Machine learning algorithm improves the detection of NASH (NAS-based) and at-risk NASH: A development and validation study.

BACKGROUND AND AIMS: Detecting NASH remains challenging, while at-risk NASH (steatohepatitis and F≥ 2) tends to progress and is of interest for drug development and clinical application. We developed prediction models by supervised machine learning techniques, with clinical data and biomarkers to stage and grade patients with NAFLD. APPROACH AND RESULTS: Learning data were collected in the Liver Investigation: Testing Marker Utility in Steatohepatitis metacohort (966 biopsy-proven NAFLD adults), staged and graded according to NASH CRN. Conditions of interest were the clinical trial definition of NASH (NAS ≥ 4;53%), at-risk NASH (NASH with F ≥ 2;35%), significant (F ≥ 2;47%), and advanced fibrosis (F ≥ 3;28%). Thirty-five predictors were included. Missing data were handled by multiple imputations. Data were randomly split into training/validation (75/25) sets. A gradient boosting machine was applied to develop 2 models for each condition: clinical versus extended (clinical and biomarkers). Two variants of the NASH and at-risk NASH models were constructed: direct and composite models.Clinical gradient boosting machine models for steatosis/inflammation/ballooning had AUCs of 0.94/0.79/0.72. There were no improvements when biomarkers were included. The direct NASH model produced AUCs (clinical/extended) of 0.61/0.65. The composite NASH model performed significantly better (0.71) for both variants. The composite at-risk NASH model had an AUC of 0.83 (clinical and extended), an improvement over the direct model. Significant fibrosis models had AUCs (clinical/extended) of 0.76/0.78. The extended advanced fibrosis model (0.86) performed significantly better than the clinical version (0.82). CONCLUSIONS: Detection of NASH and at-risk NASH can be improved by constructing independent machine learning models for each component, using only clinical predictors. Adding biomarkers only improved the accuracy of fibrosis.

Physical Activity and Dietary Composition Relate to Differences in Gut Microbial Patterns in a Multi-Ethnic Cohort-The HELIUS Study.

Physical activity (PA) at recommended levels contributes to the prevention of non-communicable diseases, such as atherosclerotic cardiovascular disease (asCVD) and type 2 diabetes mellitus (T2DM). Since the composition of the gut microbiota is strongly intertwined with dietary intake, the specific effect of exercise on the gut microbiota is not known. Moreover, multiple other factors, such as ethnicity, influence the composition of the gut microbiota, and this may be derived by distinct diet as well as PA patterns. Here we aim to untangle the associations between PA and the gut microbiota in a sample (n = 1334) from the Healthy Life In an Urban Setting (HELIUS) multi-ethnic cohort. The associations of different food groups and gut microbiota were also analyzed. PA was monitored using subjective (n = 1309) and objective (n = 162) methods, and dietary intake was assessed with ethnic-specific food frequency questionnaire (FFQ). The gut microbiota was profiled using 16S rRNA gene amplicon sequencing, and the functional composition was generated with the Phylogenetic Investigation of Communities by Reconstruction of Unobserved States (PICRUSt2). Associations were assessed using multivariable and machine learning models. In this cohort, a distinct gut microbiota composition was associated with meeting the Dutch PA norm as well as with dietary intake, e.g., grains. PA related parameters such as muscle strength and calf circumference correlated with gut microbiota diversity. Furthermore, gut microbial functionality differed between active and sedentary groups. Differential representation of ethnicities in active and sedentary groups in both monitor methods hampered the detection of ethnic-specific effects. In conclusion, both PA and dietary intake were associated with gut microbiota composition in our multi-ethnic cohort. Future studies should further elucidate the role of ethnicity and diet in this association.

SOURCE: Prediction Models for Overall Survival in Patients With Metastatic and Potentially Curable Esophageal and Gastric Cancer.

