SlideShare a Scribd company logo
1 of 1
Download to read offline
/ Department of Industrial Engineering & Innovation Sciences
/ Information Systems Group
Patient-specific Management of Adrenal Incidentalomas
J.B.R. Visser - U. Kaymak - R.J. Almeida - J.J. Visser - M. van der Meijden
From Predictive towards
Prescriptive Analytics
Introduction
Adrenal incidentaloma (AI)
An adrenal mass (> 1 cm) detected on
imaging studies performed for indications
other than adrenal disease [1]. Prevalence
of AI on CT is 1-4.1% [2].
Management of adrenal incidentalomas
The challenge is to recognize and treat the small percentage of
clinically relevant incidentalomas that pose a significant risk.
Clinically relevant findings are malignant, cause hormonal
hyperfunction or grow significantly.
Research objectives
There is demand for a patient-specific management strategy
that offers multiple moments at which we want to decide
whether or not to continue AI work-up. Two objectives that
guide us from predictive towards prescriptive analytics are:
1.		 Develop a clinical prediction model to predict if an
adrenal incidentaloma is clinically relevant.
2. 		 Derive a prescriptive model for patient-specific
management of patients with adrenal incidentalomas.
Prescriptive modeling
Integrate prediction models in Erasmus MC daily practice
using decision curve analysis and BPMN 2.0 (figure 2).
Conclusion and Future Work
This research resulted in a prescriptive model based on three
predictive models that predict if a patient will have a clinically
relevant outcome at two moments during adrenal inciden-
taloma work-up. Direction for future research are:
»» Implement additional decision moments by refining the
dataset with imaging variables from CT follow-up.
»» Perform external validation and enlarge dataset.
References
[1]	 Mansmann et al., (2004). The Clinically Inapparent Adrenal Mass: Update in Diagnosis and
Management. Endocrine Reviews
[2]	 Davenport et al., (2011). The Prevalence of Adrenal Incidentaloma in Routine Clinical Practice.
Endocrine
Results
Predictive models
Perform very good on the over-sampled test sets. Results
on the original validation sets are good but fluctuating
Prescriptive model
Patients that are not clinically relevant whose work-up was
rightly stopped based on the validation data:
»» M1: 15% of 96 patients saved from unnecessary work-up
»» M2: 25% of 16 patients saved from unnecessary work-up
All clinically relevant patients remained in the work-up.
Prescriptive Model
ErasmusMC
Radiology
Radiology Radiology
Imaging follow-up 1:
Non-contrast CT
Imaging follow-up:
CT
growth or
malignant
End AI
work-up
3-6 months
12 months
3 CT in total?
growth or
malignant
Perform CT exam
(inspect images
immediately)
AI found?
Assess patient
situation
Run Prediction
Model M1
Start AI
work-up?
End AI
work-up
End AI
work-up
Referring
Department
Referring Department Referring Department
Request CT
abdomen/thorax
Surgery
Surgery Surgery
Adrenal vein
sampling
Adrenalectomy
End AI
work-up
Endocrinology
Endocrinology Endocrinology
Endocrinologist visit 1:
Evaluate results
Patient history and
physical examination
Aldosterone
needed? Endocrinologist visit 2:
Evaluate results
Hormonal
hyperfunction?
Age > 40 and
hypertension?
Size > 4-6 cm?
Run Prediction
Model M2
Continue
work-up?
End AI
work-up
Laboratory
Laboratory Laboratory
Perform lab tests:
CS, FEO
Perform lab test:
PA
1 day 1 day
no
yes
yes
no
yes
yes
no
yes
no
no
no
yes
no
no
yes
yes
Figure 2: Prescriptive model for patient-specific management of adrenal incidentalomas
Figure 1: Experimental design for prediction models M1
Methods
Patient identification & data collection
Apply text mining to all radiology reports from 2010 till 2012
resulting in 643 patients. Patient data, lab test data, medica-
tion data and work-up data are collected. Of these adrenal
incidentalomas 5.3% are clinically relevant.
Predictive modeling
Construct three prediction models at decision moments:
»» M1: At the moment of finding (figure 1)
»» M2: After biochemical screening
The experimental design is identical for both moments.

