Tuukka Hakkarainen

Mr. Tuukka Hakkarainen


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 September 2024 in BMJ Open
Verified
Journal Article
Open access
PDF file
THTuukka Hakkarainen
Tuukka Hakkarainen
MLMari Lahelma
Mari Lahelma
TRTerhi Rahkonen
Terhi Rahkonen
VLVille Lehtinen
Ville Lehtinen
JSJulian Shepelev
Julian Shepelev
EHEija Heikkila
Eija Heikkila
Objective This study compared the costs and nursing time associated with the delivery of continuous infusion of antibiotics via elastomeric infusion pumps (EIP) versus conventional intermittent infusion (CII) across different care pathways. Design Retrospective real-world data informed a cost comparison analysis that compared costs and nursing hours between infusion of antibiotics via EIP versus CII across eight care pathways in inpatient or outpatient care during infection episodes. Real-world data were obtained from patients treated within a year with parenteral antimicrobial therapy in Päijät-Häme Region, Finland. Setting Inpatient care with hospital admission and outpatient care at hospital at home in Päijät-Häme Region in Finland. Participants 3778 patients with a total of 4214 infection episodes treated with intravenous antimicrobial therapy. Interventions Eight treatment strategies with various combinations of EIP and CII administered in inpatient or outpatient care. Primary and secondary outcome measures Direct costs and nursing time. Results Skin and soft tissue infections accounted for the highest number of episodes treated with EIP overall (30.8%; 74 out of 240 episodes) and in outpatient care specifically (53.3%; 128 out of 240 episodes). Compared with inpatient care costs with CII (€4590 per episode), treating skin and soft tissue infections in outpatient care with EIP or CII incurred only 24% (€1104) and 35% (€1620) of the costs, respectively. Across all treatment strategies and infections studied, the use of EIP consistently required less nursing time. The highest nursing time in the outpatient care was observed in sepsis episodes treated with CII (37 hours with CII vs 7 hours with EIP per episode). Conclusion Delivery of antimicrobial therapy using continuous infusions with EIP instead of CII can significantly decrease the nursing time and cost in both inpatient and outpatient care. For skin and soft tissue infections and sepsis, the utilisation of EIP is a cost-saving option in outpatient care compared with the use of CII.

13 October 2025 in Human Vaccines & Immunotherapeutics
Verified
Journal Article
Open access
MKMari Kanerva
Mari Kanerva
SHSuvi E. Heinonen
Suvi E. Heinonen
THTuukka Hakkarainen
Tuukka Hakkarainen
OIOuti Isomeri
Outi Isomeri
MNMarie Nishimwe
Marie Nishimwe
RLRiikka-Leena Leskelä
Riikka-Leena Leskelä
The risk of herpes zoster (HZ) and its complications, such as postherpetic neuralgia (PHN), increases with age and burdens patients, the healthcare system, and society. We aimed to estimate the incidence, healthcare resource use (HCRU), and direct and indirect costs due to HZ and HZ-related complications (i.e. PHN) per age group in the adult population in Finland. This retrospective, non-interventional population-based registry study collected data from four different registers over 2014-2019: three with nationwide coverage and one with partial nationwide coverage. International classification codes were used to identify HZ and PHN cases. The incidences of HZ and PHN were stratified annually and per age group (18-49, 50-59, 60-64, 65-69, 70-79, ≥80 years of age [YoA]). The HZ-associated HCRU, and direct and indirect costs were estimated by counting healthcare contact, medications, and their unit costs from national registries. HZ incidence rate increased with age from 1.99/1,000 persons in 18-49 YoA to 8.04/1,000 persons in ≥80 YoA over 2014-2019. PHN incidence also increased with age. The HZ 5-year recurrence rate was 4.5%. Average total annual costs of HZ amounted to €11.3 million; the individual costs of an HZ and a PHN HZ episode were €649 and €1,910, respectively. Estimated total costs were split between sick leave (37%), inpatient days (30%), outpatient visits (29%), and outpatient antiviral drugs (4%). In Finland, HZ poses a significant health and economic burden that increases with population aging, highlighting the need to consider HZ prevention.

