Edward Weber, MD

Edward Weber, MD

Seattle, Washington

Edward Weber, MD, is a retired medical oncologist living in Seattle, Washington. He was born and raised in a suburb of Reading, Pennsylvania. After graduating from Princeton University in 1956 with a BA in History, Dr. Weber attended medical school at the University of Pennsylvania. His internship training took place at the University of Vermont in Burlington.

A tour of service as a Naval Flight Surgeon positioned him on Whidbey Island, Washington, and this introduction to the Pacific Northwest ultimately proved irresistible. Following naval service, he received postgraduate training in internal medicine in Philadelphia at the Pennsylvania Hospital and then pursued a fellowship in hematology and oncology at the University of Washington.

His career in medical oncology was at the Tumor Institute of the Swedish Hospital in Seattle where his practice focused largely on the treatment of patients experiencing lung, breast, colon, and genitourinary cancer and malignant lymphoma.

Toward the end of his career, he developed a particular concentration on the treatment of prostate cancer. Since retirement in 2002, he has authored the PCa Commentary, published by the Prostate Cancer Treatment Research Foundation, an analysis of new developments in the prostate cancer field with essays discussing and evaluating treatment management options in this disease. He is a regular speaker at various prostate cancer support groups around Seattle.

Talks by Edward Weber, MD

PCa Commentary | Volume 184 – December 2023

PCa Commentary | Volume 184 – December 2023

Posted by | Dec 2023

Background

Some men with low- or intermediate-risk localized prostate cancer will present on MRI imaging with a lesion sufficiently small and apparently well-delineated to warrant targeted focused therapy. This is termed “focal therapy” and can be accomplished with heat probes (laser ablation), radioactive seeds (brachytherapy), freezing (cryotherapy) or highly focused radiation (stereotactic ablative radiotherapy with, i.e., CyberKnife). The goal is total eradication of the cancer with the associated benefit in quality of life by better preservation of erectile function and urinary continence as compared to whole gland treatments. It might be considered a “middle ground” between active surveillance and radical treatment and is particularly appropriate for favorable intermediate-risk cancers.

Currently, the mpMRI is the imaging tool to select patients for focal therapy. The concept of focal therapy is the irradiation of the “index” lesion as visualized on the mpMRI. Therefore, the accurate location and definition of intraprostatic cancer is essential. Since disease often extends unseen 5-10 mm beyond the MRI “area of interest,” the fully treated field is often “hemi-gland.” Appropriate candidates for focal therapy are those men with PSA less than or equal to 15ng/mL, clinical/radiological tumor stage limited to 1/2 of the prostate ( less than or equal to T2b) and Gleason Grades 2-3. A recent study (Geboers et al. BJU Int, Oct. 2023) addressed focal therapy and patient selection and reported that the sensitivity and negative predictive value for MRI imaging for excluding more advanced cancer were 79% and 77%, respectively.

Their study found that the addition of a PSMA PET scan for patient selection provided some improvement. However, the major shortcoming of focal therapy is unidentified cancer extending beyond the chosen treatment margins or subtle multifocal disease. These states are the “Achilles Heel” that decreases the effectiveness of all forms of focal therapy based on the conventional MRI.

In the 1970s pioneers in the management of breast cancer developed the “lumpectomy” procedure (local excision of cancer with breast preservation) and this strategy has become standard of care in the treatment of early breast cancer. Potentially, focal therapy of prostate cancer could achieve a similar accomplishment. The two most common forms of focal therapy for prostate cancer are brachytherapy and cryotherapy.

Focal Brachytherapy

In 2022 Langley et al. (Brachytherapy) reported the findings of the ‘Hemi-Ablative Prostate Brachytherapy Trial’ comparing low-dose-rate I-125 hemi-gland BT treatment, 30 men, vs 362 men, whole-gland “to control unilateral localized prostate cancer and reduce treatment-related toxicity at 2 years post-implant.” Bowel, bladder, erectile function and quality of life was evaluated by a combination of standard questionnaires. Symptoms were significantly less troublesome for men receiving hemi-gland vs whole-gland brachytherapy.