More Related Content

What's hot

Bias in covid 19 models
Bias in covid 19 modelsBias in covid 19 models
Bias in covid 19 modelsLaure Wynants
 
DISEASE PREDICTION SYSTEM USING DATA MINING
DISEASE PREDICTION SYSTEM USING  DATA MININGDISEASE PREDICTION SYSTEM USING  DATA MINING
DISEASE PREDICTION SYSTEM USING DATA MININGshivaniyadav112
 
Quality Assurance At Wellspring
Quality Assurance At WellspringQuality Assurance At Wellspring
Quality Assurance At WellspringRobert J Miller MD
 
Physician resistance as a barrier to implement clinical information systems b...
Physician resistance as a barrier to implement clinical information systems b...Physician resistance as a barrier to implement clinical information systems b...
Physician resistance as a barrier to implement clinical information systems b...Healthcare consultant
 
How does machine learning help in cancer detection
How does machine learning help in cancer detection How does machine learning help in cancer detection
How does machine learning help in cancer detection GlobalTechCouncil
 
Humphrey gpa overview training edition.v.2
Humphrey gpa overview   training edition.v.2Humphrey gpa overview   training edition.v.2
Humphrey gpa overview training edition.v.2Hossein Mirzaie
 
A Novel Approach for Breast Cancer Detection using Data Mining Techniques
A Novel Approach for Breast Cancer Detection using Data Mining TechniquesA Novel Approach for Breast Cancer Detection using Data Mining Techniques
A Novel Approach for Breast Cancer Detection using Data Mining Techniquesahmad abdelhafeez
 
Automated Cervicography Using a Machine Learning Classifier
Automated Cervicography Using a Machine Learning ClassifierAutomated Cervicography Using a Machine Learning Classifier
Automated Cervicography Using a Machine Learning ClassifierMobileODT
 
amylase poster
amylase posteramylase poster
amylase posterthad88
 
Predictive Analytics in Healthcare
Predictive Analytics in HealthcarePredictive Analytics in Healthcare
Predictive Analytics in HealthcareICFAIEDGE
 
Device Impact on Machine Learning Classifier Accuracy in Detecting Cervical D...
Device Impact on Machine Learning Classifier Accuracy in Detecting Cervical D...Device Impact on Machine Learning Classifier Accuracy in Detecting Cervical D...
Device Impact on Machine Learning Classifier Accuracy in Detecting Cervical D...Sara Lynn Vehling
 
Breast cancer diagnosis machine learning ppt
Breast cancer diagnosis machine learning pptBreast cancer diagnosis machine learning ppt
Breast cancer diagnosis machine learning pptAnkitGupta1476
 
A Practical Computer Program That Diagnoses Diseases In Actual Patients
A Practical Computer Program That Diagnoses Diseases In Actual PatientsA Practical Computer Program That Diagnoses Diseases In Actual Patients
A Practical Computer Program That Diagnoses Diseases In Actual PatientsCarlos Feder
 
From Big Data to Precision Medicine
From Big Data to Precision Medicine From Big Data to Precision Medicine
From Big Data to Precision Medicine Year of the X
 
Mammographyqualitycontrol 190821134226
Mammographyqualitycontrol 190821134226Mammographyqualitycontrol 190821134226
Mammographyqualitycontrol 190821134226fairoozfathi
 
Performance of automated visual evaluation as a triage test for HPV+ patients...
Performance of automated visual evaluation as a triage test for HPV+ patients...Performance of automated visual evaluation as a triage test for HPV+ patients...
Performance of automated visual evaluation as a triage test for HPV+ patients...MobileODT
 

