Use of artificial intelligence in discerning the need for prostate biopsy and readiness for clinical practice: a systematic review protocol

BACKGROUND

Variability and inaccuracies in the diagnosis of prostate cancer, and the risk of complications from invasive tests, have been extensively reported in the research literature. To address this, the use of artificial intelligence (AI) has been attracting increased interest in recent years to improve the diagnostic accuracy and objectivity. Although AI literature has reported promising results, further research is needed on the identification of evidence gaps that limit the potential adoption in prostate cancer screening practice.

METHODS

A systematic electronic search strategy will be used to identify peer-reviewed articles published from inception to the date of searches and indexed in CINAHL, IEEE Xplore, MEDLINE, Scopus, and Web of Science Core Collection databases. Registries including Cochrane Central Register of Controlled Trials, ClinicalTrials.gov and International Clinical Trials Registry Platform (ICTRP) will be searched for unpublished studies, and experts were invited to provide suitable references. The research and reporting will be based on Cochrane recommendations and PRISMA guidelines, respectively. The screening and quality assessment of the articles will be conducted by two of the authors independently, and conflicts will be resolved by a third author.

DISCUSSION

This systematic review will summarise the use of AI techniques to predict the need for prostate biopsy based on clinical and demographic indicators, including its diagnostic accuracy and readiness for adoption in clinical practice.

SYSTEMATIC REVIEW REGISTRATION

PROSPERO CRD42022336540.

Systematic Review and Narrative Synthesis of Economic Evaluations of Prostate Cancer Diagnostic Pathways Incorporating Prebiopsy Magnetic Resonance Imaging

Context

Prebiopsy magnetic resonance imaging (MRI) of the prostate has been shown to increase the accuracy of the diagnosis of clinically significant prostate cancer. However, evidence is still evolving about how best to integrate prebiopsy MRI into the diagnostic pathway and for which patients, and whether MRI-based pathways are cost effective.

Objective

This systematic review aimed to assess the evidence for the cost effectiveness of prebiopsy MRI-based prostate cancer diagnostic pathways.

Evidence acquisition

INTERTASC search strategies were adapted and combined with terms for prostate cancer and MRI, and used to search a wide range of databases and registries covering medicine, allied health, clinical trials, and health economics. No limits were set on country, setting, or publication year. Included studies were full economic evaluations of prostate cancer diagnostic pathways with at least one strategy including prebiopsy MRI. Model-based studies were assessed using the Philips framework, and trial-based studies were assessed using the Critical Appraisal Skills Programme checklist.

Evidence synthesis

A total of 6593 records were screened after removing duplicates, and eight full-text papers, reporting on seven studies (two model based) were included in this review. Included studies were judged to have a low-to-moderate risk of bias. All studies reported cost-effectiveness analyses based in high-income countries but had significant heterogeneity in diagnostic strategies, patient populations, treatment strategies, and model characteristics. Prebiopsy MRI-based pathways were cost effective compared with pathways relying on ultrasound-guided biopsy in all eight studies.

Conclusions

Incorporation of prebiopsy MRI into prostate cancer diagnostic pathways is likely to be more cost effective in than that into pathways relying on prostate-specific antigen and ultrasound-guided biopsy. The optimal prostate cancer diagnostic pathway design and method of integrating prebiopsy MRI are not yet known. Variations between health care systems and diagnostic approaches necessitate further evaluation for a particular country or setting to know how best to apply prebiopsy MRI.

Patient summary

In this report, we looked at studies that measured the health care costs and benefits and harms to patients of using prostate magnetic resonance imaging (MRI), to decide whether men need a prostate biopsy for possible prostate cancer. We found that using prostate MRI before biopsy is likely to be less costly for health care services and probably has better outcomes for patients being investigated for prostate cancer. It is still unclear what the best way to use prostate MRI is.

Time intervals and patient-level factors in oral cancer diagnostic pathways: An application of the WHO framework in India

BACKGROUND

Oral cancer, a leading cancer-site in India, is often detected at advanced stages. We evaluated the time intervals from first symptom to help-seeking and diagnosis among oral cancer patients.

