Exploring Capabilities of Large Language Models such as ChatGPT in Radiation Oncology.

Purpose: Technological progress of machine learning and natural language processing has led to the development of large language models (LLMs), capable of producing well-formed text responses and providing natural language access to knowledge. Modern conversational LLMs such as ChatGPT have shown remarkable capabilities across a variety of fields, including medicine. These models may assess even highly specialized medical knowledge within specific disciplines, such as radiation therapy. We conducted an exploratory study to examine the capabilities of ChatGPT to answer questions in radiation therapy. Methods and Materials: A set of multiple-choice questions about clinical, physics, and biology general knowledge in radiation oncology as well as a set of open-ended questions were created. These were given as prompts to the LLM ChatGPT, and the answers were collected and analyzed. For the multiple-choice questions, it was checked how many of the answers of the model could be clearly assigned to one of the allowed multiple-choice-answers, and the proportion of correct answers was determined. For the open-ended questions, independent blinded radiation oncologists evaluated the quality of the answers regarding correctness and usefulness on a 5-point Likert scale. Furthermore, the evaluators were asked to provide suggestions for improving the quality of the answers. Results: For 70 multiple-choice questions, ChatGPT gave valid answers in 66 cases (94.3%). In 60.61% of the valid answers, the selected answer was correct (50.0% of clinical questions, 78.6% of physics questions, and 58.3% of biology questions). For 25 open-ended questions, 12 answers of ChatGPT were considered as "acceptable," "good," or "very good" regarding both correctness and helpfulness by all 6 participating radiation oncologists. Overall, the answers were considered "very good" in 29.3% and 28%, "good" in 28% and 29.3%, "acceptable" in 19.3% and 19.3%, "bad" in 9.3% and 9.3%, and "very bad" in 14% and 14% regarding correctness/helpfulness. Conclusions: Modern conversational LLMs such as ChatGPT can provide satisfying answers to many relevant questions in radiation therapy. As they still fall short of consistently providing correct information, it is problematic to use them for obtaining medical information. As LLMs will further improve in the future, they are expected to have an increasing impact not only on general society, but also on clinical practice, including radiation oncology.

Extraction of Interoperable Data from Healthcare Documents by Identifying Common Data Elements: An Analysis of Radiation Therapy Planning CT Physician Order Entry Records.

INTRODUCTION: Documentation as well as IT-based management of medical data is of ever-increasing relevance in modern medicine. As radiation oncology is a rather technical, data-driven discipline, standardization, and data exchange are in principle possible. We examined electronic healthcare documents to extract structured information. Planning CT order entry documents were chosen for the analysis, as this covers a common and structured step in radiation oncology, for which standardized documentation may be achieved. The aim was to examine the extent to which relevant information may be exchanged among different institutions. MATERIALS AND METHODS: We contacted representatives of nine radiation oncology departments. Departments using standardized electronic documentation for planning CT were asked to provide templates of their records, which were analyzed in terms of form and content. Structured information was extracted by identifying definite common data elements, containing explicit information. Relevant common data elements were identified and classified. A quantitative analysis was performed to evaluate the possibility of data exchange. RESULTS: We received data of seven documents that were heterogeneous regarding form and content. 181 definite common data elements considered relevant for the planning CT were identified and assorted into five semantic groups. 139 data elements (76.8%) were present in only one document. The other 42 data elements were present in two to six documents, while none was shared among all seven documents. CONCLUSION: Structured and interoperable documentation of medical information can be achieved using common data elements. Our analysis showed that a lot of information recorded with healthcare documents can be presented with this approach. Yet, in the analyzed cohort of planning CT order entries, only a few common data elements were shared among the majority of documents. A common vocabulary and consensus upon relevant information is required to promote interoperability and standardization.

(Common) Data Elements in Radiation Oncology: A Systematic Literature Review.

