Effect of palliative care decisions making on hospital service use at end-of-life in patients with malignant brain tumors: a retrospective study.

BACKGROUND: Palliative care (PC) improves Quality of life and reduces the symptom burden. Aggressive treatments at end of life (EOL) postpone PC. The aim of this single-center retrospective study was to evaluate the timing of the PC decision i.e., termination of cancer-specific treatments and focusing on symptom-centered PC, and its impact on the use of tertiary hospital services at the EOL. METHODS: A retrospective cohort study on brain tumor patients, who were treated at the Comprehensive Cancer Center of the Helsinki University Hospital from November 1993 to December 2014 and died between January 2013 and December 2014, were retrospectively reviewed. The analysis comprised 121 patients (76 glioblastoma multiforme, 74 males; mean age 62 years; range 26-89). The decision for PC, emergency department (ED) visits and hospitalizations were collected from hospital records. RESULTS: The PC decision was made for 78% of the patients. The median survival after diagnosis was 16 months (13 months patients with glioblastoma), and after the PC decision, it was 44 days (range 1-293). 31% of the patients received anticancer treatments within 30 days and 17% within the last 14 day before death. 22% of the patients visited an ED, and 17% were hospitalized during the last 30 days of life. Of the patients who had a PC decision made more than 30 days prior to death, only 4% visited an ED or were hospitalized in a tertiary hospital in the last 30 days of life compared to patients with a late (< 30 days prior to death) or no PC decision (25 patients, 36%). CONCLUSIONS: Every third patient with malignant brain tumors had anticancer treatments during the last month of life with a significant number of ED visits and hospitalizations. Postponing the PC decision to the last month of life increases the risk of tertiary hospital resource use at EOL.

End-of-life care among patients with pancreatic cancer with or without palliative intervention: a retrospective single-centre study.

INTRODUCTION: Palliative care can reduce the symptom burden and may increase the life expectancy for patients with advanced malignancies. The aim of this study was to evaluate the impact of palliative intervention on the treatment procedures for pancreatic cancer patients during their last month of life. MATERIAL AND METHODS: This retrospective single-centre study included adult pancreatic cancer patients who were treated in Turku University Hospital during their last month of life and died between 2011 and 2016. Data were collected from hospital database. Oncological treatments, the number of radiological examinations and procedures, surgical procedures, emergency department visits, hospitalisations, the place of death and medical costs were examined in tertiary care for patients with or without contact to the palliative care unit. RESULTS: From 378 eligible patients, 20% (n = 76) had a contact to the palliative care unit. These patients had less radiological examinations (p < 0.0001), hospitalisations (p <0.0001) and emergency department visits (p = 0.021) during the last month of life. They did not die in the university hospital as often (p = 0.011) and median of their medical costs during the last month of life was approximately half (p <0.0001) when compared to patients with no palliative intervention (n = 302). They had longer overall survival (p <0.0001) which was the only difference detected in the characteristics of the groups. CONCLUSION: Fewer treatment procedures and lower tertiary care costs during the last month of life were observed for the pancreatic cancer patients who had a contact to the palliative care unit. Palliative care intervention should be an essential part of the treatment schedule for these patients.

The impact of the duration of the palliative care period on cancer patients with regard to the use of hospital services and the place of death: a retrospective cohort study.

BACKGROUND: In order to avoid unnecessary use of hospital services at the end-of-life, palliative care should be initiated early enough in order to have sufficient time to initiate and carry out good quality advance care planning (ACP). This single center study assesses the impact of the PC decision and its timing on the use of hospital services at EOL and the place of death. METHODS: A randomly chosen cohort of 992 cancer patients treated in a tertiary hospital between Jan 2013 -Dec 2014, who were deceased by the end of 2014, were selected from the total number of 2737 identified from the hospital database. The PC decision (the decision to terminate life-prolonging anticancer treatments and focus on symptom centered palliative care) and use of PC unit services were studied in relation to emergency department (ED) visits, hospital inpatient days and place of death. RESULTS: A PC decision was defined for 82% of the patients and 37% visited a PC unit. The earlier the PC decision was made, the more often patients had an appointment at the PC unit (> 180 days prior to death 72% and < 14 days 10%). The number of ED visits and inpatient days were highest for patients with no PC decision and lowest for patients with both a PC decision and an PC unit appointment (60 days before death ED visits 1.3 vs 0.8 and inpatient days 9.9 vs 2.9 respectively, p < 0.01). Patients with no PC decision died more often in secondary/tertiary hospitals (28% vs. 19% with a PC decision, and 6% with a decision and an appointment to a PC unit). CONCLUSIONS: The PC decision to initiate a palliative goal for the treatment had a distinct impact on the use of hospital services at the EOL. Contact with a PC unit further increased the likelihood of EOL care at primary care.