Findings: “The mean time to PSA nadir was 4.2 and 4.8 years in HG and WG, respectively.” Treatment failure occurred in 6.7% HG patients and in 5.5% WG patients. “Five-year relapse-survival was 97% in both groups (P=.07).”

Focal Cryotherapy

A small and carefully performed protocol of focal cryotherapy was reported by Tan et al, The Prostate, March 2023. Twenty-eight men were studied, and all underwent a 12-month follow-up biopsy. Patient eligibility required a single MRI lesion with volume less than or equal to 3 cm or two lesions each less than or equal to 1.5 cm; PSA less than or equal to 20 ng/mL; and Gleason Grade Group less than or equal to 4. The lesions were treated with 5 mm margins. The median PSA at onset was 7.3 ng/mL and was reduced to a median of 4.6 ng/mL, a 60.4% reduction.

Findings: At the 12-month MRI-based biopsy 22 patients (78.6%) had no detectable prostate cancer while 6 men had cancer with < Gleason Grade Group 2. Within the treated field 7.1% were biopsy positive and 10.7% had cancer beyond the treated field; one man had both. Four men had repeat cryotherapy, one surgery, and one with low-volume GG2 cancer entered active surveillance.

Urinary and sexual domains both demonstrated “acute deterioration at one month with recovery at 3 months.” “Ablation to the adjacent neurovascular bundle delayed recovery of sexual function for 6 months”, otherwise there was “no deterioration in sexual function.” Since focal therapy does not ablate the entire prostate, residual serum PSA remains, rendering inapplicable the usual PSA thresholds indicating post-treatment biochemical recurrence. A study of HIFU therapy by Mattlet et al, (Prostate, 2023) of 343 men found a failure rate of 23% based on clinically significant cancer on post-therapy biopsy.

The best criteria for predicting failure were “PSA nadir + 1 ng/mL at 12 months or PSA nadir + 1.5 ng/mL at 24-36 months.”

Artificial Intelligence to Treat the “Achilles Heel”

The in-field persistence of disease noted above in both types of focal treatments is likely the result of insufficient radiation dose or inherent resistance of the cancer in the treated focus. But out-of-field untreated disease is due to inaccurate targeting. Avenda Heath, a biotech company, has addressed this deficiency by creating a multimodal AI model, ‘Unfold AI,’ that produces a color-enhanced 3-D depiction of cancer within the prostate.

In their article, “Prediction and Mapping of Intraprostatic Tumor Extent with  Artificial Intelligence,” Priester, Marks et al, (European Urology Open Science, August 2023) contend that compared to their UnFold model, tumor delineation of intraprostatic tumor based on magnetic resonance imaging (MRI) significantly underestimates the extent of prostate cancer, which “complicates the definition of focal treatment margins.” Their AI-based platform is multimodal in that it combines patient-specific data (MRI, PSA, biopsy, and pathology) and artificial intelligence to create a “3-D cancer estimation map” showing the cancer’s extent and margins. Based on evaluation of 50 prostatectomy specimens from men with intermediate-risk cancer the mean sensitivity of cancer mapping was higher for AI estimated margins, 97%, than for MRI-based contours at 37%. This difference remained significant even when comparing the conventional treatment margins of 10 mm surrounding the MRI-identified tumor.

The authors’ conclusion: “This approach could help improve and standardize focal treatment margins, potentially reducing cancer recurrence rates.”

BOTTOM LINE

Focal therapy for prostate cancer is increasing. An Artificial Intelligence-based model, ‘UnFold’, more accurately defines intraprostatic tumor extent and margins compared to MRI-based estimates and can improve the efficiency of focal treatment.

Read More
PCa Commentary | Volume 183 – November 2023

PCa Commentary | Volume 183 – November 2023

Posted by | Nov 2023

Background

A forceful sea change is roiling in the management of this disease: artificial intelligence (AI) is coming into prominence benefiting cancer diagnosis, risk stratification, and the prediction of response to therapy for individual patients. Multimodal AI (using deep learning) draws upon increasingly large stores of clinical and outcome data and digital histopathology to identify patterns that can predict therapeutic benefits for personalized treatment. The reference datasets might be extensive information generated from large clinical trials, a repository of annotated pathology specimens or imaging datasets (such as those of MRIs). In recent years, the literature has reported an impressively extensive body of studies of AI applications. This Commentary will offer four examples that could inform clinical practice.