29 January 2026 in Cancers
Verified
Journal Article
Open access
PDF file
THTuukka Hakkarainen
Tuukka Hakkarainen
IHIra ira Haavisto
Ira ira Haavisto
MNMikko Nuutinen
Mikko Nuutinen
YHYrjänä Hynninen
Yrjänä Hynninen
PPPaula Poikonen-Saksela
Paula Poikonen-Saksela
RLRiikka-Leena Leskelä
Riikka-Leena Leskelä
Introduction: Women with breast cancer experience psychological distress, and resilience-strengthening psychosocial support may improve their quality of life (QoL). Identifying those at risk of low QoL is challenging. This study evaluated the cost-effectiveness of a machine learning-based QoL predictor to support clinical decision-making regarding psychosocial support (sample size: 660). Methods: A decision tree cost–utility model was developed to compare four decision-making strategies in offering psychosocial support: the clinician alone, the QoL predictor alone, the clinician supported by the predictor, and no prediction with no psychosocial support. QoL after one year was used as a proxy for resilience. Costs, health outcomes, and net monetary benefits (NMBs) were estimated using a one-year time horizon. Incremental cost-effectiveness ratios (ICERs) were calculated and dominance assessed. A societal scenario analysis incorporated productivity losses. A probabilistic sensitivity analysis generated cost-effectiveness acceptability curves. Results: Clinicians supported by the QoL predictor produced the highest NMB (EUR 16,349) and the greatest quality-adjusted life year (QALY) gain (0.759), with an ICER of EUR 22,892 compared with the next least costly strategy. Clinician-only prediction and predictor-only approaches were dominated or extendedly dominated. Under the societal perspective, all strategies produced negative NMB values due to productivity losses, but the overall ranking remained unchanged. The probabilistic sensitivity analysis showed that the combined clinician and predictor strategy had a 69% probability of being cost-effective at a willingness to pay threshold of EUR 30,000. Conclusions: Combining clinician judgement with the machine learning-based QoL predictor improved the targeting of psychosocial support and was the most cost-effective strategy. Further prospective and comparative studies are needed to confirm its long-term effectiveness and cost-effectiveness in clinical practice.

3 July 2026 in Journal of Medical Internet Research
Verified
Journal Article
Open access
CDCarina Dantas
Carina Dantas
MCMiriam Cabrita
Miriam Cabrita
MBMaciej Bobowicz
Maciej Bobowicz
HAHarm op den Akker
Harm op den Akker
XRXavier Rafael-Palou
Xavier Rafael-Palou
Elisio CostaElisio Costa
Elisio Costa
Background: The successful design and implementation of artificial intelligence (AI)–driven solutions in health care requires early and continuous multidisciplinary and multiprofessional collaboration. However, diverse disciplinary educational backgrounds, varying languages, and cultural or geographic differences can lead to misunderstandings. To bridge this gap, a structured approach to AI requirements specification can facilitate a shared terminology and a deep mutual understanding among stakeholders, serving both as a guide for technological development and as a means of defining clear pathways for clinical implementation. While technical requirements are well-established in traditional technology development domains, this structured approach remains relatively underused within clinical and social science contexts. Consequently, valuable insights derived from participatory and stakeholder-driven approaches are often overlooked, limiting the relevance and trustworthiness of AI systems in health care settings. Objective: This study presents a methodology for requirements gathering, specification, mapping, and verification, specifically engineered for the complex, multistakeholder environment of clinically applied AI. The methodology was implemented within the specific case of an international multidisciplinary project evaluating an AI-based prediction tool for neoadjuvant chemotherapy treatment response for breast cancer and forming a part of the developed AI validation framework. Methods: The process for AI requirements gathering, specification, and monitoring included 3 iterative rounds of discussion, engaging nearly 150 social, clinical, technical, ethical, and regulatory experts and patients across Europe, South America, North Africa, and Eurasia. It combines established requirements engineering methods (including the MoSCoW [Must have, Should have, Could have, Will not have] framework) with social innovation techniques to ensure inclusivity and contextual relevance. Results: A key finding is the successful development of a structured framework integrating participatory social innovation with formal requirements engineering in an international AI health care setting, through a traceable multisource workflow including clinical, ethical, and regulatory aspects. It is supplemented with an extensive list of 184 actionable consensus-based requirements, categorized by stakeholder group, providing valuable insights for AI researchers in the oncology field with the potential to be transferable to other digital health domains. The requirements align with the fairness, universality, traceability, usability, robustness, and explainability in the AI (FUTURE-AI) framework, ensuring the tool is trustworthy and comprehensive from a multistakeholder perspective, and ensuring comprehensive consideration of all elements of FUTURE-AI. Conclusions: The proposed methodology represents a significant advancement for requirements engineering in digital health by extending traditional technical processes to systematically incorporate nontechnical requirements from diverse global stakeholders. This unified approach is essential for ensuring AI solutions are not only technically robust but also clinically relevant, legally compliant, and socially acceptable.