Assessing the utilization of the decision to implement a palliative goal for the treatment of cancer patients during the last year of life at Helsinki University Hospital: a historic cohort study.

Background: To avoid aggressive treatments at the end-of-life and to provide palliative care (PC), physicians need to terminate futile anti-cancer treatments and define the palliative goal of the treatment in time. This single center study assesses the practices used to make the decision that leads to treatment with a palliative goal, i.e., the PC decision and its effect on anti-cancer treatments at the end of life.Material and methods: Patients with a cancer diagnosis treated in tertiary hospital during 1st January 2013 - 31st December 2014 and deceased by the end of 2014 were identified in the hospital database (N = 2737). Of these patients, 992 were randomly selected for this study. The PC decision was screened from patient records, i.e., termination of cancer-specific treatments and a focus on symptom-centered PC.Results: The PC decision was defined in 82% of the patients during the last year of life (49% >30 days and 33% ≤30 days before death, 18% with no decision). The median time from the decision to death was 46 days. Systemic cancer therapy was given during the last month of life in 1%, 36% and 38% (p < .001) and radiotherapy 22%, 40% and 31% (p = .03) cases, respectively; referral to a PC unit was made in 62%, 22% and 11%, respectively (p < .001). In logistic regression analyses younger age, shorter duration of the disease trajectory and type of cancer (e.g., breast cancer) were associated with a lack or late timing of the PC decision.Conclusion: The decision to initiate a palliative goal for the treatment was frequently made for cancer patients but occurred late for every third patient. Younger age and certain cancer types were associated with late PC decisions, thus leading to anti-cancer treatments continuing until close to the death with low access to a PC unit.

End-of-life decisions guiding the palliative care of cancer patients visiting emergency department in South Western Finland: a retrospective cohort study.

BACKGROUND: Until recently, palliative care (PC) resources in Finland have been sparse. To meet the increasing need for PC an end-of-life (EOL) care project has been ongoing in South Western Finland since 2012, and in 2015, a weekday palliative outpatient clinic was established in Turku University Hospital (TUH). The aim of this study was to explore the effect of the project and the PC clinic on the management practices of EOL cancer patients attending the Emergency Department (ED) of TUH from 2013 to 2016. METHODS: The medical records of all cancer patients (ICD-10 codes C00-97) admitted to the ED of TUH between August 1-December 31, in 2013 and 2016, were analyzed: n = 529, n = 432 respectively (2013 and 2016). The analysis focused on those patients in EOL care; n = 77, n = 63, respectively. The late palliative patients were defined by PC decision, thus termination of life-prolonging cancer-specific treatments. The EOL patients were in the imminently dying phase of their illness. The site of referral after an ED visit was also verified together with the documentation on advance care plans (ACP), and the impact of palliative outpatient visits. RESULTS: In 2016, the number of late palliative and EOL patients admitted to the ED has shown a tendency to decrease. The quality of the documentation for treatment goals, do-not-resuscitate (DNR) orders, living wills and connections to primary care providers has improved since 2013. Prior visits to palliative outpatient clinic correlated well with the more comprehensive ACP information: i) DNR order (p = 0.0001); ii) connection to primary care (p = 0.003); iii) documented ICD-10 code Z51.5 (p = 0.0001). CONCLUSIONS: Even modest investments in resources for PC can induce an objective change in the allocation of health care resources, and improve the ACP for the cancer patients at their EOL. A visit to a palliative outpatient clinic may offer one approach for improving the quality and completion of ACP documentation.

End-of-life chemotherapy use at a Finnish university hospital: a retrospective cohort study.