Guiding the Use of Androgen Suppression Adjuvant to Radiation Therapy:

Two published pace-setting studies on this subject were covered in previous PCa Commentaries.

PCa Commentary #180: Dr. Dan Spratt and colleagues (NEJM Evidence, June 2023) developed an AI program identifying a biomarker, derived from 1719 patients in 5 large clinical trials, that predicts the marginal benefit of adding short-term hormone therapy to primary radiation for a man with localized prostate cancer. By applying the AI-derived model, the 15-year estimate for developing distant metastases for biomarker-positive patients treated with ADT was 4% v 14.4% for biomarker-negative ADT patients. This test is commercially available at ArteraAI Prostate Test where it is fully explained.

PCa Commentary #181: The second study was presented in abstract form by Armstrong et al. at ASCO 2023:
“Development and validation of an AI-derived digital pathology-based biomarker to predict benefit of …[28 months vs 4 months] androgen deprivation therapy with radiotherapy in men with localized high-risk prostate cancer … .”

Improving Cancer Detection Based on Prostate MRI

Multiparametric MRI functions to detect prostate cancer and guide MRI-ultrasound fusion biopsies and treatment. Optimally an MRI study leads to a biopsy of only clinically significant cancer, defined as Gleason score of 7 or greater. The PIRADS (Prostate Imaging-Reporting and Data System) offers a numerical estimate for the likelihood of the presence of cancer based on the MRI. This estimate of cancer’s aggressiveness is based on a scale of 1 through 5, with 1 and 2 representing low likelihood, 3 – concerning and 4 and 5 very suspicious for cancer. Unfortunately, even this system has deficiencies.

As reported by Bhattacharya et al, Ther Adv Urol. 2022, compared to the examination of a  subsequent prostatectomy as ground truth, “12% of aggressive cancers, mostly those less than 1 cm, were missed on MRIs. False positive rate was greater than 35%. Additionally, there is high inter-reader variability. As a result, many unnecessary biopsies continue to be performed”.

“Radiomics” refers to the analytic system for extracting features of significance from MRI images that are not perceived by visual examination. There is extensive research on using radiomics to facilitate greater interpretive and predictive information from the MRI and to improve on the stratification of the PI-RAD system.

The underestimation of cancer extent on MRI is addressed by Priester et al, in ”Prediction and Mapping of Intra-prostatic Tumor Extent with Artificial Intelligence”, European Urology June 2023. One of their objectives was to improve the accuracy of tumor delineation of clinically significant cancer on the MRI to facilitate more effective focal radiation therapy, a technique increasingly gaining acceptance for intermediate-risk cancer. To accomplish this an AI model was developed combining MRI imaging, biopsy data, PSA and PSA Density values and prostate volume to produce “three-dimensional cancer estimation maps and margins.” When compared to cancer extent found on companion prostatectomy specimens, the AI estimate model was more accurate than one based on conventional MRI interpretation, ensuring a better outcome for focal radiation therapy.  This AI model is FDA-approved and commercially available: “Avenda Health AI Prostate Cancer Planning Software”.

Predicting Early Recurrence after Prostatectomy

An AI-powered method was developed to predict early recurrence at 36 months after prostatectomy based on digitized pathology slides in conjunction with clinical and outcome data (Huang et al, JCO Clin Cancer Inform, 2022). The AI platform was trained on 243 digitized whole-mount slides of prostatectomy specimens combined with information about Gleason score, staging, margin status and clinical outcome. The method was validated on 92 patients who had recurrence in <3 years and 151 who recurred after 3 years.

The 100,000 x 100,000  pixels surveyed per slide has the advantage (compared to the standard microscopic evaluation) of recording small, but relevant, regions that escape visual notice, and perhaps most important, capture immune features (not included in the Gleason Grade Groupings), of the tumor microenvironment and stroma (supporting cells) that are so influential in driving the cancer’s behavior.

Based on this data the study provided a prediction of biochemical recurrence within 3 years after surgery for men with cancer in all Gleason Grade Groups and performed better than conventional risk stratification systems. The authors felt that this AI method for identifying patients at risk for early recurrence would benefit the selection of personalized treatment.

