Workflow optimisation for multimodal imaging procedures: a case of combined X-ray and MRI-guided TACE.

This study presents a framework for workflow optimisation of multimodal image-guided procedures (MIGP) based on discrete event simulation (DES). A case of a combined X-Ray and magnetic resonance image-guided transarterial chemoembolisation (TACE) is presented to illustrate the application of this method. We used a ranking and selection optimisation algorithm to measure the performance of a number of proposed alternatives to improve a current scenario. A DES model was implemented with detail data collected from 59 TACE procedures and durations of magnetic resonance imaging (MRI) diagnostic procedures usually performed in a common MRI suite. Fourteen alternatives were proposed and assessed to minimise the waiting times and improve workflow. Data analysis observed an average of 20.68 (7.68) min of waiting between angiography and MRI for TACE patients in 71.19% of the cases. Following the optimisation analysis, an alternative was identified to reduce waiting times in angiography suite up to 48.74%. The model helped to understand and detect 'bottlenecks' during multimodal TACE procedures, identifying a better alternative to the current workflow and reducing waiting times. Simulation-based workflow analysis provides a cost-effective way to face some of the challenges of introducing MIGP in clinical radiology, highligthed in this study.

Workflow and intervention times of MR-guided focused ultrasound - Predicting the impact of new techniques.

Magnetic resonance guided focused ultrasound surgery (MRgFUS) has become an attractive, non-invasive treatment for benign and malignant tumours, and offers specific benefits for poorly accessible locations in the liver. However, the presence of the ribcage and the occurrence of liver motion due to respiration limit the applicability MRgFUS. Several techniques are being developed to address these issues or to decrease treatment times in other ways. However, the potential benefit of such improvements has not been quantified. In this research, the detailed workflow of current MRgFUS procedures was determined qualitatively and quantitatively by using observation studies on uterine MRgFUS interventions, and the bottlenecks in MRgFUS were identified. A validated simulation model based on discrete events simulation was developed to quantitatively predict the effect of new technological developments on the intervention duration of MRgFUS on the liver. During the observation studies, the duration and occurrence frequencies of all actions and decisions in the MRgFUS workflow were registered, as were the occurrence frequencies of motion detections and intervention halts. The observation results show that current MRgFUS uterine interventions take on average 213min. Organ motion was detected on average 2.9 times per intervention, of which on average 1.0 actually caused a need for rework. Nevertheless, these motion occurrences and the actions required to continue after their detection consumed on average 11% and up to 29% of the total intervention duration. The simulation results suggest that, depending on the motion occurrence frequency, the addition of new technology to automate currently manual MRgFUS tasks and motion compensation could potentially reduce the intervention durations by 98.4% (from 256h 5min to 4h 4min) in the case of 90% motion occurrence, and with 24% (from 5h 19min to 4h 2min) in the case of no motion. In conclusion, new tools were developed to predict how intervention durations will be affected by future workflow changes and by the introduction of new technology.

Mining Primary Care Electronic Health Records for Automatic Disease Phenotyping: A Transparent Machine Learning Framework.

(1) Background: We aimed to develop a transparent machine-learning (ML) framework to automatically identify patients with a condition from electronic health records (EHRs) via a parsimonious set of features. (2) Methods: We linked multiple sources of EHRs, including 917,496,869 primary care records and 40,656,805 secondary care records and 694,954 records from specialist surgeries between 2002 and 2012, to generate a unique dataset. Then, we treated patient identification as a problem of text classification and proposed a transparent disease-phenotyping framework. This framework comprises a generation of patient representation, feature selection, and optimal phenotyping algorithm development to tackle the imbalanced nature of the data. This framework was extensively evaluated by identifying rheumatoid arthritis (RA) and ankylosing spondylitis (AS). (3) Results: Being applied to the linked dataset of 9657 patients with 1484 cases of rheumatoid arthritis (RA) and 204 cases of ankylosing spondylitis (AS), this framework achieved accuracy and positive predictive values of 86.19% and 88.46%, respectively, for RA and 99.23% and 97.75% for AS, comparable with expert knowledge-driven methods. (4) Conclusions: This framework could potentially be used as an efficient tool for identifying patients with a condition of interest from EHRs, helping clinicians in clinical decision-support process.