METHODOLOGY

In this cross-sectional study, we recruited 226 consecutive oral cancer patients (mean age ( ± SD) 51.9 years ( ± 10.9); 81.9% men; 70.3% advanced stage) registered for diagnosis and treatment, between 2019 and 2021 at a cancer care centre in South India. We used WHO framework and previously standardized tools to record time intervals (appraisal, help-seeking and diagnostic) and baseline characteristics. We utilized multivariable logistic regression models to test the associations between 'prolonged (i.e., over 1 month) time intervals') and patient-level factors to estimate odds ratios (ORs) with 95% confidence intervals (CIs).

RESULTS

Over a half of patients presented with prolonged appraisal (60%) and help-seeking intervals (57%), and a third (34%) reported prolonged diagnostic interval. Patients with no formal education, no routine healthcare visits, no self-reported risk factors, and those who did not perceive initial symptoms to be serious were 2-4 times more likely to have prolonged appraisal and help-seeking than the rest. High travel costs and self-decision for visiting healthcare facility prolonged help-seeking. Diagnostic interval was prolonged only among women OR= 2.7 (95% CI: 1.2-6.1)) and in patients whose first doctor's opinion was 'nothing to worry' OR (=7.3 (95% CI: 2.6-20.5)). 'Correct knowledge of cancer' shortened appraisal and help-seeking intervals and 'incorrect knowledge and negative beliefs' prolonged diagnostic interval.

CONCLUSION

Our findings highlight that interventions targeting sociocultural and economic determinants, symptom awareness, sensitizing persons at risk (especially women) and primary care providers might reduce overall time to diagnosis. Further, patients without any known risk factors for oral cancer might be at-risk for prolonged appraisal interval. These might help inform 'pull' strategies for cancer control in India and similar settings.

Superfast Magnetic Resonance Imaging-based Diagnostic Pathway for Prostate Cancer

We describe a <36-h superfast diagnostic pathway for men at risk of prostate cancer (PCa) that was initiated in our centre in March 2022. Patients are scheduled to undergo a repeat prostate-specific antigen blood test, magnetic resonance imaging, a urology consultation, and, if indicated, prostate biopsies in a single morning. The histopathology report is available the next day, after which the biopsy results and treatment options are discussed via a telephone consultation. The project has included 122 patients so far. With a reduction to only one hospital visit per patient and just five appointments (4%) cancelled so far, this timely pathway seems to be efficient from a patient perspective. In addition, reducing the waiting time until histopathology diagnosis could decrease the anxiety and depression that patients may experience during the diagnostic workup for PCa. Therefore, we believe that this fast-track diagnostic pathway could be incorporated in the future European standard of care, bringing PCa care in line with other malignancies such as breast cancer.

Patient summary

We describe a superfast diagnostic pathway for men at risk of prostate cancer. So far, this strategy seems to be an efficient and appropriate way to shorten time to diagnosis and to reduce the number of hospital visits for patients.

Predictors of treatment initiation and mapping the cancer diagnostic pathway: A retrospective observational cohort study of patients with metastatic non-small cell lung cancer

BACKGROUND

Health-care providers in the US revealed that a substantial proportion of mNSCLC patients do not receive any first-line therapy and the biggest gaps in care are time inefficiencies in the diagnostic process. The goal of this study was to determine whether such gaps are found in Israel where healthcare is universal and participation in a medical insurance plan is free and compulsory.

METHODS

We conducted a retrospective, observational cohort study using the computerized data of Maccabi Healthcare Services, a 2.5 million-member state-mandated health-service. Patients with mNSCLC diagnosed between 2017 and 2018 were followed until December 2019.

RESULTS

Among 434 patients (62% male, mean age 68 y, 74% adenocarcinoma), 345 (79%) initiated first-line treatment. Compared to treated, untreated patients (n = 89) were more likely to be older (mean [SD]=71 years [10] vs. 67 [10], p < 0.001), have a higher co-morbidity index (5.6 ([4.4] vs. 4.0 [3.4], p < 0.001), smokers (84% vs. 66%, p = 0.001), and require hospitalization in the year prior to diagnosis (80% vs 61%, p = 0.002). There was no difference in socioeconomic status. Time from first symptom to imaging was longer for untreated than treated patients (6.51 months [4.24, 7.33] vs 3.48 months [2.76, 4.34] respectively, p = 0.22). Predictors of treatment initiation included age< 70 years, non-smokers, EGFR testing performed, ECOG performance status 0-1 and shorter wait from first symptom to imaging. Median time from first symptom to initiation of 1 L, was 7.76 months (6.51-8.75).