BACKGROUND: Recent trends in the end-of-life (EOL) cancer care have suggested that the levels of treatment are becoming more aggressive. The aim of this single-center study was to evaluate the time from the last intravenous (IV) chemotherapy treatment to death and identify factors correlating with treatment closer to death. MATERIAL AND METHODS: The study included all patients diagnosed with cancer at Turku University Central Hospital between the years 2005 and 2013 (N = 38,982) who received IV chemotherapy during the last year of life (N = 3285). The cohort of patients and their respective clinical information were identified from electronic medical records. Statistical analysis was performed to assess and compare the treatment strategies, taking into account the patient's age, the year they were treated, and the type of cancer they were diagnosed with. RESULTS: A total of 11,250 cancer patients died during the observation time and one-third (N = 3285, 29.2%) of them had received IV chemotherapy during the last year of life. The time from the last IV chemotherapy regimen to death remained consistent across the follow-up time. During the last month of life, every third patient under the age of 50 years and only one-tenth of patients over the age of 80 years received IV chemotherapy. Hematological malignancies and lymphomas were treated closer to death when compared to other diagnostic groups. CONCLUSIONS: During the period of 9 years, the pattern of EOL IV chemotherapy treatment remained stable. Every third patient died at tertiary care. Only 7.2% of patients who received IV chemotherapy during the last year of life were treated 14 days before death, which is in line with international recommendations. However, significant variation in EOL treatment strategies between different diagnosis and age groups were identified.

Assessing the utilization of radiotherapy near end of life at a Finnish University Hospital: a retrospective cohort study.

BACKGROUND: Palliative radiotherapy can improve quality of life for cancer patients during the last months of life. However, very short life expectancy may devastate the benefit of the treatment. This single center study assesses the utilization of radiotherapy during the last weeks of life. MATERIAL AND METHODS: All cancer patients (N = 38,982) treated with radiotherapy (N = 11,395) in Turku University Central Hospital during 2005-2013 were identified in the database consisting of electronic patient records. One fourth (N = 2904, 25.5%) of the radiotherapy treatments were given during the last year of life. The last radiotherapy treatments and the time from the last radiotherapy treatment to death were assessed in regards to patients' age, cancer diagnosis, domicile, place of death and the treatment year. Treatments given during the last two weeks of life were also assessed regarding the goal of treatment and the reason for possible discontinuation. RESULTS: The median time from the last fraction of radiotherapy to death was 84 d. During the last two weeks before death (N = 340), pain (29.4%) was the most common indication for radiotherapy. Treatment was discontinued in 40.6% of the patients during the last two weeks of life, and worsening of general condition was the most common reason for discontinuity (70.3%). The patients receiving radiotherapy during the last weeks of life were more likely to die in tertiary care unit. During the last year of life single-fraction treatment was used only in 7% of all therapy courses. There was a statistically significant (p < .05) decrease in the median number of fractions in the last radiotherapy treatment between 2005-2007 (8 fractions) and 2011-2013 (6 fractions). CONCLUSIONS: Up to 70% of the treatments during the last two weeks of life were not delivered to alleviate pain and utilization of single fraction radiotherapy during the last year of life was infrequent. These observations suggest that practice of radiotherapy during the last weeks of life should be revisited.

[Decision about DNR for a palliative patient - do I dare to bring up the subject?]. / Palliatilvisessa hoidossa olevan potilaan DNR-päätös - uskallanko ottaa puheeksi?

The do not resuscitate decision (DNR) is an important choice of line of action, which should not be made on light grounds, but if neglected, may harm a patient receiving palliative care. Before making the decision, one should evaluate an unsuccessful result of possible resuscitation regarding the restoration of vital functions and quality of life. Evaluation of factors suggesting a poor prognosis should be possible already before arriving at the resuscitation situation. The decision should be discussed with the patient, trying to reach a consensus on the matter. DNRs should be made more actively for patients benefiting from the decision.

[Management of pain in palliative care]. / Kipu palliatiivisessa hoidossa.

Palliative pain management is usually successful, if the medication is strengthened in a stepwise manner in accordance with pain intensity, and initiation of a strong opioid is not delayed. Finding of a sufficiently effective dose of the opioid drug with simultaneous management of adverse effects requires continuous pain assessment and patient monitoring. In many cases it is possible to enhance analgesia by supplementing the medication with an antidepressant or an antiepileptic along with the opioid and paracetamol or the analgesic. Palliative radiotherapy will relieve tissue injury pain caused by bone metastases and soft tissue tumors as well as pain due to the possible nerve entrapments caused by them.

Post-graduate Course in Palliative Medicine: Experiences from an E-Learning-Based Pilot Program, a Mixed Methods Study.