PURPOSE: Structured medical data documentation is highly relevant in a data-driven discipline such as radiation oncology. Defined (common) data elements (CDEs) can be used to record data in clinical trials, health records, or computer systems for improved standardization and data exchange. The International Society for Radiation Oncology Informatics initiated a project for a scientific literature analysis of defined data elements for structured documentation in radiation oncology. METHODS: We performed a systematic literature review on both PubMed and Scopus to analyze publications relevant to the utilization of specified data elements for the documentation of radiation therapy (RT)-related information. Relevant publications were retrieved as full-text and searched for published data elements. Finally, the extracted data elements were quantitatively analyzed and classified. RESULTS: We found a total of 452 publications, of which 46 were considered relevant for structured data documentation. Twenty-nine publications addressed defined RT-specific data elements, of which 12 publications provided data elements. Only two publications focused on data elements in radiation oncology. The 29 analyzed publications were heterogeneous regarding the subject and usage of the defined data elements, and different concepts/terms for defined data elements were used. CONCLUSION: The literature about structured data documentation in radiation oncology using defined data elements is scarce. There is a need for a comprehensive list of RT-specific CDEs the radio-oncologic community can rely on. As it has been done in other medical fields, establishing such a list would be of great value for clinical practice and research as it would promote interoperability and standardization.

Designing a Digital Medical Interview Assistant for Radiology.

Radiologists rarely interact with the patients whose radiological images they are reviewing due to time and resource constraints. However, relevant information about the patient's medical history could improve reporting performance and quality. In this work, our objective was to collect requirements for a digital medical interview assistant (DMIA) that collects the medical history from patients by means of a conversational agent and structures as well as provides the collected data to radiologists. Requirements were gathered based on a narrative literature review, a patient questionnaire and input from a radiologist. Based on these results, a system architecture for the DMIA was developed. 37 functional and 17 non-functional requirements were identified. The resulting architecture comprises five components, namely Chatbot, Natural language processing (NLP), Administration, Content Definition and Workflow Engine. To be able to quickly adapt the chatbot content according to the information needs of a specific radiological examination, there is a need for developing a sustainable process for the content generation that considers standardized data modelling as well as rewording of clinical language into consumer health vocabulary understandable to a diverse patient user group.

Current Research and Development in Hyperthermic Intraperitoneal Chemotherapy (HIPEC)-A Cross-Sectional Analysis of Clinical Trials Registered on ClinicalTrials.gov.

INTRODUCTION: Over the past two decades, cytoreductive surgery and HIPEC has improved outcomes for selected patients with peritoneal metastasis from various origins. This is a cross-sectional study with descriptive analyses of HIPEC trials registered on ClinicalTrials.gov. This study aimed to characterize clinical trials on HIPEC registered on ClinicalTrials.gov with the primary objective of identifying a trial focus and to examine whether trial results were published. METHODS: The search included trials registered from 1 January 2001 to 14 March 2022. We examined the associations of exposure variables and other trial features with two primary outcomes: therapeutic focus and results reporting. RESULTS: In total, 234 clinical trials were identified; 26 (11%) were already published, and 15 (6%) trials have reported their results but have not been published as full papers. Among ongoing nonpublished trials, 81 (39%) were randomized, 30 (14%) were blinded, n = 39 (20%) were later phase trials (i.e., phases 3 and 4), n = 152 (73%) were from a single institution, and 91 (44%) had parallel groups. Most of the trials were recruiting at the time of this analysis (75, 36%), and 39 (20%) were completed but had yet to publish results. In total, 68% of the trials focused on treatment strategies, and 53% investigated the oncological outcome. The most studied neoplasms for HIPEC trials were peritoneally metastasized colorectal cancer (32%), gastric cancer (29%), and ovarian cancer (26%). Twenty different drugs were analyzed in these clinical trials. CONCLUSIONS: Many study results are awaited from ongoing HIPEC trials. Most HIPEC trials focused on gastric, colorectal, or ovarian cancer. Many clinical trials were identified involving multiple entities and chemotherapeutic agents.