What's hot (19)

Bias in covid 19 models
Bias in covid 19 modelsBias in covid 19 models
Bias in covid 19 models
 
DISEASE PREDICTION SYSTEM USING DATA MINING
DISEASE PREDICTION SYSTEM USING  DATA MININGDISEASE PREDICTION SYSTEM USING  DATA MINING
DISEASE PREDICTION SYSTEM USING DATA MINING
 
Quality Assurance At Wellspring
Quality Assurance At WellspringQuality Assurance At Wellspring
Quality Assurance At Wellspring
 
Cspine clearance
Cspine clearanceCspine clearance
Cspine clearance
 
Physician resistance as a barrier to implement clinical information systems b...
Physician resistance as a barrier to implement clinical information systems b...Physician resistance as a barrier to implement clinical information systems b...
Physician resistance as a barrier to implement clinical information systems b...
 
AHRQ POSTER
AHRQ POSTER AHRQ POSTER
AHRQ POSTER
 
How does machine learning help in cancer detection
How does machine learning help in cancer detection How does machine learning help in cancer detection
How does machine learning help in cancer detection
 
Humphrey gpa overview training edition.v.2
Humphrey gpa overview   training edition.v.2Humphrey gpa overview   training edition.v.2
Humphrey gpa overview training edition.v.2
 
A Novel Approach for Breast Cancer Detection using Data Mining Techniques
A Novel Approach for Breast Cancer Detection using Data Mining TechniquesA Novel Approach for Breast Cancer Detection using Data Mining Techniques
A Novel Approach for Breast Cancer Detection using Data Mining Techniques
 
Automated Cervicography Using a Machine Learning Classifier
Automated Cervicography Using a Machine Learning ClassifierAutomated Cervicography Using a Machine Learning Classifier
Automated Cervicography Using a Machine Learning Classifier
 
amylase poster
amylase posteramylase poster
amylase poster
 
Predictive Analytics in Healthcare
Predictive Analytics in HealthcarePredictive Analytics in Healthcare
Predictive Analytics in Healthcare
 
Device Impact on Machine Learning Classifier Accuracy in Detecting Cervical D...
Device Impact on Machine Learning Classifier Accuracy in Detecting Cervical D...Device Impact on Machine Learning Classifier Accuracy in Detecting Cervical D...
Device Impact on Machine Learning Classifier Accuracy in Detecting Cervical D...
 
Breast cancer diagnosis machine learning ppt
Breast cancer diagnosis machine learning pptBreast cancer diagnosis machine learning ppt
Breast cancer diagnosis machine learning ppt
 
A Practical Computer Program That Diagnoses Diseases In Actual Patients
A Practical Computer Program That Diagnoses Diseases In Actual PatientsA Practical Computer Program That Diagnoses Diseases In Actual Patients
A Practical Computer Program That Diagnoses Diseases In Actual Patients
 
1115 fiztgerald schuchardt
1115 fiztgerald schuchardt1115 fiztgerald schuchardt
1115 fiztgerald schuchardt
 
From Big Data to Precision Medicine
From Big Data to Precision Medicine From Big Data to Precision Medicine
From Big Data to Precision Medicine
 
Mammographyqualitycontrol 190821134226
Mammographyqualitycontrol 190821134226Mammographyqualitycontrol 190821134226
Mammographyqualitycontrol 190821134226
 
Performance of automated visual evaluation as a triage test for HPV+ patients...
Performance of automated visual evaluation as a triage test for HPV+ patients...Performance of automated visual evaluation as a triage test for HPV+ patients...
Performance of automated visual evaluation as a triage test for HPV+ patients...
 