CONCLUSION

The proportion of untreated mNSCLC patients are comparable to those reported in the US; we did not find health disparities between socioeconomic levels. Our data suggest that the main barrier to effective diagnostic process is the wait between symptom complaint and imaging.

Modelling lung cancer diagnostic pathways using discrete event simulation

The United Kingdom has one of the poorest lung cancer survival rates in Europe. In this study, to help design and evaluate a single lung cancer pathway (SCP) for Wales, existing diagnostic pathways and processes have been mapped and then modelled with a discrete event simulation. The validated models have been used to provide key performance indicators and to examine different diagnostic testing strategies. Under the current diagnostic pathways, the mean time to treatment was 72 days for surgery patients, 56 days for chemotherapy patients, and 61 days for radiotherapy patients. Our research demonstrated that by ensuring that the patient attends their first outpatient appointment within 7 days and streamlining the diagnostic tests would have the potential to remove approximately 11 days from the current lung cancer pathway resulting in a 21% increase in patients receiving treatment within the Welsh Government set target of 62 days.

Tumefactive multiple sclerosis versus high-grade glioma: A diagnostic dilemma

Background:

Tumefactive demyelinating lesions (TDLs) share similar clinical features and MRI characteristics with high-grade glioma (HGG). This study develops an approach to navigating this diagnostic dilemma, with significant treatment implications as the management of both entities is drastically different.

Methods:

A retrospective analysis of 41 TDLs and 91 HGG with respect to demographics, presentation, and classical MRI characteristics was performed. A diagnostic pathway was then developed to help diagnose TDLs based on whole neuraxis MRI and cerebrospinal fluid (CSF) examination.

Results:

The diagnosis of TDL is more likely than HGG in younger females who present with subacute or chronic symptoms. MRI characteristics favoring TDL over HGG include smaller size, open rim enhancement, little or no associated edema or mass effect, and the presence of a T2 hypointense rim. MRI of the whole neuraxis for detection of other lesions typical of multiple sclerosis (MS), in combination with a lumbar puncture (LP) showing positive CSF-specific oligoclonal bands (OCB), was positive in 90% of the TDL cohort.

Conclusion:

The diagnostic pathway, proposed on the basis of specific clinicoradiological features, should be followed in patients with suspected TDL. If MRI demonstrates other lesions typical of MS and LP demonstrates positive CSF-specific OCBs, then patients should undergo a short course of IV steroids to look for clinical improvement. Patients who continue to deteriorate, do not demonstrate other lesions on MRI or where the LP is negative for CSF-specific OCB, should be considered for biopsy if safe to do so. This pathway will give the patients the best chance at neurological preservation.

Cutoff Values of Prostate Imaging Reporting and Data System Version 2.1 Score in Men With Prostate-specific Antigen Level 4 to 10 ng/mL: Importance of Lesion Location

INTRODUCTION

Multiparametric magnetic resonance imaging (mpMRI) has been shown to have a good performance in predicting cancer among patients with a prostate-specific antigen (PSA) level of 4 to 10 ng/mL. However, lesion location on mpMRI has never been separately considered.

PATIENTS AND METHODS

Patients with PSA level of 4 to 10 ng/mL were prospectively enrolled and underwent transrectal ultrasound-guided prostate biopsy. Patient information was collected, and logistic regression analysis was performed to determine the predictive factors of clinically significant prostate cancer (csPCa). Patients were grouped by lesion location to determine the Prostate Imaging Reporting and Data System (PI-RADS) v2.1 cutoff value in predicting csPCa.

RESULTS

Among 222 patients, 121 were diagnosed with PCa and 92 had csPCa. Age, prostate volume, PSA density, location (peripheral zone, csPCa only), and PI-RADS v2.1 score were correlated with PCa and csPCa, and PI-RADS v2.1 score was the best predictor. A PI-RADS v2.1 score of 4 was the best cutoff value for predicting csPCa in patients with lesions only in the transitional zone with respect to the Youden index (0.5896) and negative predictive value (93.10%) with acceptable sensitivity (81.82%) and specificity (77.14%). An adjustment of the cutoff value to 3 for lesions in the peripheral zone would increase the negative predictive value (92.00%) and decrease the false negative rate (2.90%) with an acceptable sensitivity (97.10%) and specificity (30.67%).

