kth.sePublications KTH
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
AI-baserat beslutsstöd för vårdprioritering: En prototyp för riskbedömning och tidsbokning inspirerad av SIP: Teknisk implementering: AI-drivet riskbedömningssystem och schemaläggningsalgoritm
KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Health Informatics and Logistics.
KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Health Informatics and Logistics.
2025 (Swedish)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesisAlternative title
AI-Based Decision Support for Healthcare Prioritization: A Prototype for Risk Assessment and Appointment Scheduling Inspired by SIP : Technical Implementation: AI-driven Risk Assessment System and Scheduling Algorithm (English)
Abstract [sv]

Den svenska vården använder Samordnad Individuell Plan (SIP) för att samordna insatser för patienter med komplexa behov. Dessa processer kännetecknas dock av ineffektiv tidsbokning, manuell riskbedömning och subjektiv prioritering, till följd av brist på digitala verktyg, vilket leder till långa väntetider. Detta examensarbete utvecklade ett AI-drivet beslutsstöd som automatiserar riskbedömning och schemaläggning. Prototypen kombinerar två komponenter:

  1. AI-modeller (Random Forest och XGBoost), som tränades på syntetiska data och uppnådde 77 procent precision för stroke.
  2. En regelbaserad greedy-algoritm för automatiserad schemaläggning, som schemalade patienter baserat på deras risknivå och ålder. I simuleringar minskade algoritmen hanteringstiden med 83 procent jämfört med manuell bokning.

Systemet visar hur AI kan användas för att prioritera högriskpatienter och minska vårdfördröjningar. Etiska och juridiska aspekter, inklusive efterlevnad av GDPR, hanterades genom användning av syntetiska data för att undvika behandling av känslig patientinformation. Studien betonar den samhälleliga nyttan av att digitalisera SIP-arbetsflöden för att öka effektiviteten och rättvisa i vården och presenterar tekniska samt organisatoriska rekommendationer för framtida implementering.

Abstract [en]

The Swedish healthcare system uses the Coordinated Individual Plan (SIP) to coordinate care for patients with complex needs. However, these processes are often characterised by inefficient scheduling, manual risk assessment, and subjective prioritisation due to a lack of digital tools, which leads to long waiting times. This thesis developed an AI-driven decision support system that automates both risk assessment and scheduling. The prototype integrates two core components:

  1. AI models (Random Forest and XGBoost), trained on synthetic datasets, which achieved 77 percent precision for stroke prediction.
  2. A rule-based greedy algorithm for automated scheduling, which scheduled patients based on their risk level and age. In simulations, the algorithm reduced administrative handling time by 83 percent compared to manual scheduling.

The system highlights AI’s potential to prioritise high-risk patients and reduce delays. Ethical and legal considerations, including GDPR compliance, were addressed through synthetic data usage to avoid processing sensitive patient information. Technical and organizational recommendations for future implementation are provided, highlighting the societal benefits of digitising SIP workflows to improve efficiency and fairness in healthcare.

Place, publisher, year, edition, pages
2025.
Series
TRITA-CBH-GRU ; 2025:101
Keywords [en]
AI, machine learning, AI-based decision support, risk assessment, healthcare prioritization, automated scheduling, SHAP, Coordinated Individual Plan (CIP), FHIR, synthetic data, predictive modelling, clinical workflow optimization, GDPR
Keywords [sv]
AI, maskininlärning, AI-baserat beslutsstöd, riskbedömning, vårdprioritering, automatiserad schemaläggning, SHAP, Samordnad Individuell Plan (SIP), FHIR, syntetisk data, prediktiv modellering, klinisk arbetsflödesoptimering, GDPR
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:kth:diva-364366OAI: oai:DiVA.org:kth-364366DiVA, id: diva2:1967539
Educational program
Bachelor of Science in Engineering - Computer Engineering
Supervisors
Examiners
Available from: 2025-06-12 Created: 2025-06-11 Last updated: 2025-06-12Bibliographically approved

Open Access in DiVA

fulltext(1613 kB)98 downloads
File information
File name FULLTEXT01.pdfFile size 1613 kBChecksum SHA-512
e555792ad60a5d2774a78421d8d6dfb473638c3e5a52712351d8931c73089d2e630bdfc3a0e019220bf4e5df2d1360475e9b403fe0d1e973330be586067c51db
Type fulltextMimetype application/pdf

By organisation
Health Informatics and Logistics
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 98 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 297 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf