identifying more plausible biological processes associated with the outcomes.

Normal tissue complication probability (NTCP) models for late rectal bleeding, stool frequency and fecal incontinence after radiotherapy in prostate cancer patients

Background and purposeCurative radiotherapy for prostate cancer may lead to anorectal side effects, including rectal bleeding, fecal incontinence, increased stool frequency and rectal pain. The main objective of this study was to develop multivariable NTCP models for these side effects. Material and methodsThe study sample was composed of 262 patients with localized or locally advanced prostate cancer (stage T1–3). Anorectal toxicity was prospectively assessed using a standardized follow-up program. Different anatomical subregions within and around the anorectum were delineated. A LASSO logistic regression analysis was used to analyze dose volume effects on toxicity. ResultsIn the univariable analysis, rectal bleeding, increase in stool frequency and fecal incontinence were significantly associated with a large number of dosimetric parameters. The collinearity between these predictors was high (VIF>5). In the multivariable model, rectal bleeding was associated with the anorectum (V70) and anticoagulant use, fecal incontinence was associated with the external sphincter (V15) and the iliococcygeal muscle (V55). Finally, increase in stool frequency was associated with the iliococcygeal muscle (V45) and the levator ani (V40). No significant associations were found for rectal pain. ConclusionsDifferent anorectal side effects are associated with different anatomical substructures within and around the anorectum. The dosimetric variables associated with these side effects can be used to optimize radiotherapy treatment planning aiming at prevention of specific side effects and to estimate the benefit of new radiation technologies.

Development and Validation of a Prediction Rule for Benefit and Harm of Dual Antiplatelet Therapy Beyond 1 Year After Percutaneous Coronary Intervention.

Dual antiplatelet therapy after percutaneous coronary intervention (PCI) reduces ischemia but increases bleeding. To develop a clinical decision tool to identify patients expected to derive benefit vs harm from continuing thienopyridine beyond 1 year after PCI. Among 11,648 randomized DAPT Study patients from 11 countries (August 2009-May 2014), a prediction rule was derived stratifying patients into groups to distinguish ischemic and bleeding risk 12 to 30 months after PCI. Validation was internal via bootstrap resampling and external among 8136 patients from 36 countries randomized in the PROTECT trial (June 2007-July 2014). Twelve months of open-label thienopyridine plus aspirin, then randomized to 18 months of continued thienopyridine plus aspirin vs placebo plus aspirin. Ischemia (myocardial infarction or stent thrombosis) and bleeding (moderate or severe) 12 to 30 months after PCI. Among DAPT Study patients (derivation cohort; mean age, 61.3 years; women, 25.1%), ischemia occurred in 348 patients (3.0%) and bleeding in 215 (1.8%). Derivation cohort models predicting ischemia and bleeding had c statistics of 0.70 and 0.68, respectively. The prediction rule assigned 1 point each for myocardial infarction at presentation, prior myocardial infarction or PCI, diabetes, stent diameter less than 3 mm, smoking, and paclitaxel-eluting stent; 2 points each for history of congestive heart failure/low ejection fraction and vein graft intervention; -1 point for age 65 to younger than 75 years; and -2 points for age 75 years or older. Among the high score group (score ≥2, n = 5917), continued thienopyridine vs placebo was associated with reduced ischemic events (2.7% vs 5.7%; risk difference [RD], -3.0% [95% CI, -4.1% to -2.0%], P < .001) compared with the low score group (score <2, n = 5731; 1.7% vs 2.3%; RD, -0.7% [95% CI, -1.4% to 0.09%], P = .07; interaction P < .001). Conversely, continued thienopyridine was associated with smaller increases in bleeding among the high score group (1.8% vs 1.4%; RD, 0.4% [95% CI, -0.3% to 1.0%], P = .26) compared with the low score group (3.0% vs 1.4%; RD, 1.5% [95% CI, 0.8% to 2.3%], P < .001; interaction P = .02). Among PROTECT patients (validation cohort; mean age, 62 years; women, 23.7%), ischemia occurred in 79 patients (1.0%) and bleeding in 37 (0.5%), with a c statistic of 0.64 for ischemia and 0.64 for bleeding. In this cohort, the high-score patients (n = 2848) had increased ischemic events compared with the low-score patients and no significant difference in bleeding. Among patients not sustaining major bleeding or ischemic events 1 year after PCI, a prediction rule assessing late ischemic and bleeding risks to inform dual antiplatelet therapy duration showed modest accuracy in derivation and validation cohorts. This rule requires further prospective evaluation to assess potential effects on patient care, as well as validation in other cohorts. clinicaltrials.gov Identifier: NCT00977938.