CONCLUSION

PI-RADS v2.1 score is an effective predictor of csPCa in patients with PSA levels of 4 to 10 ng/mL. Patients with transitional zone or peripheral zone lesions should undergo biopsy if the PI-RADS v2.1 score is ≥ 4 or ≥ 3, respectively.

Parent's perspectives of the pathway to diagnosis of childhood cancer: a matter of diagnostic triage

BACKGROUND

Early diagnosis is crucial for the treatment of childhood cancer as it in some cases can prevent progression of disease and improve prognoses. However, childhood cancer can be difficult to diagnose and barriers to early diagnosis are multifactorial. New knowledge about factors influencing the pathway to diagnosis contribute to a deeper understanding of the mechanisms that influence this time span. Qualitative research in the field is sparse but can be expected to lead to additional useful insights that could contribute to efforts shorten time to diagnosis. The purpose of this study was to explore parents' experiences of the pathway to diagnosis in the time between their noticing bodily or behavioural changes and their child's diagnosis.

METHODS

The study is a qualitative interview study carried out in large Danish hospital. Thirty-two interviews with a total of 46 parents of children with cancer were included for analysis. The children were diagnosed with haematological cancers (n = 17), solid tumours (n = 9) or brain tumours (n = 6). Data were analysed applying the theoretical model of pathways to treatment and an inductive-deductive approach. A revised 'diagnostic triage' model was developed and validated by member checking.

RESULTS

The pathway to diagnosis was influenced by various factors which we present as consistent parts of a new diagnostic triage model. Each factor impacts the level of urgency assigned to bodily and behavioural changes by parents, general practitioners and specialists. The model of diagnostic triage was developed and validated to understand mechanisms influencing time from the point parents notice changes in their child to diagnosis. The model identifies dynamic movement between parental triage in everyday life and professional triage in a healthcare system, both affecting appraisal and case escalation according to: 1) the nature of bodily and behavioural changes, 2) parental intuition, 3) social relations, 4) professional-child-parent interaction, and 5) specialist-child-parent interaction.

CONCLUSIONS

Diagnostic triage is a model which explains mechanisms that shape the pathway to diagnosis. It is a contribution aimed at supporting the clinical diagnostic process, that ultimately could ensure more timely testing, referral and diagnosis, and also a novel theoretical framework for future research on diagnostic pathways.

Deep gluteal syndrome is defined as a non-discogenic sciatic nerve disorder with entrapment in the deep gluteal space: a systematic review

PURPOSE

Clinicians are not confident in diagnosing deep gluteal syndrome (DGS) because of the ambiguity of the DGS disease definition and DGS diagnostic pathway. The purpose of this systematic review was to identify the DGS disease definition, and also to define a general DGS diagnostic pathway.

METHODS

A systematic search was performed using four electronic databases: PubMed, MEDLINE, EMBASE, and Google Scholar. In eligibility criteria, studies in which cases were explicitly diagnosed with DGS were included, whereas review articles and commentary papers were excluded. Data are presented descriptively.

RESULTS

The initial literature search yielded 359 articles, of which 14 studies met the eligibility criteria, pooling 853 patients with clinically diagnosed with DGS. In this review, it was discovered that the DGS disease definition was composed of three parts: (1) non-discogenic, (2) sciatic nerve disorder, and (3) nerve entrapment in the deep gluteal space. In the diagnosis of DGS, we found five diagnostic procedures: (1) history taking, (2) physical examination, (3) imaging tests, (4) response-to-injection, and (5) nerve-specific tests (electromyography). History taking (e.g. posterior hip pain, radicular pain, and difficulty sitting for 30 min), physical examination (e.g. tenderness in deep gluteal space, pertinent positive results with seated piriformis test, and positive Pace sign), and imaging tests (e.g. pelvic radiographs, spine and pelvic magnetic resonance imaging (MRI)) were generally performed in cases clinically diagnosed with DGS.