Viewers also liked

Adrenal masses on FDG PET
Adrenal masses on FDG PETAdrenal masses on FDG PET
Adrenal masses on FDG PETadamshu
 
Adrenal and other retroperitoneal masses
Adrenal and other retroperitoneal massesAdrenal and other retroperitoneal masses
Adrenal and other retroperitoneal massesPhilipp Steiger
 
Adrenal gland diseases and tumors
Adrenal gland diseases and tumorsAdrenal gland diseases and tumors
Adrenal gland diseases and tumorsMD Patholgoy, AFMC
 
Imaging of the adrenal glands
Imaging of the adrenal glands Imaging of the adrenal glands
Imaging of the adrenal glands Satish Naga
 
Mri u buồng trứng
Mri u buồng trứngMri u buồng trứng
Mri u buồng trứngNgoan Pham
 
The adrenal gland, catecholamine synthesis
The adrenal gland, catecholamine synthesisThe adrenal gland, catecholamine synthesis
The adrenal gland, catecholamine synthesisAtif Khirelsied
 
Adrenal gland tumors (Radiology)
Adrenal gland tumors (Radiology)Adrenal gland tumors (Radiology)
Adrenal gland tumors (Radiology)Dr Abdalla M. Gamal
 

Viewers also liked (9)

Adrenal masses on FDG PET
Adrenal masses on FDG PETAdrenal masses on FDG PET
Adrenal masses on FDG PET
 
Adrenal and other retroperitoneal masses
Adrenal and other retroperitoneal massesAdrenal and other retroperitoneal masses
Adrenal and other retroperitoneal masses
 
Adrenal gland diseases and tumors
Adrenal gland diseases and tumorsAdrenal gland diseases and tumors
Adrenal gland diseases and tumors
 
Imaging of the adrenal glands
Imaging of the adrenal glands Imaging of the adrenal glands
Imaging of the adrenal glands
 
Mri u buồng trứng
Mri u buồng trứngMri u buồng trứng
Mri u buồng trứng
 
The adrenal gland, catecholamine synthesis
The adrenal gland, catecholamine synthesisThe adrenal gland, catecholamine synthesis
The adrenal gland, catecholamine synthesis
 
Adrenal Tumors
Adrenal TumorsAdrenal Tumors
Adrenal Tumors
 
Adreno cortical tumors
Adreno cortical tumorsAdreno cortical tumors
Adreno cortical tumors
 
Adrenal gland tumors (Radiology)
Adrenal gland tumors (Radiology)Adrenal gland tumors (Radiology)
Adrenal gland tumors (Radiology)
 

Similar to Poster_Visser2015

CDAC 2018 Elemento A precision medicine
CDAC 2018 Elemento A precision medicineCDAC 2018 Elemento A precision medicine
CDAC 2018 Elemento A precision medicineMarco Antoniotti
 
IRJET - Classifying Breast Cancer Tumour Type using Convolution Neural Netwo...
IRJET  - Classifying Breast Cancer Tumour Type using Convolution Neural Netwo...IRJET  - Classifying Breast Cancer Tumour Type using Convolution Neural Netwo...
IRJET - Classifying Breast Cancer Tumour Type using Convolution Neural Netwo...IRJET Journal
 
i.a.Preoperative ovarian cancer diagnosis using neuro fuzzy approach
i.a.Preoperative ovarian cancer diagnosis using neuro fuzzy approachi.a.Preoperative ovarian cancer diagnosis using neuro fuzzy approach
i.a.Preoperative ovarian cancer diagnosis using neuro fuzzy approachJonathan Josue Cid Galiot
 
Performance Evaluation using Supervised Learning Algorithms for Breast Cancer...
Performance Evaluation using Supervised Learning Algorithms for Breast Cancer...Performance Evaluation using Supervised Learning Algorithms for Breast Cancer...
Performance Evaluation using Supervised Learning Algorithms for Breast Cancer...IRJET Journal
 
A Review on Data Mining Techniques for Prediction of Breast Cancer Recurrence
A Review on Data Mining Techniques for Prediction of Breast Cancer RecurrenceA Review on Data Mining Techniques for Prediction of Breast Cancer Recurrence
A Review on Data Mining Techniques for Prediction of Breast Cancer RecurrenceDr. Amarjeet Singh
 