Objective: To study whether E-learning methods are feasible in the post-graduate education of palliative medicine. Methods: A mixed-methods study. Evaluations from pilot course attendees were analyzed numerically and answers to open-ended questions about E-learning were analyzed using inductive content analysis. A national pilot E-learning-based post-graduate course in palliative medicine with 24 participating physicians in Finland. The evaluation of teaching modules and different aspects of the course was achieved from the participants through numerical statements and open-ended questions. Results: The feedback on most aspects of the course was good. For example, issues of pain and symptom control, lectures, pre-exams, and group discussions were deemed suitable for E-learning, while studying communication and existential issues through E-learning was considered more challenging. The benefits of E-learning included efficacy, better accessibility, and the possibility to go back to the teaching material. Reduced networking and face-to-face interactions were stated as challenges of E-learning. Conclusions: E-learning is feasible in the post-graduate education of palliative medicine and can be 'surprisingly rewarding'. It allows easy access to learn many important topics, while social networking may fall short. Further studies are needed to assess the increase in competence by different learning methods.

Palliative-care nurses' and physicians' descriptions of the competencies needed in their working units.

BACKGROUND: Specialists were asked to describe the most essential palliative and end-of-life care competencies needed in their working units, in order to deepen the understanding of the phenomenon. AIM: To describe the most essential competencies of palliative-care nurses and physicians. METHODS: The data was collected using an open-ended question in a survey sent to registered nurses (n=129) working within palliative care and to physicians (n=64) with a special competency in palliative care. The data was analysed using content analysis. RESULTS: The description of the most essential competencies included 16 main categories and 63 subcategories in total. The three strongest main categories were 'clinical competence', 'competence in social interactions' and 'competence in giving support'. Eleven main categories were based on both nurses' and physicians' data, while five main categories were created from nurses' data only. CONCLUSION: Interprofessional palliative-care education is recommended for the undergraduate and postgraduate education of nurses and physicians.

Effect of Palliative Care Decision on Use of Hospital Services in Pancreatic Cancer Patients: A Retrospective Study.

BACKGROUND/AIM: Continuing chemotherapy or using hospital services near the end of life (EOL) and delaying the approach to palliative care (PC) services are factors impairing quality of life near the EOL. PATIENTS AND METHODS: Records of patients with pancreatic cancer treated at Helsinki University Hospital in 2013 and deceased by the end of 2014 were reviewed (N=221). The PC decision establishes the point when anticancer treatment is interrupted and the focus shifts to symptom-centered PC. The timing of the PC decision, referrals to specialized PC, use of hospital services at the EOL, and place of death were examined. RESULTS: The median overall survival was 13 months from diagnosis. The PC decision was made <30 days prior to death or not at all for 44% of patients. In addition, 68% of these patients used hospital service in the last month of life compared to 32% of patients with an earlier PC decision (p<0.001). A later or lacking PC decision correlated with a larger proportion of deaths in a secondary or tertiary hospital (64% vs. 36%), but the difference was not statistically significant (p=0.25). CONCLUSION: A late or lacking PC decision for patients with pancreatic cancer was found in almost half of the patients. There was a significant difference in the use of hospital services depending on the timing of the decision. An earlier PC decision might improve EOL care, since a late or lacking PC decision relates to a more abundant use of hospital services and an increased risk of hospital deaths.

Improved risk prediction of chemotherapy-induced neutropenia-model development and validation with real-world data.

BACKGROUND: The existing risk prediction models for chemotherapy-induced febrile neutropenia (FN) do not necessarily apply to real-life patients in different healthcare systems and the external validation of these models are often lacking. Our study evaluates whether a machine learning-based risk prediction model could outperform the previously introduced models, especially when validated against real-world patient data from another institution not used for model training. METHODS: Using Turku University Hospital electronic medical records, we identified all patients who received chemotherapy for non-hematological cancer between the years 2010 and 2017 (N = 5879). An experimental surrogate endpoint was first-cycle neutropenic infection (NI), defined as grade IV neutropenia with serum C-reactive protein >10 mg/l. For predicting the risk of NI, a penalized regression model (Lasso) was developed. The model was externally validated in an independent dataset (N = 4594) from Tampere University Hospital. RESULTS: Lasso model accurately predicted NI risk with good accuracy (AUROC 0.84). In the validation cohort, the Lasso model outperformed two previously introduced, widely approved models, with AUROC 0.75. The variables selected by Lasso included granulocyte colony-stimulating factor (G-CSF) use, cancer type, pre-treatment neutrophil and thrombocyte count, intravenous treatment regimen, and the planned dose intensity. The same model predicted also FN, with AUROC 0.77, supporting the validity of NI as an endpoint. CONCLUSIONS: Our study demonstrates that real-world NI risk prediction can be improved with machine learning and that every difference in patient or treatment characteristics can have a significant impact on model performance. Here we outline a novel, externally validated approach which may hold potential to facilitate more targeted use of G-CSFs in the future.