BACKGROUND: Personalized prediction of treatment outcomes can aid patients with cancer when deciding on treatment options. Existing prediction models for esophageal and gastric cancer, however, have mostly been developed for survival prediction after surgery (ie, when treatment has already been completed). Furthermore, prediction models for patients with metastatic cancer are scarce. The aim of this study was to develop prediction models of overall survival at diagnosis for patients with potentially curable and metastatic esophageal and gastric cancer (the SOURCE study). METHODS: Data from 13,080 patients with esophageal or gastric cancer diagnosed in 2015 through 2018 were retrieved from the prospective Netherlands Cancer Registry. Four Cox proportional hazards regression models were created for patients with potentially curable and metastatic esophageal or gastric cancer. Predictors, including treatment type, were selected using the Akaike information criterion. The models were validated with temporal cross-validation on their C-index and calibration. RESULTS: The validated model's C-index was 0.78 for potentially curable gastric cancer and 0.80 for potentially curable esophageal cancer. For the metastatic models, the c-indices were 0.72 and 0.73 for esophageal and gastric cancer, respectively. The 95% confidence interval of the calibration intercepts and slopes contain the values 0 and 1, respectively. CONCLUSIONS: The SOURCE prediction models show fair to good c-indices and an overall good calibration. The models are the first in esophageal and gastric cancer to predict survival at diagnosis for a variety of treatments. Future research is needed to demonstrate their value for shared decision-making in clinical practice.

Accuracy of cytokeratin 18 (M30 and M65) in detecting non-alcoholic steatohepatitis and fibrosis: A systematic review and meta-analysis.

INTRODUCTION: Association between elevated cytokeratin 18 (CK-18) levels and hepatocyte death has made circulating CK-18 a candidate biomarker to differentiate non-alcoholic fatty liver from non-alcoholic steatohepatitis (NASH). Yet studies produced variable diagnostic performance. We aimed to provide summary estimates with increased precision for the accuracy of CK-18 (M30, M65) in detecting NASH and fibrosis among non-alcoholic fatty liver disease (NAFLD) adults. METHODS: We searched five databases to retrieve studies evaluating CK-18 against a liver biopsy in NAFLD adults. Reference screening, data extraction and quality assessment (QUADAS-2) were independently conducted by two authors. Meta-analyses were performed for five groups based on the CK-18 antigens and target conditions, using one of two methods: linear mixed-effects multiple thresholds model or bivariate logit-normal random-effects model. RESULTS: We included 41 studies, with data on 5,815 participants. A wide range of disease prevalence was observed. No study reported a pre-defined cut-off. Thirty of 41 studies provided sufficient data for inclusion in any of the meta-analyses. Summary AUC [95% CI] were: 0.75 [0.69-0.82] (M30) and 0.82 [0.69-0.91] (M65) for NASH; 0.73 [0.57-0.85] (M30) for fibrotic NASH; 0.68 (M30) for significant (F2-4) fibrosis; and 0.75 (M30) for advanced (F3-4) fibrosis. Thirteen studies used CK-18 as a component of a multimarker model. CONCLUSIONS: For M30 we found lower diagnostic accuracy to detect NASH compared to previous meta-analyses, indicating a limited ability to act as a stand-alone test, with better performance for M65. Additional external validation studies are needed to obtain credible estimates of the diagnostic accuracy of multimarker models.

Interferon Gamma-Induced Protein (IP-10) as Potential Biomarker for Cancer-Related-Fatigue: Results from a 6-month Randomized Controlled Trial.

We examined if serum concentrations Interferon gamma-induced protein (IP-10) is a potential clinical biomarker for cancer-related-fatigue (CRF). Fatigue scores and IP-10 concentrations were measured from curatively treated fatigued cancer patients randomized to either cognitive behavioral therapy (CBT, n = 26) or waiting-list (WL, n = 13). No correlation was found between baseline IP-10 level and fatigue severity and no significant differences in IP-10 serum levels were observed between fatigued and matched non-fatigued patients (n = 22). Relative changes in IP-10 concentrations from baseline to six-month follow-up were not significantly different between the CBT and WL conditions. In this study, IP-10 showed low potential as clinical CRF biomarker. TRIAL REGISTRATION: This study is registered at ClinicalTrials.gov (NCT01096641).

Volatile organic compounds in exhaled breath are independent of systemic inflammatory syndrome caused by intravenous lipopolysaccharide infusion in humans: results from an experiment in healthy volunteers.