AI in Association with Cancer Diagnosis and Gleason Grading

AI algorithms have performed well in this task and have been multiply validated. Many are certified for clinical use. The usefulness of AI has not been to replace pathologists in analyzing biopsy specimens, but to augment the heavy workload of pathologists. “Pathologic examination of prostate specimens is laborious and time-consuming due to the large number of slides per case – 50-100 slides per case.” (Tolkach)

In a comprehensive study by Tolkach et al. (Nature NPI Precision Oncology, 2023) 7473 biopsy cores were digitized, assessed for tumor detection and the results were compared with the findings of expert pathologists. “We show high levels of diagnostic accuracy for prostate cancer detection and agreement levels for Gleason grading comparable with experienced genitourinary pathologists.”

BOTTOM LINE

The application of artificial intelligence is becoming widespread in the field of prostate cancer with the promise of improving clinical practice.

Read More
PCa Commentary | Volume 182 – October 2023

PCa Commentary | Volume 182 – October 2023

Posted by | Oct 2023

Background

With the increased use of PSMA PET/CT scanning both at initial diagnosis of advanced prostate cancer and at disease recurrence, a substantial number of men will be found to have some extent of metastatic disease — either metastatic hormone-sensitive prostate cancer (mHSPC) or castration-resistant prostate cancer (CRPC). The second of these states will have arisen in what is termed ‘non-metastatic’ castration-resistant cancer (rising PSA despite castrate level of testosterone), in which, upon PET scanning, metastases are frequently identified. There is no current consensus regarding the appropriate treatment regimens for these disease states. Three options have been studied:

Metastases-directed radiation therapy only, i.e., no androgen deprivation therapy (ADT)
until progression
MDT combined with ADT
The newest option, MDT combined with intermittent hormone therapy (IHT)
Studies to date report that all three options prolong overall survival compared to ADT only.

Dividing mHSPC into High Tumor Burden vs Low Tumor Burden

Two major clinical trials (STAMPEDE and CHAARTED) have defined ‘high burden’ as: the presence of visceral metastases or four or more bone lesions one or more beyond the vertebral bodies and pelvis. These studies were based on standard CT and bone scans. This distinction between high and low burden disease has been developed to guide therapeutic regimens such as systemic treatment with Docetaxel with ADT +/- newer anti-androgen receptor agents i.e., Zytiga  or Xtandi) for high-burden disease. For low burden disease, MDT+/- ADT are options, including ablation of the prostate.

An early trial reported by Palma et al, Lancet 2019, established that MDT alone for men with 1-5
metastases had a superior overall survival than ADT only (SABR-COMET trial). Currently recruiting is NCT03721341 using MDT for treatment of 4-10 oligometastatic lesions combined with a variety of standard of care options as selected by the treating physician vs any chosen treatment option but without MDT.

Currently recent and ongoing studies in low burden disease focus on avoiding ADT until disease progression thus avoiding ADT toxicity.

New Techniques Under Development for Estimating Prognosis

Patient selection for MDT is currently best made with PSMA PET/CT scanning, which offers greater sensitivity than conventional imaging. Research is developing techniques to predict prognosis with greater sensitivity. One promising option is assessing the metabolic aggressiveness of the metastatic lesions under consideration for MDT by measuring the  PET SUV (specific uptake value) of individual lesions. SUV is a measure of cancer aggressiveness. In this assessment the SUVmax is calculated, which totals the combined metabolic activity of all the lesions. This requires special technology.

However, the mHSPC disease state is a heterogeneous collection of members each with different
biological behavior and a different risk of progression. An estimate of prognoses for a man with
mHSPC can be assessed by applying the genomic classifier Decipher on tissue from the primary.
A more technologically advanced assessment of biological behavior would be evaluating
microRNA or circulating tumor DNA in blood.

Initial Studies: The ORIOLE and STOMP trials of MDT 

The above-named studies were two early randomized trials of mHSPC employed MDT (with stereotactic radiation therapy) versus observation only in men with 3 or fewer metastatic sites.