EPAC-lung: European pooled analysis of the prognostic value of circulating tumour cells in small cell lung cancer.

BACKGROUND: Circulating tumour cell (CTC) number is an independent prognostic factor in patients with small cell lung cancer (SCLC) but there is no consensus on the CTC threshold for prognostic significance. We undertook a pooled analysis of individual patient data to clinically validate CTC enumeration and threshold for prognostication. METHODS: Four European cancer centres, experienced in CellSearch CTC enumeration for SCLC provided pseudo anonymised data for patients who had undergone pre-treatment CTC count. Data was collated, and Cox regression models, stratified by centre, explored the relationship between CTC count and survival. The added value of incorporating CTCs into clinico-pathological models was investigated using likelihood ratio tests. RESULTS: A total of 367 patient records were evaluated. A one-unit increase in log-transformed CTC counts corresponded to an estimated hazard ratio (HR) of 1.24 (95% CI: 1.19-1.29, P<0.0001) for progression free survival (PFS) and 1.23 (95% CI: 1.18-1.28, P<0.0001) for overall survival (OS). CTC count of ≥15 or ≥50 was significantly associated with an increased risk of progression (CTC ≥15: HR 3.20, 95% CI: 2.50-4.09, P<0.001; CTC ≥50: HR 2.56, 95% CI: 2.01-3.25, P<0.001) and an increased risk of death (CTC ≥15: HR 2.90, 95% CI: 2.28-3.70, P<0.001; CTC ≥50: HR 2.47, 95% CI: 1.95-3.13, P<0.001). There was no significant inter-centre heterogeneity observed. Addition of CTC count to clinico-pathological models as a continuous log-transformed variable, offers further prognostic value (both likelihood ratio P<0.001 for OS and PFS). CONCLUSIONS: Higher pre-treatment CTC counts are a negative independent prognostic factor in SCLC when considered as a continuous variable or dichotomised counts of ≥15 or ≥50. Incorporating CTC counts, as a continuous variable, improves clinic-pathological prognostic models.

Characteristics of Children Prescribed Antipsychotics: Analysis of Routinely Collected Data.

OBJECTIVE: Antipsychotics are licensed for psychosis and are also prescribed for behavior control. This study aims to examine characteristics and outcomes of children prescribed antipsychotics. METHODS: A cohort study using general practice and hospital records linked with education records for 1,488,936 children living in Wales between 1999 and 2015. The characteristics of the children who were prescribed antipsychotics are presented using descriptive statistics and outcomes such as respiratory illness, diabetes, and injury were analyzed using multilevel logistic regression and the prior event rate ratio (PERR). RESULTS: Children with intellectual difficulty/autism were more likely to be prescribed antipsychotics (2.8% have been prescribed an antipsychotic [75% with autism] compared with 0.15% of children without intellectual difficulty). Those with intellectual disabilities/autism were prescribed antipsychotics at a younger age and for a longer period. Antipsychotic use was associated with a higher rate of respiratory illness for all (PERR of hospital admission: 1.55 [95% CI: 1.51-1.598] or increase in rate of 2 per 100 per year in those treated), and for those with intellectual difficulty/autism, there was a higher rate of injury and hospitalized depression. However, among those without intellectual difficulty/autism, there were lower rates of depression (PERR: 0.55 [95% CI: 0.51-0.59]). CONCLUSIONS: This work shows real-world use of antipsychotics and provides information on the rate of possible adverse events in children treated. Antipsychotics are predominantly used for those with intellectual difficulty/autism rather than those with a psychotic diagnosis. There is evidence that rates of respiratory disease, epilepsy, and diabetes are also higher postantipsychotic use for all. In those with intellectual difficulty/autism, hospital-admitted depression and injury are higher postantipsychotic use. The use of antipsychotics for behavioral management is likely to have increased cost implications to the healthcare system.

The clinical utility of circulating tumour cells in patients with small cell lung cancer.

Small cell lung cancer (SCLC) accounts for 15% of lung cancer diagnosed worldwide. It is aggressive and characterised by early metastatic spread with rapid development of chemo resistance such that less than 5% of patients diagnosed survive 5 years. Surgery is rarely performed and failure to identify new effective treatments has been attributed in a large part to lack of good quality tumour biopsies available for translational research. Liquid biopsies provide a minimally invasive alternative to traditional tumour biopsy. Circulating tumour cells (CTCs) are abundant in SCLC and can be enriched and isolated from a venous blood sample. In recent years progress has been made into the molecular characterisation of CTCs and their use to form tumour xenografts in mice for preclinical studies. This review will discuss the current status of the clinical utility of CTCs in patients with SCLC, highlighting their potential application to treatment decision making, drug development in clinical trials and preclinical testing.