Systemic inflammatory response syndrome (SIRS) is observed during critical illness in most patients. It is defined by a clinical definition. The composition of volatile organic compounds (VOCs) in exhaled breath may change during SIRS and may thus serve as a diagnostic tool. We investigated whether exhaled breath VOCs can serve as biomarker for SIRS in a human model of endotoxemia. Eighteen healthy volunteers received 2 ng Eschericia coli lipopolysaccharide (LPS) kg-1 body weight intravenously. Venous blood and exhaled breath were collected before infusion of LPS and every 2 h thereafter, up to 8 h after infusion. The interleukin (IL)-6 concentration was measured in plasma. VOCs in the exhaled breath were measured by gas chromatography and mass spectrometry. A mixed effects model was fitted to examine the relation between the measured compounds in exhaled breath and time after LPS infusion or IL-6 levels in plasma. Partially-least squares discriminant analysis (PLS-DA) was used to investigate whether we could discriminate between samples collected before and after LPS infusion. The exhaled concentrations of 3-methyl-pentane, 4-methyl-pentanol, 1-hexanol, 2,4-dimethyl-heptane, decane and one unknown compound changed after LPS infusion. However, the false-discovery rate was 43% for the total set of 52 compounds that were present in all samples. Of these VOCs only the unknown compound was associated with systemic levels of IL-6. The PLS-DA algorithm resulted in a moderate discriminatory accuracy. SIRS induced by endotoxemia in human volunteers resulted in minor changes in exhaled VOCs. We therefore conclude that LPS infusion in healthy volunteers does not induce metabolic effects that can be detected through VOC analysis of the exhaled breath. This trial is registered at the Dutch Trial Register: NTR4455.

Facial asymmetry in head and neck rhabdomyosarcoma survivors.

INTRODUCTION: Radiotherapy is essential for achieving and maintaining local control in head and neck rhabdomyosarcoma (HNRMS) patients. However, radiotherapy may cause outgrowth disturbances of facial bone and soft tissue, resulting in facial asymmetry. The aim of this study was to develop a method to visualize and measure facial asymmetry in HNRMS survivors using three-dimensional (3D) imaging techniques. METHODS: Facial deformity was evaluated in a multidisciplinary clinical assessment of 75 HNRMS survivors, treated with external beam radiotherapy (EBRT, n = 26) or Ablative surgery, MOulage brachytherapy, and REconstruction (AMORE, n = 49). Individual facial asymmetry was measured using 3D photogrammetry and expressed in a raw asymmetry index and a normalized sex-age-ethnicity-matched asymmetry signature weight. Facial asymmetry was also compared between British and Dutch controls and between survivors and their matched controls. RESULTS: Facial asymmetry was more pronounced with increasing age (P < 0.01) in British controls compared with Dutch controls (P = 0.04). Survivors developed more facial asymmetry than matched controls (P < 0.001). The clinical assessment of facial deformity correlated with the raw asymmetry index (r = 0.60, P < 0.001). DISCUSSION: 3D imaging can be used for objective measurement of facial asymmetry in HNRMS survivors. The raw asymmetry index correlated with a clinical assessment of facial deformity. Comparisons between treatment groups seemed inappropriate given the differences in facial asymmetry between British and Dutch controls. In future studies, pretreatment images could act as matched controls for posttreatment evaluation.

MIBG scans in patients with stage 4 neuroblastoma reveal two metastatic patterns, one is associated with MYCN amplification and in MYCN-amplified tumours correlates with a better prognosis.

PURPOSE: The aim of this study was to find clinically relevant MIBG-avid metastatic patterns in patients with newly diagnosed stage 4 neuroblastoma. METHODS: Diagnostic (123)I-MIBG scans from 249 patients (123 from a European and 126 from the COG cohort) were assessed for metastatic spread in 14 body segments and the form of the lesions: "focal" (clear margins distinguishable from adjacent background) or "diffuse" (indistinct margins, dispersed throughout the body segment). The total numbers of diffuse and focal lesions were recorded. Patients were then categorized as having lesions exclusively focal, lesions more focal than diffuse, lesions more diffuse than focal, or lesions exclusively diffuse. RESULTS: Diffuse lesions affected a median of seven body segments and focal lesions a median of two body segments (P < 0.001, both cohorts). Patients with a focal pattern had a median of 2 affected body segments and those with a diffuse pattern a median of 11 affected body segments (P < 0.001, both cohorts). Thus, two MIBG-avid metastatic patterns emerged: "limited-focal" and "extensive-diffuse". The median numbers of affected body segments in MYCN-amplified (MNA) tumours were 5 (European cohort) and 4 (COG cohort) compared to 9 and 11, respectively, in single-copy MYCN (MYCNsc) tumours (P < 0.001). Patients with exclusively focal metastases were more likely to have a MNA tumour (60% and 70%, respectively) than patients with the other types of metastases (23% and 28%, respectively; P < 0.001). In a multivariate Cox regression analysis, focal metastases were associated with a better event-free and overall survival than the other types of metastases in patients with MNA tumours in the COG cohort (P < 0.01). CONCLUSION: Two metastatic patterns were found: a "limited and focal" pattern found mainly in patients with MNA neuroblastoma that correlated with prognosis, and an "extensive and diffuse" pattern found mainly in patients with MYCNsc neuroblastoma.