Breast Cancer Prediction
Breast Cancer PredictionBreast Cancer Prediction
Breast Cancer PredictionIRJET Journal
 
ca cervix screening.pptx
ca cervix screening.pptxca cervix screening.pptx
ca cervix screening.pptxSeemadas31
 
Efficacy endpoints in Oncology
Efficacy endpoints in OncologyEfficacy endpoints in Oncology
Efficacy endpoints in OncologyAngelo Tinazzi
 
Study on Physicians Request for Computed Tomography Examinations for Patients...
Study on Physicians Request for Computed Tomography Examinations for Patients...Study on Physicians Request for Computed Tomography Examinations for Patients...
Study on Physicians Request for Computed Tomography Examinations for Patients...IRJESJOURNAL
 
PROactive evaluation of function to Avoid CardioToxicity
PROactive evaluation of function to Avoid CardioToxicityPROactive evaluation of function to Avoid CardioToxicity
PROactive evaluation of function to Avoid CardioToxicitydirectoricos
 
Galena presentation 8 feb 16
Galena presentation  8 feb 16Galena presentation  8 feb 16
Galena presentation 8 feb 16Galenabio
 
Whole body screening – risks and benefits
Whole body screening – risks and benefitsWhole body screening – risks and benefits
Whole body screening – risks and benefitsWan Najwa Zaini
 
IRJET- Breast Cancer Prediction using Support Vector Machine
IRJET-  	  Breast Cancer Prediction using Support Vector MachineIRJET-  	  Breast Cancer Prediction using Support Vector Machine
IRJET- Breast Cancer Prediction using Support Vector MachineIRJET Journal
 
NY Prostate Cancer Conference - A. Vickers - Session 8: Debate 2: Categorical...
NY Prostate Cancer Conference - A. Vickers - Session 8: Debate 2: Categorical...NY Prostate Cancer Conference - A. Vickers - Session 8: Debate 2: Categorical...
NY Prostate Cancer Conference - A. Vickers - Session 8: Debate 2: Categorical...European School of Oncology
 
Motion in Hadron therapy (radiotherapy)
Motion in Hadron therapy (radiotherapy)Motion in Hadron therapy (radiotherapy)
Motion in Hadron therapy (radiotherapy)siavashzare2
 
USING DATA MINING TECHNIQUES FOR DIAGNOSIS AND PROGNOSIS OF CANCER DISEASE
USING DATA MINING TECHNIQUES FOR DIAGNOSIS AND PROGNOSIS OF CANCER DISEASEUSING DATA MINING TECHNIQUES FOR DIAGNOSIS AND PROGNOSIS OF CANCER DISEASE
USING DATA MINING TECHNIQUES FOR DIAGNOSIS AND PROGNOSIS OF CANCER DISEASEIJCSEIT Journal
 

Similar to Poster_Visser2015 (20)

CDAC 2018 Elemento A precision medicine
CDAC 2018 Elemento A precision medicineCDAC 2018 Elemento A precision medicine
CDAC 2018 Elemento A precision medicine
 
IRJET - Classifying Breast Cancer Tumour Type using Convolution Neural Netwo...
IRJET  - Classifying Breast Cancer Tumour Type using Convolution Neural Netwo...IRJET  - Classifying Breast Cancer Tumour Type using Convolution Neural Netwo...
IRJET - Classifying Breast Cancer Tumour Type using Convolution Neural Netwo...
 
i.a.Preoperative ovarian cancer diagnosis using neuro fuzzy approach
i.a.Preoperative ovarian cancer diagnosis using neuro fuzzy approachi.a.Preoperative ovarian cancer diagnosis using neuro fuzzy approach
i.a.Preoperative ovarian cancer diagnosis using neuro fuzzy approach
 
Performance Evaluation using Supervised Learning Algorithms for Breast Cancer...
Performance Evaluation using Supervised Learning Algorithms for Breast Cancer...Performance Evaluation using Supervised Learning Algorithms for Breast Cancer...
Performance Evaluation using Supervised Learning Algorithms for Breast Cancer...
 