1 September 2025 in Clinical Genitourinary Cancer
Verified
Journal Article
Open access
TMTeemu J. Murtola
Teemu J. Murtola
THTuukka Hakkarainen
Tuukka Hakkarainen
MLMari Lahelma
Mari Lahelma
PPPaula Pennanen
Paula Pennanen
RLRiikka-Leena Leskelä
Riikka-Leena Leskelä
ARAntti Rannikko
Antti Rannikko
Prostate cancer is the most prevalent cancer among men in Finland, causing significant healthcare costs. Understanding the economic burden of various treatment pathways is vital for optimizing healthcare strategies. This study aimed at estimating healthcare resource utilization and associated costs for patients with localized prostate cancer (LPC) and locally advanced prostate cancer (LAPC) based on initial treatment decisions in Finland. A retrospective, noninterventional study was conducted using pseudonymized patient-level data from the 5 University Hospitals and the Social Insurance Institution of Finland. The cohort included 16,212 adults diagnosed with localized prostate cancer (LPC) or locally advanced prostate cancer (LAPC) between 1 July 2010 and 30 June 2021. Patients were categorized into 4 groups: no immediate treatment (NIT), radiotherapy only (RT), radiotherapy combined with androgen deprivation therapy (RT+ADT), and radical prostatectomy (RP). Healthcare resource utilization and costs were analyzed on a per-patient-year basis, considering inpatient admissions, outpatient visits, emergency department visits, and outpatient medication costs. The first-year costs were highest for RP (€11,766) and RT+ADT (€10,421), reflecting intensive treatment, followed by RT only (€9,014) and no immediate treatment (NIT) (€4,129). Over time, costs decreased for RP and RT+ADT groups. Emergence of metastatic disease significantly increased costs, particularly due to outpatient medication. Costs began rising 1-2 years before metastasis, indicating early health deterioration. This study highlights significant cost variations across different treatment pathways for prostate cancer in Finland and underscores the economic impact of metastatic disease. Early detection and effective management are essential for cost containment.

22 June 2025 in Expert Review of Pharmacoeconomics & Outcomes Research
Verified
Journal Article
Open access
THTuukka Hakkarainen
Tuukka Hakkarainen
HIHaavisto Ira
Haavisto Ira
LRLeskelä Riikka-Leena
Leskelä Riikka-Leena
This systematic scoping review aimed to identify and analyze current methodological approaches used in model-based economic evaluations (EEs) of prognostic and predictive companion diagnostics (pCDx), highlighting methodological gaps and challenges. Systematic searches were conducted in PubMed and Scopus (January 2009-March 2023). Included studies were model-based EEs, methodological papers, or reviews specifically addressing prognostic or predictive CDx. Data extraction followed modified CHEERS checklist. Results were synthesized narratively across six methodological domains. No formal risk of bias assessment was done per scoping review conventions. Eighty-eight studies were included, of which 60 were model-based EEs. Most studies utilized Markov cohort models (37%) or decision tree - Markov hybrids (30%). Quality-adjusted life-years (QALYs) were the main outcome (88%). Only 15% of studies derived clinical utility from randomized controlled trials, and fewer than half explicitly modeled diagnostic accuracy. Methodological limitations included inconsistent modeling of real-world test-treatment pathways, insufficient consideration of pretest probabilities, diagnostic thresholds, and inadequate uncertainty analyses. This review identified variability and methodological gaps in economic evaluations of pCDx. Standardizing evaluation methods, integrating real-world evidence, and systematically considering the diagnostic accuracy and uncertainty could improve robustness of pCDx evaluations. Limitations of this study included overrepresentation of breast cancer studies. OSF Registries (22 February 2023) DOI 10.17605/OSF.IO/GVFMQ.