Anaemia: a rare but neglected problem among Finnish patients receiving chemotherapy for solid tumours.

GOALS OF THE WORK: Anaemia is very frequently diagnosed among cancer patients. Use of erythropoietins has proved to be effective in reducing the need of transfusions and enhancing patients' quality of life, but may also have detrimental effects in treating nonanemic asymptomatic patients. We assessed the frequency of anaemia and the frequency with which it was diagnosed and treated in different types of solid tumours treated at outpatient chemotherapy policlinics. MATERIALS AND METHODS: During the study period, altogether 733 consecutive subjects received chemotherapy at the five Finnish University Hospitals. Their data were collected. The physician who was responsible for the chemotherapy treatment was unaware of the survey. The response to anaemia (treated or not, the modality of treatment) were established from patients records; 69% were females, mean age was 61 years (range, 24-92). RESULTS: The median haemoglobin level was 12.7 g/dL (range, 8.9-15.5 g/dL). About one third of the patients (200/733, 27%) had a value less than 12 g/dL. In only 15% of these cases was there any documentation of response or a possible treatment option for anaemia. On the other hand, only 12% of all patients (N=91) had a haemoglobin value less than 11 g/dL. However, in most of them anaemia had not been considered; in only 25% of cases was an active treatment option selected. CONCLUSIONS: According to our survey, anaemia was less common in our patients than in the European Cancer Anaemia Survey. Only a minority of chemotherapy patients receiving their treatments as outpatients would need active treatment for their anaemia.

Effect of estrogen and altered diet hardness on the expression of estrogen receptor alpha and matrix metalloproteinase-8 in rat condylar cartilage.

AIMS: To examine the effect of decreased estrogen level and altered diet hardness on condylar cartilage morphology of the rat temporomandibular joint (TMJ) and on the expression of condylar cartilage estrogen receptor alpha (ERa) and matrix metalloproteinase-8 (MMP-8). METHODS: A total of 36 female rats was divided into four groups: ovariectomized rats fed a normal diet, non-ovariectomized controls fed a normal diet, ovariectomized rats fed a soft diet, and non-ovariectomized controls fed a soft diet. Ovariectomy was performed at the age of 60 days. Seven days after the operation, the rats were sacrificed. Repeated measures ANOVA and Duncan's multiple comparison tests were used for statistical analysis. RESULTS: The ovariectomized rats had thicker cartilage layers than the controls, both in the normal diet and soft diet groups. The thinnest cartilage layers were found in the control rats fed with the soft diet. The thickness of the chondroblastic layer was significantly higher (P < .001) in the normal-diet rats than in the soft-diet rats in both ovariectomized and non-ovariectomized groups. The thickness of the proliferative layer was significantly higher (P < .001) in the ovariectomized soft-diet rats than in the soft-diet control rats. The proportional amount of ERa was statistically significantly higher (P < .001) in the condylar cartilage of the ovariectomized rats than in the non-ovariectomized control rats both in the normal- and soft-diet groups. The proportional amount of ERa was statistically significantly higher (P < .001) in the ovariectomized normal-diet rats than in the ovariectomized soft-diet rats. The proportional number of MMP-8-positive cells was statistically significantly higher (P < .001) in the condylar cartilage of ovariectomized rats fed the soft diet than in non-ovariectomized control rats fed the soft diet. Control rats fed with the normal diet had a higher proportional amount of MMP-8 positive cells than control rats fed with the soft diet (P < .05). CONCLUSION: The rat TMJ condylar cartilage is sensitive to changes in estrogen levels and altered diet hardness.

Impact of the Regional Palliative Care Pathway on Emergency Room Visits and Hospitalizations.

