Introduction: Crossing the boundaries of innovation in healthcare, this research delves into the depths of hospital efficiency and health policies in the Apulia region of Italy. With an approach that skillfully intertwines advanced machine learning techniques and data analysis, the beating heart of this work is the adoption of the revolutionary Cluster Principal Data-Envelopment and ANOVA (CPDA) method. This methodology not only promises a holistic evaluation of hospital efficiency but also pays meticulous attention to the perceived quality of services and their resilience in the face of the population's evolving needs. Materials and Methods: The journey begins with a thorough analysis of healthcare performance in Apulia, where CPDA becomes the tool to decipher efficiency and quality perception, unveiling the vital importance of service adaptability. This initial phase opens the door to a detailed comparison between the healthcare systems of Apulia and Emilia-Romagna, where efficiency and quality parameters intertwine to explore operational practices and resource management in different regional contexts. Moving forward, attention shifts to hospital energy efficiency and its socio-economic impact, bridging the gap between energy resource management, healthcare economics, and service quality. A further qualitative leap is achieved with the introduction of neural network models for an in-depth examination of operational efficiency in hospitals, considering variables such as energy costs, personnel costs, and the effectiveness of medical device utilization. Results: Efficient structures emerge at various levels, while technical efficiency is decomposed into pure technical efficiency (PTE) and allocative efficiency (SE), painting a landscape of significant differences in efficiency across different hospital levels. The integration of the Particle Swarm Optimization (PSO) algorithm into the CPDA model elevates the model's discriminative capacity, refining the performance evaluation. Furthermore, a direct correlation between hospital efficiency and the perceived quality of healthcare is revealed, indicated by a negative linear relationship between scale efficiency and patients' propensity for hospitalization. The analysis then delves into the complex interaction between hospital organizational structures, patients' propensity for hospitalization, and the resulting energy costs. The increase in medical devices in public hospitals in Apulia is directly linked to rising energy costs, highlighting the importance of a balanced approach towards the adoption of new medical technologies. Conclusions: The research proposes a decision support system for healthcare in Apulia, based on advanced analytical methodologies and data-driven decisions. This system aims to optimize the efficiency, effectiveness, and sustainability of healthcare services in the region, representing a significant contribution to the field of healthcare analysis. Demonstrating how the integration of advanced machine learning techniques can improve operational efficiency in hospitals and positively influence health policies, the work emphasizes the crucial importance of technological innovation for optimized resource management and evidence-based decision support.
Introduzione: Attraversando i confini dell'innovazione in campo sanitario, la presente ricerca si immerge nelle profondità dell'efficienza ospedaliera e delle politiche sanitarie nella regione Puglia in Italia. Con un approccio che intreccia abilmente tecniche avanzate di machine learning e analisi dei dati, il cuore pulsante di questo lavoro è l'adozione del rivoluzionario metodo Cluster Principal Data-Envelopment e ANOVA (CPDA). Questa metodologia non solo promette una valutazione olistica dell'efficienza delle strutture ospedaliere ma pone anche un'attenzione scrupolosa sulla qualità percepita dei servizi e sulla loro resilienza di fronte alle esigenze in continua evoluzione della popolazione. Materiali e metodi: Il viaggio inizia con un'analisi meticolosa della performance sanitaria in Puglia, dove il CPDA diventa lo strumento per decifrare l'efficienza e la percezione della qualità dell'assistenza, svelando l'importanza vitale dell'adattabilità dei servizi sanitari. Questa fase iniziale apre le porte a un confronto dettagliato tra i sistemi ospedalieri di Puglia ed Emilia-Romagna, dove parametri di efficienza e qualità si intrecciano per esplorare le pratiche operative e la gestione delle risorse in contesti regionali diversi. Proseguendo, l'attenzione si sposta sull'efficienza energetica ospedaliera e il suo impatto socio-economico, tracciando un ponte tra la gestione delle risorse energetiche, l'economia sanitaria e la qualità del servizio. Un ulteriore salto qualitativo si realizza con l'introduzione di modelli di reti neurali per una disamina approfondita dell'efficienza operativa ospedaliera, prendendo in considerazione variabili quali i costi energetici, i costi del personale e l'efficacia nell'utilizzo dei dispositivi medici. Risultati: Strutture efficienti si delineano a vari livelli, mentre l'efficienza tecnica si scompone in efficienza tecnica pura (PTE) ed efficienza allocativa (SE), disegnando un panorama di differenze significative nell'efficienza tra i vari livelli ospedalieri. L'integrazione dell'algoritmo