Faster recovery of gastrointestinal transit after laparoscopy and fast-track care in patients undergoing colonic surgery.

BACKGROUND & AIMS: Postoperative ileus is characterized by delayed gastrointestinal (GI) transit and is a major determinant of recovery after colorectal surgery. Both laparoscopic surgery and fast-track multimodal perioperative care have been reported to improve clinical recovery. However, objective measures supporting faster GI recovery are lacking. Therefore, GI transit was measured following open and laparoscopic colorectal surgery with or without fast-track care. METHODS: Patients (n = 93) requiring elective colonic surgery were randomized to laparoscopic or conventional surgery with fast-track multimodal management or standard care, resulting in 4 treatment arms. Gastric emptying and colonic transit were scintigraphically assessed from days 1 to 3 in 78 patients and compared with clinical parameters such as time to tolerance of solid food and/or bowel movement and time until (ready for) discharge. RESULTS: A total of 71 patients without mechanical bowel obstructions or surgical complications requiring intervention were available for analysis. No differences in gastric emptying 24 hours after surgery between the different groups were observed (P = .61). However, the median colonic transit of patients undergoing laparoscopic/fast-track care was significantly faster compared with the laparoscopic/standard, open/fast-track, and open/standard care groups. Multiple linear regression analysis showed that both laparoscopic surgery and fast-track care were significant independent predictive factors of improved colonic transit. Both were associated with significantly faster clinical recovery and shorter time until tolerance of solid food and first bowel movement. CONCLUSIONS: Colonic transit recovers significantly faster after laparoscopic surgery and the fast-track program; laparoscopy and fast-track care lead to faster recovery of GI motility and improve clinical recovery.

Lymph node sampling and taking of blind biopsies are important elements of the surgical staging of early ovarian cancer.

BACKGROUND: The purpose of this study was to determine the effect of lymph node sampling and taking of blind biopsies as part of the surgical staging procedure for early ovarian cancer on disease-free survival (DFS) and overall survival (OS) in patients who received no adjuvant chemotherapy. METHODS: In the EORTC ACTION Trial, 448 patients with early ovarian carcinoma were randomized between November 1990 and March 2000-224 patients to observation and 224 to adjuvant platin-based chemotherapy. Only patients allocated to observation were included for the current study. Analyses were performed in a subgroup of 75 optimally staged patients (group A), 46 patients in whom all staging steps were performed except para-aortic or pelvic lymph node sampling (group B), and 14 patients who fulfilled all staging criteria but in whom no blind peritoneal biopsies were taken (group C). The study group did not differ in stage distribution, cell type, or tumor grade. RESULTS: Significantly improved 5-year DFS (P = 0.03) and 5-year OS (P = 0.01) were found in group A (optimally staged) versus group B (no lymph node sampling). A significant difference was also shown in 5-year DFS (P = 0.02) and 5-year OS (P = 0.003) between group A and group C (no blind biopsies). Recurrences occurred in 11 (14.6%) of 75 patients in group A, 16 (34.8%) of 46 patients in group B, and 5 (35.7%) of 14 in group C. The 5-year DFS in group A was 79% versus 61% and 64% in groups B and C, respectively. The 5-year OS decreased from 89% in group A to 71% in group B and 65% in group C. CONCLUSIONS: In this study, statistically significant differences were found in patients in whom para-aortic and pelvic lymph node sampling and taking of blind peritoneal biopsies were undertaken compared with patients in whom these staging steps had been omitted. These findings support the relevance of lymph node sampling and the taking of blind peritoneal biopsies in the surgical staging of early ovarian cancer.