BACKGROUND/AIM: To explore the effect of palliative care (PC) pathway including home care and end-of-life care beds in the community hospitals supported by a PC unit in the secondary hospital on ER visits and hospitalizations. PATIENTS AND METHODS: Patients with advanced cancer and no further oncologic therapies who visited the ER of the Hyvinkää hospital before (2009) and after (2015) the establishment of the PC pathway were evaluated. RESULTS: A total of 112 patients visited the ER in both years, but revisits decreased from 59% to 38% (p<0.01). The most common symptoms necessitating the visit were pain (20%) and dyspnoea (14%). The proportion of patients admitted to a secondary hospital were 56% and 45% (p=0.016) and to community hospitals 12% and 28% (p<0.001) in 2009 and 2015, respectively. CONCLUSION: Organizing a PC pathway for cancer patients together with primary and secondary care decreases revisits to ER and admissions to secondary hospitals.

Nordic Specialist Course in Palliative Medicine: Evaluation and Impact on the Development of Palliative Medicine in the Nordic Countries: A Survey among Participants from Seven Courses 2003-2017.

Background: The five Nordic Associations for palliative medicine (PM) have since 2003 organized a common specialist course for six weeks in two years. Aim: To describe the course: participants, evaluations, impact on participants' careers, and on the development of PM in the Nordic countries. Methods: Information on participants taken from the course archive and national registries. A web survey sent to graduates from the courses 2003-2013 (n = 150) and 2013-2017 (n = 72). Results: Mean age at course start was 46.9 years; 66% were women. Mean overall evaluation score 5.7 (range 5.4-6.0, max 7.0). Survey response rate 84% (n = 186); 80% of respondents were working in PM, the majority as leaders, >90% engaged in teaching PM. About 40% were active in PM associations, lobbying, and guideline development. Conclusion: The Nordic Specialist Course in PM has had a profound impact on the participants' postcourse careers, influencing the development of PM in the Nordic countries.

Does Decision-making in End-of-life Care Differ Between Graduating Medical Students and Experienced Physicians?

BACKGROUND/AIM: Appropriate decision-making in end-of-life (EOL) care is essential for both junior and senior physicians. The aim of this study was to compare the decision-making and attitudes of medical students with those of experienced general practitioners (GP) regarding EOL-care. MATERIALS AND METHODS: A questionnaire presenting three cancer patient scenarios concerning decisions and ethical aspects of EOL-care was offered to 500 Finnish GPs and 639 graduating medical students in 2015-2016. RESULTS: Responses were received from 222 (47%) GPs and 402 (63%) students. The GPs withdrew antibiotics (p<0.001) and nasogastric tubes (p=0.007) and withheld resuscitation (p<0.001), blood transfusions (p=0.002) and pleural drainage (p<0.001) more often than did the students. The students considered euthanasia and assisted suicide less reprehensible (p<0.001 in both) than did the GPs. CONCLUSION: Medical students were more unwilling to withhold and withdraw therapies in EOL-care than were the GPs, but the students considered euthanasia less reprehensible. Medical education should include aspects of decision-making in EOL-care.

A predictive model of overall survival in patients with metastatic castration-resistant prostate cancer.

Metastatic castration resistant prostate cancer (mCRPC) is one of the most common cancers with a poor prognosis. To improve prognostic models of mCRPC, the Dialogue for Reverse Engineering Assessments and Methods (DREAM) Consortium organized a crowdsourced competition known as the Prostate Cancer DREAM Challenge. In the competition, data from four phase III clinical trials were utilized. A total of 1600 patients' clinical information across three of the trials was used to generate prognostic models, whereas one of the datasets (313 patients) was held out for blinded validation. The previously introduced prognostic model of overall survival of chemotherapy-naive mCRPC patients treated with docetaxel or prednisone (so called Halabi model) was used as a performance baseline. This paper presents the model developed by the team TYTDreamChallenge and its improved version to predict the prognosis of mCRPC patients within the first 30 months after starting the treatment based on available clinical features of each patient. In particular, by replacing our original larger set of eleven features with a smaller more carefully selected set of only five features the prediction performance on the independent validation cohort increased up to 5.4 percent. While the original TYTDreamChallenge model (iAUC=0.748) performed similarly as the performance-baseline model developed by Halabi et al. (iAUC=0.743), the improved post-challenge model (iAUC=0.779) showed markedly improved performance by using only PSA, ALP, AST, HB, and LESIONS as features. This highlights the importance of the selection of the clinical features when developing the predictive models.