Improving patient safety through culture &evidence based practices
Improving patient safety through culture &evidence based practicesImproving patient safety through culture &evidence based practices
Improving patient safety through culture &evidence based practices
 
A Review on Data Mining Techniques for Prediction of Breast Cancer Recurrence
A Review on Data Mining Techniques for Prediction of Breast Cancer RecurrenceA Review on Data Mining Techniques for Prediction of Breast Cancer Recurrence
A Review on Data Mining Techniques for Prediction of Breast Cancer Recurrence
 
Breast Cancer Prediction
Breast Cancer PredictionBreast Cancer Prediction
Breast Cancer Prediction
 
ca cervix screening.pptx
ca cervix screening.pptxca cervix screening.pptx
ca cervix screening.pptx
 
Efficacy endpoints in Oncology
Efficacy endpoints in OncologyEfficacy endpoints in Oncology
Efficacy endpoints in Oncology
 
Study on Physicians Request for Computed Tomography Examinations for Patients...
Study on Physicians Request for Computed Tomography Examinations for Patients...Study on Physicians Request for Computed Tomography Examinations for Patients...
Study on Physicians Request for Computed Tomography Examinations for Patients...
 
PROactive evaluation of function to Avoid CardioToxicity
PROactive evaluation of function to Avoid CardioToxicityPROactive evaluation of function to Avoid CardioToxicity
PROactive evaluation of function to Avoid CardioToxicity
 
Galena presentation 8 feb 16
Galena presentation  8 feb 16Galena presentation  8 feb 16
Galena presentation 8 feb 16
 
Cytoreductive nephrectomy
Cytoreductive nephrectomyCytoreductive nephrectomy
Cytoreductive nephrectomy
 
Whole body screening – risks and benefits
Whole body screening – risks and benefitsWhole body screening – risks and benefits
Whole body screening – risks and benefits
 
D5 efficacy endpoints in oncology
D5   efficacy endpoints in oncologyD5   efficacy endpoints in oncology
D5 efficacy endpoints in oncology
 
IRJET- Breast Cancer Prediction using Support Vector Machine
IRJET-  	  Breast Cancer Prediction using Support Vector MachineIRJET-  	  Breast Cancer Prediction using Support Vector Machine
IRJET- Breast Cancer Prediction using Support Vector Machine
 
2012, Veeravagu, et al, IM SC Mets, Contemp NS
2012, Veeravagu, et al, IM SC Mets, Contemp NS2012, Veeravagu, et al, IM SC Mets, Contemp NS
2012, Veeravagu, et al, IM SC Mets, Contemp NS
 
NY Prostate Cancer Conference - A. Vickers - Session 8: Debate 2: Categorical...
NY Prostate Cancer Conference - A. Vickers - Session 8: Debate 2: Categorical...NY Prostate Cancer Conference - A. Vickers - Session 8: Debate 2: Categorical...
NY Prostate Cancer Conference - A. Vickers - Session 8: Debate 2: Categorical...
 
Motion in Hadron therapy (radiotherapy)
Motion in Hadron therapy (radiotherapy)Motion in Hadron therapy (radiotherapy)
Motion in Hadron therapy (radiotherapy)
 
USING DATA MINING TECHNIQUES FOR DIAGNOSIS AND PROGNOSIS OF CANCER DISEASE
USING DATA MINING TECHNIQUES FOR DIAGNOSIS AND PROGNOSIS OF CANCER DISEASEUSING DATA MINING TECHNIQUES FOR DIAGNOSIS AND PROGNOSIS OF CANCER DISEASE
USING DATA MINING TECHNIQUES FOR DIAGNOSIS AND PROGNOSIS OF CANCER DISEASE
 