The outcome of both trials (as reviewed by Deek et al., JCO 2022), was a prolongation of progression-free survival (PFS) in both studies. MDT targeted three or fewer lesions based on CT and bone scans in each man in the MDT arm. Progression-free survival was superior in both trials compared to observation only with a pooled median PFS of 11.9 months in the MDT arms and 5.9 months with observation only. Men in the study with high-risk mutations in the genes BRCA 1/2, ATM. RB1 and TP53 who received MDT also benefited, but to a lesser extent with a median PFS of 7.5 months.

In the ORIOLE trial at onset, in addition to CT and bone scans, men also had PSMA PET scans. The PET scans detected a total of 36 lesions of which 16 had not been seen on the CT and bone scans, emphasizing the importance of basing MDT on imaging with PSMA PET/CT.

The EXTEND Trial (NCT03599765)

The question addressed in “Addition of Metastases-Directed Therapy to Intermittent
Hormone Therapy for Oligometastatic Prostate Cancer,” Tang et al., JAMA Oncol. 2023, was “Does the addition of metastasis-directed therapy to intermittent hormone therapy improve progression-free survival for men with oligometastatic prostate cancer?” The study anticipated that the known “synergy” between hormone therapy and radiation therapy, would benefit the MDT treated group. MDT was delivered with the CyberKnife to 5 or fewer lesions. The study was randomized 1:1 between those receiving MDT therapy plus IHT and those receiving IHT only. The participants were stratified by the number of metastatic lesions (1-2 vs 3-5). All men received radiation to the prostate. Although some had received varying periods of HT pre-study, at trial onset androgen suppression was delivered for 6 months, after which hormone therapy was withheld until progression. Progression was defined as clinical or a PSA rise of greater than 25% or greater than 2 ng/mL above the nadir.

Both the ORIOLE and EXTEND trials found evidence that the immune system was sensitized to
attack metastatic sites that were too small to be imaged. The presumed explanation: In
destroying the targeted lesions intracellular proteins were released that sensitized T-cells to
attack additional metastatic site too small to be imaged.

Results  

At the time of the report’s analysis the median PFS had not been reached in the MDT /IHT arm but was 15.8 months in the IHT-only group.

A secondary goal of the trial was to prolong the duration during which the testosterone level was near normal. After stopping  ADT at 6 months the men in IHT group experienced testosterone levels greater than 150 ng/dL (low normal) for only 6 months before disease progression. In the MDT/IHT arm the median duration of having a testosterone level about 150 ng/dL had not been determined at the time of data analysis.

The trial reached its goal: By adding MDT to intermittent androgen suppression PFS was prolonged and the duration of normal testosterone level before progression was extended compared to intermittent hormone therapy only.

BOTTOM LINE

The increased use of PSMA scanning at the time of diagnosis is associated with an increased prevalence of metastatic hormone sensitive prostate cancer. A variety of treatment regimens using metastasis directed therapy (MDT) are under active study.

Read More
PCa Commentary | Volume 181 – September 2023

PCa Commentary | Volume 181 – September 2023

Posted by | Sep 2023

Background

The function of initial staging of prostate cancer is to accurately estimate the risk of progression in order to guide optimal therapy. The influential National Comprehensive Cancer Network (NCCN)
recommends a PSMA PET/CT as part of initial staging for men in the risk categories of intermediate- and high-risk cancer as defined by clinicopathologic features: PSA, Gleason score, clinical tumor stage and number of positive biopsy cores. For men with a life expectancy of >10 years molecular analysis (i.e., Decipher, Prolaris or OncotypeDx Prostate) is suggested by the NCCN.

PSMA PET/CT in advanced cancer identifies lesions that are missed on conventional CT and bone scans. Yaxley et al., BJU Int 2019 reported the results of primary staging by PSMA PET/CT in 1253 men, half and half with intermediate and high-risk disease in the largest published study on this subject. Metastases were identified in 12.1%; 8.2% in men with PSA values <10 ng/ml and 47% with PSA values > 20 ng/mL. Segregated by Gleason Grade, metastases were found in 6.4% with GG 2-3 (Gleason 3+3 and 3+4). Extra-pelvic lymph nodes occurred in 47%. Bone metastases were found in 5.2% in men with intermediate-risk and in 20% high-risk cancer.