CONCLUSION

Existing literature suggests the DGS disease definition as being a non-discogenic sciatic nerve disorder with entrapment in the deep gluteal space. Also, the general diagnostic pathway for DGS was composed of history taking (posterior hip pain, radicular pain, and difficulty sitting for 30 min), physical examination (tenderness in deep gluteal space, positive seated piriformis test, and positive Pace sign), and imaging tests (pelvic radiographs, pelvic MRI, and spine MRI). This review helps clinicians diagnose DGS with more confidence.

LEVEL OF EVIDENCE

IV.

Improving the diagnostic accuracy of appendicitis using a multidisciplinary pathway

BACKGROUND/PURPOSE

Improvement opportunities exist in the accuracy and timeliness of the diagnosis of childhood appendicitis. The purpose of our study was to conduct a post-implementation audit of a diagnostic pathway for children with suspected appendicitis presenting to our pediatric emergency department.

METHODS

We adopted a diagnostic pathway that utilized a validated risk of appendicitis stratification tool (Alvarado Score) with protocolized use of abdominal ultrasound for moderate risk patients. We conducted a 10% convenience sample audit of pathway patients treated over the subsequent 18-month period. Outcome measures included false negative and positive rates, sensitivity, specificity, and overall pathway accuracy.

RESULTS

One hundred thirty-four pathway patients, of which 22 (16.4%) had appendicitis confirmed pathologically, were evaluated. The risk group distribution of patients was: low risk (29%), moderate risk (60%), and high risk (11%). The negative appendectomy rate was 4.4% (reduced from 14% pre-pathway), and the false negative (missed appendicitis) rate was 3.0%. No patients received CT scans. Pathway sensitivity was 81.8%% (95% CI 59.7% to 94.8%), specificity-92.9%% (95% CI 86.4%-96.9%), and overall accuracy-91.0% (95% CI 84.9%-95.3%).

CONCLUSION

Implementation of a diagnostic pathway achieved a high level of accuracy and reduced our institutional negative appendectomy rate by 67%. The audit identified additional pathway improvement opportunities.

LEVELS OF EVIDENCE

Level IV.

Soft tissue sarcoma in children, adolescents and young adults: Outcomes according to compliance with international initial care guidelines

BACKGROUND

Outcomes for adults with soft tissue sarcoma are better when managed at referral centers. Care guidelines advise for 5 main criteria: 1-Imaging before biopsy; 2-Tumor biopsy before surgery; 3-Multidiscipinary team discussion (MTD) before biopsy; 4-Biopsy in "expert centers"; 5-Somatic molecular biology feasible. The aim is to describe and assess the prognostic impact of initial management of STS according to the type of referring centers and the number of optimal criteria.

METHODS

Monocentric retrospective analysis of the management of 127 youths (0-25 years) with localized STS treated from 2006 to 2015.

RESULTS

Median age at diagnosis was 9.6 years (range: 025). Overall, only 41% patients had 5/5, 28% 3-4, 31% ≤2. No adequate imaging was performed before surgery/biopsy for 18% patients, no biopsy before treatment for 29%. Patients referred by "expert centers" had higher compliance to guidelines (P = 0.025). Upfront surgery was performed in 59/127 patients. Immediate re-operation was inversely related to the number of criteria (0% when 5 criteria vs. 14% for 3-4, 46% if ≤ 2; P < 0.001). For malignant tumors, outcome was better when 5 criteria were reached: 5 year EFS 90.8% (81.4-100.0%) vs. 71.6 for (60.4-84.9%; ≤4 criteria; p = 0.033), OS 93.6% (85.5-100%) vs. 79.5% (68.9-91.8%; p = 0.11), and LRFFS 90.6% (81.0-100.0) vs. 73.1% (62.0-86.3%; p = 0.047).

CONCLUSION

Less than half of the youths with STS are initially managed according to international guidelines, highlighting the need for better information about optimal management. These results plead for immediate management in reference centers to reduce initial burden of therapy.

Diagnostic performance of non-invasive imaging for stable coronary artery disease: A meta-analysis

BACKGROUND

To determine diagnostic performance of non-invasive tests using invasive fractional flow reserve (FFR) as reference standard for coronary artery disease (CAD).

METHODS

Medline, Embase, and citations of articles, guidelines, and reviews for studies were used to compare non-invasive tests with invasive FFR for suspected CAD published through March 2017.

