Petrizzo 2025a - Revision history

Tomamil: Tomamil moved page Review 902316223783 to Petrizzo 2025a

2025-06-23T14:30:03Z

Tomamil moved page Review 902316223783 to Petrizzo 2025a

MPetrizzo: Import changes, formatting sub-headers, fixing spacing between bullet points, small changes.

2025-05-30T18:36:59Z

Import changes, formatting sub-headers, fixing spacing between bullet points, small changes.

Show changes

MPetrizzo at 18:23, 30 May 2025

2025-05-30T18:23:46Z

Show changes

MPetrizzo: Proper Table Formatting

2025-05-06T01:26:48Z

Proper Table Formatting

Show changes

MPetrizzo: MPetrizzo moved page Draft Petrizzo 769196690 to Review 902316223783

2025-05-02T14:45:35Z

MPetrizzo moved page Draft Petrizzo 769196690 to Review 902316223783

MPetrizzo at 13:34, 2 May 2025

2025-05-02T13:34:31Z

MPetrizzo: Fixed References

2025-05-02T13:30:13Z

Fixed References

Show changes

MPetrizzo: Changed references to []

2025-04-30T15:18:00Z

Changed references to []

Show changes

MPetrizzo: in the works, quick save

2025-04-29T15:20:58Z

in the works, quick save

Show changes

MPetrizzo at 14:56, 29 April 2025

2025-04-29T14:56:30Z

@@ Line 63: / Line 63: @@
 |  style="border-top: 1pt solid black;border-bottom: 1pt solid black;text-align: center;vertical-align: top;"|''ChatGPT-4o''
 |  style="border-top: 1pt solid black;border-bottom: 1pt solid black;text-align: center;vertical-align: top;"|''LlaMa-3.1v-405B''
-|Gemini 1.5 Pro
+|  style="border-top: 1pt solid black;border-bottom: 1pt solid black;text-align: center;vertical-align: top;"|''Gemini-1.5-Pro''
 |-
 |  style="border-top: 1pt solid black;vertical-align: top;"|''Architecture''
@@ Line 69: / Line 69: @@
 |  style="border-top: 1pt solid black;text-align: center;vertical-align: top;"|Encoder-Decoder
 |  style="border-top: 1pt solid black;text-align: center;vertical-align: top;"|Decoder Only
-|MoE TRNN
+|  style="border-top: 1pt solid black;text-align: center;vertical-align: top;"|''MoE TRNN''
 |-
 |  style="vertical-align: top;"|''Model Size''
@@ Line 75: / Line 75: @@
 |  style="text-align: center;vertical-align: top;"|~500 GB
 |  style="text-align: center;vertical-align: top;"|~1 TB
-|N/A*
+|  style="text-align: center;vertical-align: top;"|N/A*
 |-
 |  style="vertical-align: top;"|''Parameters''
@@ Line 81: / Line 81: @@
 |  style="text-align: center;vertical-align: top;"|~1.8 Trillion
 |  style="text-align: center;vertical-align: top;"|~405 Billion
-|N/A*
+|  style="text-align: center;vertical-align: top;"|N/A*
 |-
 |  style="vertical-align: top;"|''Speed (Tokens/second)''
@@ Line 87: / Line 87: @@
 |  style="text-align: center;vertical-align: top;"|63.3
 |  style="text-align: center;vertical-align: top;"|27.8
-|59.8
+|  style="text-align: center;vertical-align: top;"|59.8
 |-
 |  rowspan='1' style="border-bottom: 1pt solid black;vertical-align: top;"|''Cost (Per Million Tokens)''