Molecular analysis of single circulating tumour cells following long-term storage of clinical samples.

The CellSearch® semiautomated CTC enrichment and staining system has been established as the 'gold standard' for CTC enumeration with CellSearch® CTC counts recognized by the FDA as prognostic for a number of cancers. We and others have gone on to show that molecular analysis of CellSearch® CTCs isolated shortly after CellSearch® enrichment provides another valuable layer of information that has potential clinical utility including predicting response to treatment. Although CellSearch® CTCs can be readily isolated after enrichment, the process of analysing a single CellSearch® patient sample, which may contain many CTCs, is both time-consuming and costly. Here, we describe a simple process that will allow storage of all CellSearch® -enriched cells in glycerol at -20 °C for up to 2 years without any measurable loss in the ability to retrieve single cells or in the genome integrity of the isolated cells. To establish the suitability of long-term glycerol storage for single-cell molecular analysis, we isolated individual CellSearch® -enriched cells by DEPArray™ either shortly after CellSearch® enrichment or following storage of matched enriched cells in glycerol at -20 °C. All isolated cells were subjected to whole-genome amplification (WGA), and the efficacy of single-cell WGA was evaluated by multiplex PCR to generate a Genome Integrity Index (GII). The GII results from 409 single cells obtained from both 'spike-in' controls and clinical samples showed no statistical difference between values obtained pre- and postglycerol storage and that there is no further loss in integrity when DEPArray™-isolated cells are then stored at -80 °C for up to 2 years. In summary, we have established simple yet effective 'stop-off' points along the CTC workflow enabling CTC banking and facilitating selection of suitable samples for intensive analysis once patient outcomes are known.

Molecular analysis of circulating tumor cells identifies distinct copy-number profiles in patients with chemosensitive and chemorefractory small-cell lung cancer.

In most patients with small-cell lung cancer (SCLC)-a metastatic, aggressive disease-the condition is initially chemosensitive but then relapses with acquired chemoresistance. In a minority of patients, however, relapse occurs within 3 months of initial treatment; in these cases, disease is defined as chemorefractory. The molecular mechanisms that differentiate chemosensitive from chemorefractory disease are currently unknown. To identify genetic features that distinguish chemosensitive from chemorefractory disease, we examined copy-number aberrations (CNAs) in circulating tumor cells (CTCs) from pretreatment SCLC blood samples. After analysis of 88 CTCs isolated from 13 patients (training set), we generated a CNA-based classifier that we validated in 18 additional patients (testing set, 112 CTC samples) and in six SCLC patient-derived CTC explant tumors. The classifier correctly assigned 83.3% of the cases as chemorefractory or chemosensitive. Furthermore, a significant difference was observed in progression-free survival (PFS) (Kaplan-Meier P value = 0.0166) between patients designated as chemorefractory or chemosensitive by using the baseline CNA classifier. Notably, CTC CNA profiles obtained at relapse from five patients with initially chemosensitive disease did not switch to a chemorefractory CNA profile, which suggests that the genetic basis for initial chemoresistance differs from that underlying acquired chemoresistance.

Defining Disease Phenotypes in Primary Care Electronic Health Records by a Machine Learning Approach: A Case Study in Identifying Rheumatoid Arthritis.