Poster_Visser2015

  • 1. / Department of Industrial Engineering & Innovation Sciences / Information Systems Group Patient-specific Management of Adrenal Incidentalomas J.B.R. Visser - U. Kaymak - R.J. Almeida - J.J. Visser - M. van der Meijden From Predictive towards Prescriptive Analytics Introduction Adrenal incidentaloma (AI) An adrenal mass (> 1 cm) detected on imaging studies performed for indications other than adrenal disease [1]. Prevalence of AI on CT is 1-4.1% [2]. Management of adrenal incidentalomas The challenge is to recognize and treat the small percentage of clinically relevant incidentalomas that pose a significant risk. Clinically relevant findings are malignant, cause hormonal hyperfunction or grow significantly. Research objectives There is demand for a patient-specific management strategy that offers multiple moments at which we want to decide whether or not to continue AI work-up. Two objectives that guide us from predictive towards prescriptive analytics are: 1. Develop a clinical prediction model to predict if an adrenal incidentaloma is clinically relevant. 2. Derive a prescriptive model for patient-specific management of patients with adrenal incidentalomas. Prescriptive modeling Integrate prediction models in Erasmus MC daily practice using decision curve analysis and BPMN 2.0 (figure 2). Conclusion and Future Work This research resulted in a prescriptive model based on three predictive models that predict if a patient will have a clinically relevant outcome at two moments during adrenal inciden- taloma work-up. Direction for future research are: »» Implement additional decision moments by refining the dataset with imaging variables from CT follow-up. »» Perform external validation and enlarge dataset. References [1] Mansmann et al., (2004). The Clinically Inapparent Adrenal Mass: Update in Diagnosis and Management. Endocrine Reviews [2] Davenport et al., (2011). The Prevalence of Adrenal Incidentaloma in Routine Clinical Practice. Endocrine Results Predictive models Perform very good on the over-sampled test sets. Results on the original validation sets are good but fluctuating Prescriptive model Patients that are not clinically relevant whose work-up was rightly stopped based on the validation data: »» M1: 15% of 96 patients saved from unnecessary work-up »» M2: 25% of 16 patients saved from unnecessary work-up All clinically relevant patients remained in the work-up. Prescriptive Model ErasmusMC Radiology Radiology Radiology Imaging follow-up 1: Non-contrast CT Imaging follow-up: CT growth or malignant End AI work-up 3-6 months 12 months 3 CT in total? growth or malignant Perform CT exam (inspect images immediately) AI found? Assess patient situation Run Prediction Model M1 Start AI work-up? End AI work-up End AI work-up Referring Department Referring Department Referring Department Request CT abdomen/thorax Surgery Surgery Surgery Adrenal vein sampling Adrenalectomy End AI work-up Endocrinology Endocrinology Endocrinology Endocrinologist visit 1: Evaluate results Patient history and physical examination Aldosterone needed? Endocrinologist visit 2: Evaluate results Hormonal hyperfunction? Age > 40 and hypertension? Size > 4-6 cm? Run Prediction Model M2 Continue work-up? End AI work-up Laboratory Laboratory Laboratory Perform lab tests: CS, FEO Perform lab test: PA 1 day 1 day no yes yes no yes yes no yes no no no yes no no yes yes Figure 2: Prescriptive model for patient-specific management of adrenal incidentalomas Figure 1: Experimental design for prediction models M1 Methods Patient identification & data collection Apply text mining to all radiology reports from 2010 till 2012 resulting in 643 patients. Patient data, lab test data, medica- tion data and work-up data are collected. Of these adrenal incidentalomas 5.3% are clinically relevant. Predictive modeling Construct three prediction models at decision moments: »» M1: At the moment of finding (figure 1) »» M2: After biochemical screening The experimental design is identical for both moments.