@@ Line 49: / Line 49: @@
 Mixture of Experts (MoE) is a sub-divisional-based architecture comprising multiple networks connected similarly to TRNN to achieve self-attention (IBM, 2024<sub>b</sub>). This is accomplished through specialized “experts” to perform subdivided tasks of the model. Working similarly to an office, the “leader” flows all input directions, and calls upon “workers” who are the specialized experts. This type of model has lower training times and higher accuracy convergence compared to conventional models  (IBM, 2024<sub>b</sub>). While not a new concept, its difficult conceptualization makes it a novel approach to Machine Learning and is currently deployed in advanced modern models, such as ChatGPT 4.0.
-==Scientific Foundation==
+==SCIENTIFIC FOUNDATION==
 Simulated Patients are a fundamental aspect of psychotherapy training which requires a certified actor to be available. Due to this, oftentimes another psychiatric resident loses training time to serve as a simulated patient for another resident. While virtual patients seem promising as an alternative, they lack the interactivity of a simulated patient. As such, this project aimed to develop virtual patients that have the advantage of simulated patients by leveraging AI.
@@ Line 155: / Line 155: @@
 Previous research in utilizing AI to replicate patients for training residents is novel, with very limited conceptualization and application. However, recently a new trial has been published; Patient-Ψ attempts the goal of training mental health professionals via ChatGPT-4.0 specialization and prompt engineering. These prompts reflect specific emotional and situational aspects of the individual to be replicated and then use a “trainer” framework to converse between the patient and a user. The results of the model output were compared with professionals against the default ChatGPT-4.0 model. Further, this paper aims specifically at CBT training and aims for generalization in future research. Vitally, the usage of supervised learning is not explored, instead opted for unsupervised learning. Further, rapid model development warrants the usage of multiple models for analysis.
-==Methodology==
+==METHODOLOGY==
 === ''Data Collection''===
@@ Line 207: / Line 207: @@
 <div class="center" style="width: auto; margin-left: auto; margin-right: auto;">[[File:Draft_Petrizzo_769196690-image4-c.png|centre|thumb|306x306px|'''Figure 12''': Usage. (Generated by Student)]]</div>
-==Results and Analysis==
+==RESULTS AND ANALYSIS==
 The individual metrics for model accuracy, recall, and instruction following are characteristically different depending on the exact patient transcript utilized (Table 3). This could be due to varying data quality, which cannot be verified for patient anonymization. Likewise, data quality is not standardized nor verified for usage as a virtual patient. Each model received an accuracy through a randomized series of 50 messages from the training set, the messages were randomized with a random number generator. The randomized set utilized identical seeds to ensure model comparison.
@@ Line 307: / Line 307: @@
 The ability for a model to respond quickly is also a vital component of a chatbot design, to enhance user satisfaction and make fluid conversation. Having the model entirely installed on the system makes Llama the fastest model, being dependent on the configuration and specification of the system, while Gemini 1.5 Pro took extensive safety measures; not necessarily negative, but would extend prediction times dramatically. Furthermore, the rate-limiting of API-based models, such as the ChatGPT and Gemini series used in this paper, may incidentally cause inputs to be buffered or lost entirely. The transfer-learning models responded much quicker than the equivalent fine-tuned models. Oftentimes being faster in comparison of milliseconds to multiple seconds.
-==Conclusion==
+==CONCLUSION==
 ''' '''Utilizing modern Artificial Intelligence models to develop virtual patients is a promising applicable concept which warrants further development with higher computational power. The need for such developments is high; especially in ensuring resident training quality and creating availability to simulated patients. Furthermore, the promise for such concepts to be successful increases with the development of more advanced models that can capture semantic relations with even fewer inputs. The creation of a website interface was successfully developed to be utilized; however, there are various hurdles before full deployment into professional environments.
@@ Line 323: / Line 323: @@
 There is potential apparent in each model’s displayed accuracy and further metrics to evaluate the model’s performance are necessary to determine their use in real-life application. For example; ChatGPT-4o mini having a higher accuracy than the base-model equivalent is highly counterintuitive and needs to be evaluated further. The accuracy of the models overall reflects some semantic correspondence successfully gathered by the model, which can also likely be improved through more data. Interaction with the model was successfully implemented and developed intentionally to provide the ability for model addition as technology develops further. The website was also developed with the ability to be converted into an app for mobile devices, further supporting scalability as models are evaluated further. By utilizing Electron as a secondary port, the website has executable files, a website interface, and mobile conversion capacities. This allows easy integration into ongoing training systems for residents. In all, this paper demonstrates the potential of AI to greatly improve the availability of resident training.
-==Acknowledgments:==
+==ACKNOWLEDGEMENTS:==
 In Loving Memory of Zuri Leung.
@@ Line 329: / Line 329: @@
 Thank you to Ms. Colette, Ms. Beatty, and Dr. Kramer for their amazing guidance.
-==References:==
+==REFERENCES:==
 ACGME Competencies (2024). ''Accreditation Council for Graduate Medical Education.'' Retrieved on September 26, 2024, from URL: [https://www.acgme.org/programs-and-institutions/programs/common-program-requirements/ https://www.acgme.org/programs-and-institutions/programs/common-program-requirements/]

← Older revision	Revision as of 14:30, 23 June 2025
(No difference)

← Older revision	Revision as of 14:45, 2 May 2025
(No difference)