OBJECTIVES: 1) To use data-driven method to examine clinical codes (risk factors) of a medical condition in primary care electronic health records (EHRs) that can accurately predict a diagnosis of the condition in secondary care EHRs. 2) To develop and validate a disease phenotyping algorithm for rheumatoid arthritis using primary care EHRs. METHODS: This study linked routine primary and secondary care EHRs in Wales, UK. A machine learning based scheme was used to identify patients with rheumatoid arthritis from primary care EHRs via the following steps: i) selection of variables by comparing relative frequencies of Read codes in the primary care dataset associated with disease case compared to non-disease control (disease/non-disease based on the secondary care diagnosis); ii) reduction of predictors/associated variables using a Random Forest method, iii) induction of decision rules from decision tree model. The proposed method was then extensively validated on an independent dataset, and compared for performance with two existing deterministic algorithms for RA which had been developed using expert clinical knowledge. RESULTS: Primary care EHRs were available for 2,238,360 patients over the age of 16 and of these 20,667 were also linked in the secondary care rheumatology clinical system. In the linked dataset, 900 predictors (out of a total of 43,100 variables) in the primary care record were discovered more frequently in those with versus those without RA. These variables were reduced to 37 groups of related clinical codes, which were used to develop a decision tree model. The final algorithm identified 8 predictors related to diagnostic codes for RA, medication codes, such as those for disease modifying anti-rheumatic drugs, and absence of alternative diagnoses such as psoriatic arthritis. The proposed data-driven method performed as well as the expert clinical knowledge based methods. CONCLUSION: Data-driven scheme, such as ensemble machine learning methods, has the potential of identifying the most informative predictors in a cost-effective and rapid way to accurately and reliably classify rheumatoid arthritis or other complex medical conditions in primary care EHRs.

Preclinical feasibility of a technology framework for MRI-guided iliac angioplasty.

PURPOSE: Interventional MRI has significant potential for image guidance of iliac angioplasty and related vascular procedures. A technology framework with in-room image display, control, communication and MRI-guided intervention techniques was designed and tested for its potential to provide safe, fast and efficient MRI-guided angioplasty of the iliac arteries. METHODS: A 1.5-T MRI scanner was adapted for interactive imaging during endovascular procedures using new or modified interventional devices such as guidewires and catheters. A perfused vascular phantom was used for testing. Pre-, intra- and post-procedural visualization and measurement of vascular morphology and flow was implemented. A detailed analysis of X-ray fluoroscopic angiography workflow was conducted and applied. Two interventional radiologists and one physician in training performed 39 procedures. All procedures were timed and analyzed. RESULTS: MRI-guided iliac angioplasty procedures were successfully performed with progressive adaptation of techniques and workflow. The workflow, setup and protocol enabled a reduction in table time for a dedicated MRI-guided procedure to 6 min 33 s with a mean procedure time of 9 min 2 s, comparable to the mean procedure time of 8 min 42 s for the standard X-ray-guided procedure. CONCLUSIONS: MRI-guided iliac vascular interventions were found to be feasible and practical using this framework and optimized workflow. In particular, the real-time flow analysis was found to be helpful for pre- and post-interventional assessments. Design optimization of the catheters and in vivo experiments are required before clinical evaluation.

Comparative ergonomic workflow and user experience analysis of MRI versus fluoroscopy-guided vascular interventions: an iliac angioplasty exemplar case study.

PURPOSE: A methodological framework is introduced to assess and compare a conventional fluoroscopy protocol for peripheral angioplasty with a new magnetic resonant imaging (MRI)-guided protocol. Different scenarios were considered during interventions on a perfused arterial phantom with regard to time-based and cognitive task analysis, user experience and ergonomics. METHODS: Three clinicians with different expertise performed a total of 43 simulated common iliac angioplasties (9 fluoroscopic, 34 MRI-guided) in two blocks of sessions. Six different configurations for MRI guidance were tested in the first block. Four of them were evaluated in the second block and compared to the fluoroscopy protocol. Relevant stages' durations were collected, and interventions were audio-visually recorded from different perspectives. A cued retrospective protocol analysis (CRPA) was undertaken, including personal interviews. In addition, ergonomic constraints in the MRI suite were evaluated. RESULTS: Significant differences were found when comparing the performance between MRI configurations versus fluoroscopy. Two configurations [with times of 8.56 (0.64) and 9.48 (1.13) min] led to reduce procedure time for MRI guidance, comparable to fluoroscopy [8.49 (0.75) min]. The CRPA pointed out the main influential factors for clinical procedure performance. The ergonomic analysis quantified musculoskeletal risks for interventional radiologists when utilising MRI. Several alternatives were suggested to prevent potential low-back injuries. CONCLUSIONS: This work presents a step towards the implementation of efficient operational protocols for MRI-guided procedures based on an integral and multidisciplinary framework, applicable to the assessment of current vascular protocols. The use of first-user perspective raises the possibility of establishing new forms of clinical training and education.