RESULTS

Seventy-seven studies met inclusion criteria. The diagnostic test with the highest sensitivity to detect a functionally significant coronary lesion was coronary computed tomography (CT) angiography [88%(85%-90%)], followed by FFR derived from coronary CT angiography (FFR_CT) [85%(81%-88%)], positron emission tomography (PET) [85%(82%-88%)], stress cardiac magnetic resonance (stress CMR) [81%(79%-84%)], stress myocardial CT perfusion combined with coronary CT angiography [79%(74%-83%)], stress myocardial CT perfusion [77%(73%-80%)], stress echocardiography (Echo) [72%(64%-78%)] and stress single-photon emission computed tomography (SPECT) [64%(60%-68%)]. Specificity to rule out CAD was highest for stress myocardial CT perfusion added to coronary CT angiography [91%(88%-93%)], stress CMR [91%(90%-93%)], and PET [87%(86%-89%)].

CONCLUSION

A negative coronary CT angiography has a higher test performance than other index tests to exclude clinically-important CAD. A positive stress myocardial CT perfusion added to coronary CT angiography, stress cardiac MR, and PET have a higher test performance to identify patients requiring invasive coronary artery evaluation.

The diagnostic pathway of Parkinson's disease: a cross-sectional survey study of factors influencing patient dissatisfaction

BACKGROUND

The diagnostic pathway of Parkinson's disease (PD) is often complicated. Experiences during this pathway can affect patients' satisfaction and their confidence and trust in healthcare providers. Although healthcare providers cannot influence the impact of the diagnosis, they can influence how patients experience the pathway. This study, therefore, aims to provide insight into PD patients' dissatisfaction with the diagnostic pathway and to describe the factors that influence it.

METHODS

We carried out a cross-sectional survey study among 902 patient members of the Dutch Parkinson's Disease Association, who were each asked to write an essay about their diagnostic pathway. A coding format was developed to examine the content of these essays. Inter-observer agreement on coding patient dissatisfaction was calculated using Cohen's kappa. The χ² test and a multivariable logistic regression analysis were performed to assess the relation between dissatisfaction and sex, level of education, duration of the pathway, communication with the general practitioner (GP) and the neurologist, the number of healthcare providers involved, whether or not a second opinion had taken place (including the person who initiated it) and diagnostic delay (taking into consideration who caused the delay according to the patient). A subgroup analysis was performed to gain insight into sex-related differences.

RESULTS

Of all patients, 16.4% explicitly described they were dissatisfied with the diagnostic pathway, whereas 4.8% were very satisfied. The inter-observer agreement on coding dissatisfaction was κ = 0.82. The chance of dissatisfaction increased with a lower level of education, the involvement of more than one additional healthcare provider, a second opinion initiated by the patient and delay caused by a healthcare provider. When only the GP and the neurologist were involved, women were more likely to be dissatisfied than men.

CONCLUSIONS

PD patients' dissatisfaction with the diagnostic pathway is related to a lower level of education, a second opinion initiated by the patient and experienced diagnostic delay. GPs can positively influence patients' experiences if they are aware of these risk factors for dissatisfaction and pay extra attention to communication and shared decision making. This will contribute to a trusting therapeutic relationship that is indispensable with progression of the disease.

Time intervals in diagnosing Parkinson's disease: The patients' views

OBJECTIVE

To explore patients' views on their pathway to the diagnosis of Parkinson's disease (PD).

METHODS

A qualitative study of 52 essays written by patients with PD, using comparative content analysis.

RESULTS

Patients divide their diagnostic pathway into three time intervals: recognition of the symptoms; the decision to seek help; and the process of diagnosing PD. Patients have difficulties recognizing the prodromal symptoms of PD (their knowledge is based on public figures with advanced PD) and mention their general practitioners do as well. The decision to seek help is influenced by the patient's attitude toward health care and by their significant others. More than half of the patients believe their diagnosis was delayed. However, the majority of all patients are satisfied with their diagnostic trajectory.

CONCLUSION

The pathway to diagnosing PD is an iterative process influenced by patient-, health care provider- and disease-related factors. Despite possible delay in diagnosis, patients are content with their pathway.

PRACTICE IMPLICATIONS

In order to facilitate earlier diagnosis and timely therapeutic intervention (in particular with regard to future possibilities for disease modifying therapy), effort is required to increase the recognition of prodromal symptoms of PD by patients, their significant others and health care providers.