Optimizing prostate cancer detection: 8 versus 12-core biopsy protocol.

PURPOSE: We compared prostate cancer detection rates achieved using an 8 and 12-core biopsy protocol in a clinical population to determine the significance of additional transition zone sampling on repeat biopsy. MATERIALS AND METHODS: Between September 2004 and September 2007, 269 eligible patients with a clinical suspicion of prostate cancer referred to our department were randomized to an 8-core lateral (group 1) or a 12-core lateral and parasagittal (group 2) transrectal ultrasound guided prostate biopsy protocol. Study inclusion criteria were age dependent increased serum prostate specific antigen (1.25 ng/ml or greater at ages less than 50 years, 1.75 or greater at ages 50 to less than 60 years, 2.25 or greater at ages 60 to less than 70 years and 3.25 or greater at ages 70 years or greater), positive digital rectal examination and/or suspicious transrectal ultrasound. After negative first round biopsy patients underwent 12-core biopsy, including 4 transition zone cores. RESULTS: Nine patients were excluded from analysis because of protocol violation or they did not complete the whole biopsy procedure due to discomfort. The cancer detection rate in groups 1 and 2 did not differ significantly (34.1% or 45 of 132 patients and 38.3% or 49 of 128, respectively, p = 0.48). Detected cancer median Gleason scores were similar in the groups. Of 109 patients who underwent repeat biopsy prostate cancer was detected in 20 (14.4%), of whom 9 had positive cores from the transition zone and 6 had positive biopsies only from the transition zone. CONCLUSIONS: There are no statistically significant differences in the prostate cancer detection rate between 8 and 12-core prostate biopsy protocols. Transition zone biopsies contribute to prostate cancer detection in a repeat biopsy protocol.

A role for the fibrinolytic system in postsurgical adhesion formation.

OBJECTIVE: To look for evidence of a fibrinolytic insufficiency as a cause of adhesion formation. DESIGN: Retrospective and prospective study. SETTING: University medical center. PATIENT(S): Retrospective study: 50 patients undergoing laparoscopy, divided into patients with and without endometriosis. Prospective study: 18 patients undergoing infertility surgery involving a second-look laparoscopy. INTERVENTION(S): During all surgical procedures, adhesions were scored, and peritoneal fluid and plasma were collected. MAIN OUTCOME MEASURE(S): Parameters of the fibrinolytic system were measured to establish a possible relation with the presence and formation of adhesions. RESULT(S): In patients with endometriosis and adhesions, significantly higher peritoneal fluid concentrations were found for plasminogen activator inhibitor-1 (PAI-1), tissue plasminogen activator (tPA), and plasminogen, compared with patients with endometriosis but without adhesions. In the prospective study, initial peritoneal PAI-1 concentrations correlated significantly with the extent of adhesion formation (r(s) = 0.49) and adhesion-improvement scores (r(s) = -0.52). Also, the change in concentration of tPA and fibrinogen from the initial surgical procedure to the second-look laparoscopy correlated significantly with adhesion-improvement scores (DeltatPA: r(s)= 0.50; Deltafibrinogen: r(s) = -0.64). CONCLUSION(S): This first prospective study in humans adds further weight to the hypothesis that adhesions are caused by an insufficiency in peritoneal fibrinolytic activity. Plasminogen activator inhibitor-1 is a potential marker for the identification of patients at risk for developing adhesions.

Detection of cervical intraepithelial neoplasia in women with atypical squamous or glandular cells of undetermined significance cytology: a prospective study.

BACKGROUND: (1) To assess the prevalence of histologically confirmed cervical intraepithelial neoplasia in patients with cervical smears diagnosed as atypical squamous or glandular cells of undetermined significance. (2) To evaluate the role of colposcopy and the presence of human papillomavirus in detecting underlying cervical intraepithelial neoplasia. MATERIALS AND METHODS: In this prospective cohort, 148 women with atypical squamous or glandular cells of undetermined significance were evaluated by colposcopy, histological sampling, and human papillomavirus deoxyribonucleic acid testing. RESULTS: Histological diagnosis of >/= cervical intraepithelial neoplasia II was found in 10/148 women. Women with a histological >/= cervical intraepithelial neoplasia II had a higher prevalence of >/= two abnormal quadrants (90% vs. 38%/= cervical intraepithelial neoplasia II.