di ottimizzazione PSO nel modello CPDA eleva la capacità discriminante del modello, affinando la valutazione delle prestazioni ospedaliere. Inoltre, emerge una correlazione diretta tra l'efficienza ospedaliera e la qualità percepita dell'assistenza sanitaria, rivelata da una relazione lineare negativa tra l'efficienza di scala e la propensione dei pazienti all'ospedalizzazione. L'analisi si addentra poi nella complessa interazione tra le strutture organizzative ospedaliere, la propensione dei pazienti all'ospedalizzazione e i costi energetici risultanti. L'incremento dei dispositivi medici negli ospedali pubblici pugliesi si lega direttamente all'aumento dei costi energetici, sottolineando l'importanza di un approccio bilanciato verso l'adozione di nuove tecnologie mediche. Conclusioni: La ricerca propone un sistema di supporto decisionale per l'assistenza sanitaria in Puglia, basato su metodologie analitiche avanzate e decisioni guidate dai dati. Questo sistema mira a ottimizzare l'efficienza, l'efficacia e la sostenibilità dei servizi sanitari nella regione, rappresentando un contributo significativo al campo dell'analisi sanitaria. Dimostrando come l'integrazione di tecniche avanzate di machine learning possa migliorare l'efficienza operativa ospedaliera e influenzare positivamente le politiche sanitarie, il lavoro enfatizza l'importanza cruciale dell'innovazione tecnologica per una gestione ottimizzata delle risorse sanitarie e un supporto decisionale basato su prove.
Decision Support System (DSS) for policy formulation in the Apulian regional health system / Santamato, Vito. - (2024). [10.14274/santamato-vito_phd2024]
Decision Support System (DSS) for policy formulation in the Apulian regional health system
Santamato, Vito
2024-01-01
Abstract
Introduction: Crossing the boundaries of innovation in healthcare, this research delves into the depths of hospital efficiency and health policies in the Apulia region of Italy. With an approach that skillfully intertwines advanced machine learning techniques and data analysis, the beating heart of this work is the adoption of the revolutionary Cluster Principal Data-Envelopment and ANOVA (CPDA) method. This methodology not only promises a holistic evaluation of hospital efficiency but also pays meticulous attention to the perceived quality of services and their resilience in the face of the population's evolving needs. Materials and Methods: The journey begins with a thorough analysis of healthcare performance in Apulia, where CPDA becomes the tool to decipher efficiency and quality perception, unveiling the vital importance of service adaptability. This initial phase opens the door to a detailed comparison between the healthcare systems of Apulia and Emilia-Romagna, where efficiency and quality parameters intertwine to explore operational practices and resource management in different regional contexts. Moving forward, attention shifts to hospital energy efficiency and its socio-economic impact, bridging the gap between energy resource management, healthcare economics, and service quality. A further qualitative leap is achieved with the introduction of neural network models for an in-depth examination of operational efficiency in hospitals, considering variables such as energy costs, personnel costs, and the effectiveness of medical device utilization. Results: Efficient structures emerge at various levels, while technical efficiency is decomposed into pure technical efficiency (PTE) and allocative efficiency (SE), painting a landscape of significant differences in efficiency across different hospital levels. The integration of the Particle Swarm Optimization (PSO) algorithm into the CPDA model elevates the model's discriminative capacity, refining the performance evaluation. Furthermore, a direct correlation between hospital efficiency and the perceived quality of healthcare is revealed, indicated by a negative linear relationship between scale efficiency and patients' propensity for hospitalization. The analysis then delves into the complex interaction between hospital organizational structures, patients' propensity for hospitalization, and the resulting energy costs. The increase in medical devices in public hospitals in Apulia is directly linked to rising energy costs, highlighting the importance of a balanced approach towards the adoption of new medical technologies. Conclusions: The research proposes a decision support system for healthcare in Apulia, based on advanced analytical methodologies and data-driven decisions. This system aims to optimize the efficiency, effectiveness, and sustainability of healthcare services in the region, representing a significant contribution to the field of healthcare analysis. Demonstrating how the integration of advanced machine learning techniques can improve operational efficiency in hospitals and positively influence health policies, the work emphasizes the crucial importance of technological innovation for optimized resource management and evidence-based decision support.File | Dimensione | Formato | |
---|---|---|---|
5.TESI_SANTAMATO_VITO.pdf
accesso aperto
Descrizione: Tesi di Dottorato
Tipologia:
PDF Editoriale
Licenza:
Dominio pubblico
Dimensione
17.84 MB
Formato
Adobe PDF
|
17.84 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.