Applications of Machine Learning in Palliative Care: A Systematic Review.

Objective: To summarize the available literature on using machine learning (ML) for palliative care practice as well as research and to assess the adherence of the published studies to the most important ML best practices. Methods: The MEDLINE database was searched for the use of ML in palliative care practice or research, and the records were screened according to PRISMA guidelines. Results: In total, 22 publications using machine learning for mortality prediction (n = 15), data annotation (n = 5), predicting morbidity under palliative therapy (n = 1), and predicting response to palliative therapy (n = 1) were included. Publications used a variety of supervised or unsupervised models, but mostly tree-based classifiers and neural networks. Two publications had code uploaded to a public repository, and one publication uploaded the dataset. Conclusions: Machine learning in palliative care is mainly used to predict mortality. Similarly to other applications of ML, external test sets and prospective validations are the exception.

Accuracy of the Apple Watch Oxygen Saturation Measurement in Adults: A Systematic Review.

The purpose of this review is to summarize the research on the accuracy of oxygen saturation (spO2) measurements using the Apple Watch (Apple Inc., Cupertino, California). The Medline and Google Scholar databases were searched for papers evaluating the spO2 measurements of the Apple Watch vs. any kind of ground truth and records were analyzed according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The five publications with 973 total patients that met the inclusion criteria all used the Apple Watch Series 6 and described 95% limits of agreement of +/- 2.7 to 5.9% spO2. However, outliers of up to 15% spO2 were reported. Only one study had patient-level data uploaded to a public repository. The Apple Watch Series 6 does not show a strong systematic bias compared to conventional, medical-grade pulse oximeters. However, outliers do occur and should not cause concern in otherwise healthy individuals. The impact of race on measurement accuracy should be investigated.

Toward Data-Driven Radiation Oncology Using Standardized Terminology as a Starting Point: Cross-sectional Study.

BACKGROUND: The inability to seamlessly exchange information across radiation therapy ecosystems is a limiting factor in the pursuit of data-driven clinical practice. The implementation of semantic interoperability is a prerequisite for achieving the full capacity of the latest developments in personalized and precision medicine, such as mathematical modeling, advanced algorithmic information processing, and artificial intelligence approaches. OBJECTIVE: This study aims to evaluate the state of terminology resources (TRs) dedicated to radiation oncology as a prerequisite for an oncology semantic ecosystem. The goal of this cross-sectional analysis is to quantify the state of the art in radiation therapy specific terminology. METHODS: The Unified Medical Language System (UMLS) was searched for the following terms: radio oncology, radiation oncology, radiation therapy, and radiotherapy. We extracted 6509 unique concepts for further analysis. We conducted a quantitative analysis of available source vocabularies (SVs) and analyzed all UMLS SVs according to the route source, number, author, location of authors, license type, the lexical density of TR, and semantic types. Descriptive data are presented as numbers and percentages. RESULTS: The concepts were distributed across 35 SVs. The median number of unique concepts per SV was 5 (range 1-5479), with 14% (5/35) of SVs containing 94.59% (6157/6509) of the concepts. The SVs were created by 29 authors, predominantly legal entities registered in the United States (25/35, 71%), followed by international organizations (6/35, 17%), legal entities registered in Australia (2/35, 6%), and the Netherlands and the United Kingdom with 3% (1/35) of authors each. Of the total 35 SVs, 16 (46%) did not have any restrictions on use, whereas for 19 (54%) of SVs, some level of restriction was required. Overall, 57% (20/35) of SVs were updated within the last 5 years. All concepts found within radiation therapy SVs were labeled with one of the 29 semantic types represented within UMLS. After removing the stop words, the total number of words for all SVs together was 56,219, with a median of 25 unique words per SV (range 3-50,682). The total number of unique words in all SVs was 1048, with a median of 19 unique words per vocabulary (range 3-406). The lexical density for all concepts within all SVs was 0 (0.02 rounded to 2 decimals). Median lexical density per unique SV was 0.7 (range 0.0-1.0). There were no dedicated radiation therapy SVs. CONCLUSIONS: We did not identify any dedicated TRs for radiation oncology. Current terminologies are not sufficient to cover the need of modern radiation oncology practice and research. To achieve a sufficient level of interoperability, of the creation of a new, standardized, universally accepted TR dedicated to modern radiation therapy is required.