Recurrent cervical cancer: detection and prognosis.

BACKGROUND: Only a small proportion of cervical cancer recurrences is detected during routine follow-up. We investigated which percentage of recurrences is detected during follow-up, which diagnostic tools are helpful to detect recurrent disease and which factors are of prognostic significance once recurrent disease has been established in patients treated for cervical cancer stage IB-IVA. METHODS: Characteristics of the primary tumor, characteristics of recurrent disease and follow-up were collected retrospectively from clinical records of 277 patients who achieved a complete remission of at least 3 months after primary treatment for cervical cancer in 1992, 1993 and 1994 in three university hospitals in the Netherlands. RESULTS: Of 277 patients, 47 (17%) developed recurrent disease; this was most often detected after self-referral (45%), and in 32% during routine follow-up. Survival did not differ significantly between these two groups. The presence of symptoms (87%) was the most important first abnormal test result leading to diagnosis of recurrence. In univariate analysis, disease-free interval (DFI) and treatment modality were significant prognostic factors for crude survival of recurrence. However, treatment modality varied considerably and the subgroups were small. Therefore, multivariate analysis was not feasible and clinically valid conclusions could not be drawn. CONCLUSIONS: In only 32% of all cases, recurrence was detected during a scheduled follow-up visit. In the majority of patients, recurrent cervical cancer was detected by symptoms (87%). In recurrent disease, DFI was a prognostic factor for survival.

The role of allopurinol in human liver ischemia/reperfusion injury: a prospective randomized clinical trial.

BACKGROUND/AIMS: To investigate the effect of pretreatment with allopurinol on oxidative stress during reperfusion and the role in liver tissue protection in partial liver resections for colorectal cancer metastases confined to the liver. METHODOLOGY: Prospective, randomized, clinical trial, single center, Leiden University Medical Center, The Netherlands. SUBJECTS: Curative partial liver resection of colorectal metastases in 16 patients with or without allopurinol pretreatment, between June 1992 and February 1994. INTERVENTIONS: Partial liver resections with Pringle maneuver, intravenous allopurinol versus no allopurinol. OUTCOME MEASURES: The effect of allopurinol on liver cell damage caused by ischemia/reperfusion studied by measuring malondialdehyde, glutathione, glutathione disulfide, vitamin C, liver enzymes and blood clotting factors in blood samples. Morbidity and mortality were also evaluated. RESULTS: Pretreatment with allopurinol had no significant effect on any of our study parameters. CONCLUSIONS: Because ischemia/reperfusion damage is little in our study, pretreatment with allopurinol is of no value.

Recurrent cervical cancer: detection and prognosis.

BACKGROUND: Only a small proportion of cervical cancer recurrences is detected during routine follow-up. We investigated which percentage of recurrences is detected during follow-up, which diagnostic tools are helpful to detect recurrent disease and which factors are of prognostic significance once recurrent disease has been established in patients treated for cervical cancer stage IB-IVA. METHODS: Characteristics of the primary tumor, characteristics of recurrent disease and follow-up were collected retrospectively from clinical records of 277 patients who achieved a complete remission of at least 3 months after primary treatment for cervical cancer in 1992, 1993 and 1994 in three university hospitals in the Netherlands. RESULTS: Of 277 patients, 47 (17%) developed recurrent disease; this was most often detected after self-referral (45%), and in 32% during routine follow-up. Survival did not differ significantly between these two groups. The presence of symptoms (87%) was the most important first abnormal test result leading to diagnosis of recurrence. In univariate analysis, disease-free interval (DFI) and treatment modality were significant prognostic factors for crude survival of recurrence. However, treatment modality varied considerably and the subgroups were small. Therefore, multivariate analysis was not feasible and clinically valid conclusions could not be drawn. CONCLUSIONS: In only 32% of all cases, recurrence was detected during a scheduled follow-up visit. In the majority of patients, recurrent cervical cancer was detected by symptoms (87%). In recurrent disease, DFI was a prognostic factor for survival.