Enter the Immune System — Its Influence on Cancer Behavior

The influence of immune cell infiltration within the tumor and from the surrounding microenvironment is not taken into account in assigning a Gleason score and therefore is not considered in the NCCN classifications of risk. The variety of promoter and suppressive lymphocytes and macrophages that comprise these infiltrations are not fully identified under the microscope and play no role in standard risk assessments.

The immune microenvironment of the primary tumor influences both the initiation and early progression (i.e., toward a higher Gleason score) of the developing cancer. Immune elements compete (i.e., pro-tumor and anti-tumor) to suppress malignant clones from progressing — while others promote disorganization and aggressiveness. Protective cells include immune enhancing CD8+T-cells, Killer T-cells, protective macrophages; immune suppressive cells include T-regulation cells and immune suppressive macrophages. In fact, recent studies reveal that the ratio of one particular gene in anti-tumor macrophages to a different gene in pro-tumor macrophages can by itself determine the outcome in a man’s cancer — and possibly all cancers. (Bill et al., SCIENCE, Aug 2023).

These immune cellular elements are not only found within and surrounding tumors but also can be identified in the blood to various amounts. Based on their presence in the blood, Chinese researchers have “developed and validated a machine-learning nomogram for the prediction of risk stratification of prostate cancer based on subsets of these lymphocytes in the blood.” This nomogram functioned better than the standard NCCN prognostic risk groups. (Yang et al., Journal of Translational Medicine 2023.)

The Predictive Power of Artificial Intelligence

The genomic classifier Decipher has been multiply validated to estimate prognosis based on its risk scale of 0 to 1.0. However, AI has the capability to derive a prediction — for example of an individual man’s response to a given treatment. When whole mount pathology slides, multiply stained, are digitized into a scanner, the AI process identifies standard histology but also detects the subtypes of immune cells infiltrating the tumor and the surrounding microenvironment. This comprehensive analysis presents a complete picture of a man’s cancer, its predicted behavior and supports individualized management.

Two Examples of Clinically Useful Applications of AI for Intensifying or De-intensifying
Therapy

Commentary #180 discusses a study assessing the relative benefits of adding ADT to
radiation therapy in men with advanced cancer based on a derived biomarker.
At the 2023 annual meeting of the American Society of Clinical Oncology, Armstrong and
colleagues from Duke University presented their abstract, “Development and validation of an
AI-derived digital pathology-based biomarker to predict benefit of long-term androgen deprivation therapy with radiotherapy in men with localized high-risk prostate cancer across
multiple phase III NRG/RTOG trials,” i.e., a goal “to guide ADT duration to maximize benefits
and minimize risks.”
“Pre-treatment prostate biopsy slides were digitized from six randomized trials evaluating the
benefit of radiation therapy +/- ADT” in men with localized high-risk prostate cancer with end
points of distant metastases (DM) and prostate cancer-specific mortality. The data from this
training set was then validated in a major trial comparing radiation plus 4 vs. 28 months of ADT and determined a distinguishing biomarker. Their study found that 28 months of ADT was 13% better than 4 months in the biomarker-positive group as compared to only 2% better in the biomarker-negative group, a finding that could influence clinical decision-making.
[A spokesman for Artera AI.com said the company is working on developing a test based on this
study for commercial availability.]

BOTTOM LINE

PSMA PET/CT scans and applications of AI in prostate cancer management are aiding individualized patient management.

Read More
PCa Commentary | Volume 180 – August 2023

PCa Commentary | Volume 180 – August 2023

Posted by | Aug 2023

Background

Ever since 1675 when the Dutch lens maker, Leeuwenhoek, looked down the newly invented microscope at rainwater and reported seeing ‘animalcules – tiny dancing creatures” (bacteria), pathologists have been similarly looking down their scopes and guiding prostate management by applying their expertise in pattern recognition.

In the 1960s, Dr. Donald Gleason organized those patterns into doublets of 3, 4 (i.e., 3+4) and 5 to create the prognostic Gleason Score — now further refined. Anthony D’Amico, professor of Radiation Oncology at Harvard Medical School is credited for establishing prognostic categories segregating “risk of recurrence” into low-, intermediate- and high-risk prostate cancer (with intermediate-risk now subdivided into favorable” and “unfavorable.”)