Contemporary treatment patterns and survival of cervical cancer patients in Ethiopia.

BACKGROUND: Cervical cancer is the second commonly diagnosed cancer and the second leading cause of cancer death in women in Ethiopia, with rates among the highest worldwide. However, there are limited data on cervical cancer treatment patterns and survival in the country. Herein, we examine treatment patterns and survival of cervical cancer patients treated in Tikur Anbessa Hospital Radiotherapy Center (TAHRC), the only hospital with radiotherapy facility in the country. METHODS: Women with histologically verified cervical cancer who were seen in 2014 (January 1, 2014 to December 31, 2014) at TAHRC were included. Information about clinical characteristics and treatments were extracted from the patients' medical record files. The information on vital status was obtained from medical chart and through telephone calls. RESULT: Among 242 patients included in the study, the median age at diagnosis was 48 years. The median waiting time for radiotherapy was 5.6 months (range 2 to 9 months). Stage migration occurred in 13% of patients while waiting for radiotherapy. Consequently, the proportion of patients with stage III or IV disease increased from 66% at first consultation to 74% at the initiation of radiotherapy. Among 151 patients treated with curative intent, only 34 (22.5%) of the patients received concurrent chemotherapy while the reaming patients received radiotherapy alone. The 5-year overall survival rate was 28.4% (20.5% in the worst-case scenario). As expected, survival was lower in patients with advanced stage at initiation of radiotherapy and in those treated as palliative care. CONCLUSION: The survival of cervical cancer patients remains low in Ethiopia because of late presentation and delay in receipt of radiotherapy, leading to stage migration in substantial proportion of the cases. Concerted and coordinated multisectoral efforts are needed to promote early presentation of cervical cancer and to shorten the unacceptable, long waiting time for radiotherapy.

Pressurized Intraperitoneal Aerosol Chemotherapy-Related Clinical Trials in the Treatment of Peritoneal Metastases.

INTRODUCTION: Pressurized intraperitoneal aerosol chemotherapy (PIPAC) is a treatment option for patients with peritoneal metastases. We evaluated the current status of ongoing prospective clinical trials investigating PIPAC to provide an overview and predict trends in this field. METHODS: All 367,494 records of clinical trials registered at ClinicalTrials.gov were searched for trials dealing with PIPAC. Active or unpublished trials were further analyzed. RESULTS: In total, 22 clinical trials were identified and selected for further analyses. Most trials had a single-arm design and were phase I or II. No phase III trials were registered. Academic centers were recorded as primary sponsors in the majority of trials (63.6%). Every year, between 2 and 5 new trials were initiated. In 17 trials (81.8%), PIPAC was used in a palliative setting only, 2 trials performed PIPAC in a neoadjuvant setting, and 2 trials performed PIPAC in an adjuvant setting. Six different drugs (doxorubicin, cisplatin, oxaliplatin, nab-paclitaxel, 5-fluorouracil, and docetaxel) were used in these clinical trials. Most trials investigated the efficacy (n = 15) or safety (n = 7) of PIPAC therapies. CONCLUSIONS: The results of ongoing clinical trials will bring specific information on indications for PIPAC as well as the impact of PIPAC on quality of life and overall survival.

The prognostic impact of daytime and seasonality of radiotherapy on head and neck cancer.

