Cite this DOI

Jangam Raghunath, J. R. (2023). A Extensive Study on Deep learning Architecture on Patient Treatment Trajectory Mining. *Journal of Science & Technology*, *7*(5), 32–41. https://doi.org/10.46243/jst.2018.v7.i05.pp32-41

@article{jangamraghunath2023extensive,
  author    = {Jangam Raghunath, Jangam Raghunath},
  title     = {{A Extensive Study on Deep learning Architecture on Patient Treatment Trajectory Mining}},
  journal   = {Journal of Science \& Technology},
  year      = {2023},
  month     = {jul},
  volume    = {7},
  number    = {5},
  pages     = {32--41},
  publisher = {Longman Publishers},
  issn      = {2456-5660},
  doi       = {10.46243/jst.2018.v7.i05.pp32-41},
  url       = {https://doi.org/10.46243/jst.2018.v7.i05.pp32-41},
  language  = {en},
  abstract  = {Patient treatment trajectory mining is current research field to access the response of the patient to new treatment data in clinical trials which is available in form high dimensional data. However processing of high dimensional trajectory data using machine learning model named markov chain model, learns the events but it is cumbersome and ambiguous on identifying the latent events and it fails to tackle long term dependencies between the clinical events. In order to tackle those challenges, deep learning model has been employed to effectively classify the patient treatment data to highlight the future outcome of the patients. In this paper, an extensive study has been carried out on deep learning architecture to predict the future outcomes on the patient treatment trajectory data. It is vital and essential task for providing detailed insight on disease progression and interventions. We demonstrate the efficacy of the model on long term dependency for disease progression modelling, intervention recommendation, and future risk prediction on treatment trajectory data. Further prediction on the irregularly distributed data has been analysed on employment of sampling, latent representatives and effective use of loss function. Moreover importance of activation functi on for learning representatives has been exploited for efficient future event prediction on extracted trajectory representation. Finally outline of the proposed methodology as framework to predict the prognosis of the patient has provid ed. Evaluation of models has been carried out on the ovarian cancer patient treatment data}
}

TY  - JOUR
TI  - A Extensive Study on Deep learning Architecture on Patient Treatment Trajectory Mining
AU  - Jangam Raghunath, Jangam Raghunath
JO  - Journal of Science & Technology
PY  - 2023
DA  - 2023/07/18/
VL  - 7
IS  - 5
SP  - 32
EP  - 41
PB  - Longman Publishers
SN  - 2456-5660
LA  - en
AB  - Patient treatment trajectory mining is current research field to access the response of the patient to new treatment data in clinical trials which is available in form high dimensional data. However processing of high dimensional trajectory data using machine learning model named markov chain model, learns the events but it is cumbersome and ambiguous on identifying the latent events and it fails to tackle long term dependencies between the clinical events. In order to tackle those challenges, deep learning model has been employed to effectively classify the patient treatment data to highlight the future outcome of the patients. In this paper, an extensive study has been carried out on deep learning architecture to predict the future outcomes on the patient treatment trajectory data. It is vital and essential task for providing detailed insight on disease progression and interventions. We demonstrate the efficacy of the model on long term dependency for disease progression modelling, intervention recommendation, and future risk prediction on treatment trajectory data. Further prediction on the irregularly distributed data has been analysed on employment of sampling, latent representatives and effective use of loss function. Moreover importance of activation functi on for learning representatives has been exploited for efficient future event prediction on extracted trajectory representation. Finally outline of the proposed methodology as framework to predict the prognosis of the patient has provid ed. Evaluation of models has been carried out on the ovarian cancer patient treatment data
DO  - 10.46243/jst.2018.v7.i05.pp32-41
UR  - https://doi.org/10.46243/jst.2018.v7.i05.pp32-41
ER  -

{
    "type": "article-journal",
    "id": "10.46243/jst.2018.v7.i05.pp32-41",
    "DOI": "10.46243/jst.2018.v7.i05.pp32-41",
    "URL": "https://doi.org/10.46243/jst.2018.v7.i05.pp32-41",
    "title": "A Extensive Study on Deep learning Architecture on Patient Treatment Trajectory Mining",
    "source": "Smart Scholars DOI Registry",
    "container-title": "Journal of Science & Technology",
    "author": [
        {
            "family": "Jangam Raghunath",
            "given": "Jangam Raghunath"
        }
    ],
    "issued": {
        "date-parts": [
            [
                2023,
                7,
                18
            ]
        ]
    },
    "volume": "7",
    "issue": "5",
    "page": "32-41",
    "publisher": "Longman Publishers",
    "language": "en",
    "abstract": "Patient treatment trajectory mining is current research field to access the response of the patient to new treatment data in clinical trials which is available in form high dimensional data. However processing of high dimensional trajectory data using machine learning model named markov chain model, learns the events but it is cumbersome and ambiguous on identifying the latent events and it fails to tackle long term dependencies between the clinical events. In order to tackle those challenges, deep learning model has been employed to effectively classify the patient treatment data to highlight the future outcome of the patients. In this paper, an extensive study has been carried out on deep learning architecture to predict the future outcomes on the patient treatment trajectory data. It is vital and essential task for providing detailed insight on disease progression and interventions. We demonstrate the efficacy of the model on long term dependency for disease progression modelling, intervention recommendation, and future risk prediction on treatment trajectory data. Further prediction on the irregularly distributed data has been analysed on employment of sampling, latent representatives and effective use of loss function. Moreover importance of activation functi on for learning representatives has been exploited for efficient future event prediction on extracted trajectory representation. Finally outline of the proposed methodology as framework to predict the prognosis of the patient has provid ed. Evaluation of models has been carried out on the ovarian cancer patient treatment data",
    "ISSN": "2456-5660"
}

From the record as registered (version 2) — the record and its history. Programs: https://registry.smartscholars.in/api.php?action=cite&doi=10.46243%2Fjst.2018.v7.i05.pp32-41 gives all four in one JSON answer.