[Google reminds us that “A prognostic biomarker provides information about the patient’s overall cancer outcome, regardless of therapy, whilst a predictive biomarker gives information about the effect of a therapeutic intervention.”]

Feng, Spratt et al., have now advanced the art by generating a personalized precision predictive model by utilizing large data sets, machine learning and the less human-dependent “deep learning” — both components of artificial intelligence. Their analysis was directed toward discovering a biomarker that can predict which men with intermediate-risk prostate cancer benefit from the addition of ADT to radiotherapy.

Their study found that some men gained much, but others only minimally. Previous data has found that only 60% of men with intermediate-risk cancer benefit from the addition of ADT to radiotherapy — although those with “unfavorable” intermediate-risk benefit more so. The challenge was identifying who benefits and who does not.

The Spratt AI Study

“Artificial Intelligence Predictive Model for Hormone Therapy Use in Prostate Cancer,” NEJM Evidence, June 29, 2023., by Dr. Daniel Spratt with many collaborators on behalf of NRG Prostate Cancer AI Consortium.

Dr. Spratt: “With the first-ever predictive biomarker of ADT benefit in prostate cancer, created with AI, we are able to further realize the ability to create a personalized approach for the treatment of cancer.” (Quoted in Precision Medicine News, 2023).

The study was based on “digitized pathology images of pretreatment prostate tissue and clinical data of 5727 patients enrolled in 5 phase 3 randomized trials in which treatment was radiotherapy with or without ADT.” The goal was to develop a binary model to predict the benefit from short-term ADT regarding the likelihood of developing distant metastases.

The article notes that androgen deprivation therapy (ADT) is customarily combined with radiation treatment in this setting. These were trials of radiation treatment for higher grades of prostate cancer, in which there are “no validated predictive models to guide its use.”

Spratt’s colleagues endeavored to establish such a guide – a binary determinant for men with localized intermediate-risk cancer predicting whether “a given patient will benefit from ADT or not“ based on the risk of time to developing distant metastases. They generated such a model by analyzing 4 major randomized clinical trials comparing radiation therapy alone or combined with ADT.

“Data from these trials were acquired and digitized and then were used to train a predictive AI model” to predict the differential benefit of ADT according to their biomarker status. Their image extraction method was described: “For each patient, the tissue across all available digital slides was divided into 256 x 256-pixel patches. … [and the] model was trained on image patches using self-supervised learning. Over 2.5 million tissue patches across four trials … were fed through the model 200 times to train the model.”

The next step was to take this predictive model and validate it using data from RTOG trial 9408 which randomized men with intermediate-risk cancer to radiation treatment plus or minus 4 months of ADT. By applying the AI-derived model, the 15-year estimate for developing distant metastases for biomarker-positive patients treated with ADT was 4% v 14.4% for biomarker-negative ADT patients. In developing their biomarker, they found the best cut-point was 67% for segregating biomarker-positive from biomarker-negative.

By applying the biomarker established in the development model, 543 men were biomarker-positive, indicating that ADT “significantly reduced (by 10.5 percentage points) the risk of distant metastases at 15 years compared to radiotherapy alone.” For 1051 biomarker-negative patients ADT conferred minimal benefit (percentage point benefit 0.5%). For prostate cancer-specific mortality, the comparison of benefits was 10.2% and 1.2%, respectively.

Dr. Spratt concluded, “Our AI-based predictive model was able to identify patients with a predominantly intermediate risk for prostate cancer likely to benefit from short-term ADT.” In an interview with ‘News Wise’ Dr. Spratt said: “We are fortunate to be already offering this test at UH Seidman Cancer Center, Case Western Reserve University, to our patients from Northwest Ohio, our nation, and around the world.” (Quoted in News Wise, June 2023)

BOTTOM LINE

The article reviewed in this Commentary is a prime example of how Artificial Intelligence can benefit the clinical management of prostate cancer.

From Artera.ai: “The ArteraAI Prostate Test is a Laboratory Developed Test that is now clinically available through a single CLIA-certified laboratory in Jacksonville, FL. Clinicians who would like to order the ArteraAI Prostate Test can contact us at support@artera.ai. Soon after, a member of our Customer Success team will reach out to set up an account in the ArteraAI Portal to enable order submission.”

Read More

Join the GRU Community

- Why Join? -