BACKGROUND: The potential impact of daytime and season of radiotherapy application on prognosis is unclear. This was analyzed in a retrospective cohort of patients who were diagnosed with non-metastatic head and neck squamous cell carcinoma (HNSCC) and treated with definitive radiotherapy with or without chemotherapy. MATERIALS AND METHODS: Patient and tumor characteristics, treatment parameters and outcome until last follow-up or death were obtained. Median radiotherapy delivery daytime of each patient was categorized as morning (AM) and afternoon (PM). Treatment season was defined by median date of treatment course. Each year was divided into DARK and LIGHT according to equinoxes. Time-to-event endpoints were defined by first biopsy confirming the HNSCC. RESULTS: Six hundred fifty-five cases were identified who were treated with (chemo)radiotherapy between 2002 and 2015. Median follow-up was 47 months. No significant heterogeneity in patient, tumor and treatment characteristics were observed between DARK and LIGHT or regarding median daily fraction time (X2 p > 0.05). Five-year loco-regional control (73% vs. 61%; p = 0.0108) and progression-free survival (51% vs. 43%; p = 0.0374) were superior when radiotherapy was administered in DARK. Neither the daytime nor any other treatment time-related parameter affected prognosis. CONCLUSION: This is the first study investigating and presenting the prognostic impact of seasonality regarding the treatment course on loco-regional control and progression-free survival (DARK > LIGHT). The biological mechanism of action is unclear. These results should be interpreted with caution and our findings have to be validated externally.

The impact of delivery daytime and seasonality of radiotherapy for head and neck cancer on toxicity burden.

AIM: The potential impact of the daytime and season of radiotherapy application on acute and late toxicity burden was analyzed on a cohort of curatively treated head and neck squamous cell carcinoma patients. METHODS: Through a retrospective chart review, patient and tumor characteristics, treatment parameters and outcome were obtained. Patients treated with definitive or adjuvant radiotherapy with and without chemotherapy receiving ≥60 Gy between 2002 and 2015 were included (n = 617). Daily fraction times and dates were extracted. Median radiotherapy delivery time of each patient was categorized as morning (AM) and afternoon (PM). Treatment season was defined by the median day of the treatment course. Each year was divided into DARK and LIGHT by the March and September equinoxes. Acute (T) and late (A) toxicity were defined by TAME methodology. RESULTS: Median follow-up was 51 months. Mean T and A scores during and after radiotherapy in DARK vs. LIGHT were 1.98 vs. 1.61 (p = 0.0127) and 0.41 vs. 0.30 (p = 0.1699), respectively. Mean T and A scores during and after AM vs. PM radiotherapy were 1.71 vs. 1.88 (p = 0.0387) and 0.31 vs. 0.41 (p = 0.2638), respectively. Multivariate analyses indicated DARK vs. LIGHT as the only independent treatment time-related factor among other factors such as tumor subsite, UICC stage, radiotherapy technique, and chemotherapy for T. CONCLUSION: This is the first study investigating the impact of seasonality on toxicity burden, showing higher acute toxicity with radiotherapy in DARK. The daytime did not predict the toxicity. The hypothesis-generating findings of this retrospective study should be further investigated.

Decision Making Criteria in Oncology.

Decision making is one of the most complex skills required of an oncologist and is affected by a broad range of parameters. For example, the wide variety of treatment options, with various outcomes, side-effects and costs present challenges in selecting the most appropriate treatment. Many treatment choices are affected by limited scientific evidence, availability of therapies or patient-specific factors. In the decision making process, standardized approaches can be useful, but a multitude of criteria are relevant to this process. Thus, the aim of this review is to summarize common types of decision criteria used in oncology by focusing on 3 main categories: criteria associated with the decision maker (both patient and doctor), decision specific criteria, and the often-overlooked contextual factors. Our review aims to highlight the broad range of decision criteria in use, as well as variations in their interpretation.

Multidisciplinary Cancer Management of Colorectal Cancer in Tikur Anbessa Specialized Hospital, Ethiopia.

PURPOSE: Multidisciplinary cancer care is currently considered worldwide as standard for the management of patients with cancer. It improves patient diagnostic and staging accuracy and provides patients the benefit of having physicians of various specialties participating in their treatment plan. The purpose of this study was to describe the profile of patients discussed in the Tikur Anbessa Multidisciplinary Tumor Board (MTB) and the potential benefits brought by multidisciplinary care. METHODS: The study involved the retrospective assessment of all patient cases presented to the Tikur Anbessa Hospital colorectal cancers MTB between March 2016 and November 2017. The data were collected from the MTB medical summary documents and were analyzed using SPSS version 20 (SPSS, Chicago, IL). RESULTS: Of 147 patients with colorectal cancer, 96 (65%) were men. The median age at presentation was 46 years (range, 17-78 years). The predominant cancer was rectal (n = 101; 69%), followed by colon (n = 24; 16%). Of these, 68 (45%) and 22 (15%) had stage III and IV disease, respectively, on presentation to the MTB. The oncology department presented the majority of the patients for discussion. Most patients had undergone surgery before the MTB discussion but had no proper preoperative clinical staging information. The majority of patients with rectal cancer treated before the MTB discussion had undergone surgery upfront; however, most of the patients who were treatment naive before MTB received neoadjuvant chemoradiotherapy before surgery. CONCLUSION: Decisions made by tumor boards are more likely to conform to evidence-based guidelines than are those made by individual clinicians. Therefore, early referral of patients to MTB before any treatment should be encouraged. Finally, other hospitals in Ethiopia should take a lesson from the Tikur Anbessa Hospital colorectal cancers MTB and adopt multidisciplinary cancer management.

Breast cancer care in northern Ethiopia - cross-sectional analysis.

BACKGROUND: In Ethiopia, the incidence of new cases of breast cancer is currently increasing resulting to high rates of morbidity and mortality. Breast cancer is by far the most common cancer accounting for more than one out of three cancer cases in women and one out of every five in the general population. The study was conducted in University of Gondar Hospital cancer center, located in the North-West Ethiopia; to evaluate the clino-pathologic characteristics of breast cancer and care provided for patients. METHODS: All biopsy proven breast cancer patients treated between 2016 and 2017, were identified and information regarding histology, stage, therapeutic procedure and follow up was retrospectively collected from their individual medical records and descriptive analysis was done. RESULTS: Among 82 patients treated, 67 (82%) were women and 15 (18%) were men. The median age at the time of diagnosis was 45 years (25-82 years). Operation was performed for 56 (68%) patients. The predominant histology was ductal carcinoma in 61 patients (74%), followed by breast carcinoma of No Special Type (NST) in 17 (21%). The late presentation of the patients and the advanced stage at the time of presentation was observed in most of the patients. Chemotherapy was administered in 79 (96%) patients. Radiotherapy was not available in the hospital. CONCLUSION: Breast cancer incidence is rising and becoming a major public health problem in Northern Ethiopia. Breast cancer care in northern-Ethiopia is limited in terms of both pathology, imaging and the offered treatment modalities, which need to be improved.

Emerging patient-specific treatment modalities in head and neck cancer - a systematic review.

INTRODUCTION: Head and neck cancer (HNC) is an immunosuppressive disease that demonstrates heterogeneous molecular characteristics and features of tumor-host interaction. Beside radiotherapy and surgery, the current standard of care in systemic treatment involves the use of cytotoxic chemotherapy, monoclonal antibodies (mAbs), and tyrosine kinase inhibitors (TKIs). There are also other modalities being developed under the category of immunotherapy, but they are overshadowed by the recent advancements of immune checkpoint inhibitors. AREAS COVERED: This systematic review covers recent advancements in 'patient-specific' treatment modalities, which can be only administered to a given patient. EXPERT OPINION: Currently, patient-specific treatment modalities in HNC mainly consist of active immunotherapy using adoptive cell therapies and/or gene engineered vectors. Despite the slow pace of development, the interest continues in these treatment modalities. The future of HNC treatment is expected to be guided by biomarkers and personalized approaches with tailored combinations of local treatments (radiotherapy, surgery), systemic agents and immune system modulation. Systematic research is required to generate robust data and obtain a high-level of evidence for the effectiveness of such treatment modalities.

Current efforts in research of pleural mesothelioma-An analysis of the ClinicalTrials.gov registry.

OBJECTIVES: Currently there are many uncertainties in the optimal treatment of malignant pleural mesothelioma (MPM), this is reflected in discrepancies between current guidelines. Our aim was to evaluate the current status of prospective interventional clinical trials within the ClinicalTrials.gov registry in MPM in order to predict a potential impact on MPM management in the next years. MATERIAL AND METHODS: The records of 263.832 clinical trials registered were searched in December 2017. Trials starting between 2005 and 2017 (n = 262) were selected for further manual review. Trials including other tumour entities or mesothelioma originating outside the pleura (n = 94) were excluded, as well as trials where the primary endpoint has already been published (n = 22). RESULTS: In total, 91 clinical trials were identified and selected for further analysis. Most trials had a single arm design, were in phase I, and were non-randomized. Academic centres were recorded as primary sponsors in the majority of trials (56%), followed by industry in 21%. Most studies investigated targeted (n = 42) or cytotoxic therapies (n = 39). Ten studies investigated different genetic therapies. In 67% of the trials (n = 61) targeted and/or cytotoxic therapies were involved. Treatments involving surgery were investigated in 12 trials (13%), radiotherapy in 10 trials (11%). Only five studies (6%) were phase 3 studies and one was a phase 2/3 study. Four of these five phase 3 trials investigated targeted therapies, while one trial investigated prophylactic radiotherapy of operative tracts. CONCLUSIONS: Currently running trials in MPM are mostly in early phases and dominated by systemic therapies. Very few trials evaluate loco-regional therapeutic approaches. The current controversy surrounding the use of surgery and radiotherapy within multimodal therapy strategies will not be answered by these trials in the coming years.

Clinical trials involving positron emission tomography and prostate cancer: an analysis of the ClinicalTrials.gov database.

BACKGROUND: The goal of this study is to evaluate the status and future perspectives of clinical trials on positron emission tomography in prostate cancer for diagnostic or therapeutic as well as for surveillance purposes. METHODS: The www.ClinicalTrials.gov database was searched on the 20th of January 2017 for all trials containing terms describing "prostate cancer" (prostate, prostatic, malignant, malignancy, cancer, tumor) and "positron emission tomography". In total 167 trials were identified. Trials that included diseases other than PCa were excluded (n = 27; 16%). Furthermore, we excluded trials (n = 4, 2%) withdrawn prior to first patient enrollment. The remaining trials (n = 137, 82%) were selected for further manual classification analysis. RESULTS: One hundred thirty-seven trials were detected and analyzed. Majority of trials were in "active" recruitment status (n = 46, 34%) followed by trials that had been "completed" - (n = 34, 25%) and trials with "closed recruitment but active follow-up" (n = 23, 17%). Phase 1 and 2 comprised 46% of the complete trial portfolio. Locally confined disease was of major interest (n = 46, 34%), followed by metastatic disease - not otherwise specified (n = 43, 13%). Evaluation of PET was the primary goal of the trial in 114 (83%) cases. Most of the trials evaluated only one agent (n = 122, 89%). Choline and PSMA represented two major groups (total 50%) and they were equally distributed across trial portfolio with 25% (n = 34) each. PSMA trials showed the highest average annual growth rate of 56%. The trials were conducted in 17 countries. CONCLUSION: The scientific community is showing a strong and ever-growing interest in the field and we expect that in the coming years, more phase III trials will be initiated ultimately delivering the required Level 1 evidence.