Elaborating the potential of Artificial Intelligence in automated CAR-T cell manufacturing 闡述人工智能在自動化 CAR-T 細胞製造中的潛力
Niklas Bäckel (1) ^(1**){ }^{1 *}, Simon Hort ^(1){ }^{1}, Tamás Kis ^(2){ }^{2}, 尼克拉斯·巴克勒(1) ^(1**){ }^{1 *} 、西蒙·霍特 ^(1){ }^{1} 、塔马什·基什 ^(2){ }^{2}David F. Nettleton (1) ^(3){ }^{3}, Joseph R. Egan (1) ^(4){ }^{4}, John J. L. Jacobs (1) ^(5){ }^{5}, Dennis Grunert ^(1){ }^{1} and Robert H. Schmitt ^(1,6){ }^{1,6} 大衛·F·內特頓 (1) ^(3){ }^{3} 、約瑟夫·R·伊根 (1) ^(4){ }^{4} 、約翰·J·L·雅各布斯 (1) ^(5){ }^{5} 、丹尼斯·格魯納特 ^(1){ }^{1} 和羅伯特·H·施密特 ^(1,6){ }^{1,6}^(1){ }^{1} Fraunhofer Institute for Production Technology IPT, Aachen, Germany, ^(2){ }^{2} Institute for Computer Science and Control, Hungarian Research Network, Budapest, Hungary, ^(3){ }^{3} IRIS Technology Solutions, Barcelona, Spain, ^(4){ }^{4} Department of Biochemical Engineering, Mathematical Modelling of Cell and Gene Therapies, University College London, London, United Kingdom, ^(5){ }^{5} Clinical Care and Research, ORTEC B.V., Zoetermeer, Netherlands, ^(6){ }^{6} Laboratory for Machine Tools and Production Engineering (WZL), RWTH Aachen University, Aachen, Germany 弗勞恩霍夫生產技術研究所, 亞琛, 德國
匈牙利研究網絡 中央計算機研究所, 布達佩斯, 匈牙利
艾瑞斯科技解決方案, 巴塞羅那, 西班牙
倫敦大學學院 生化工程系 細胞和基因療法數學建模, 倫敦, 英國
ORTEC B.V. 臨床護理與研究, 佐特梅爾, 荷蘭
亞琛工業大學 機床與生產工程實驗室 (WZL), 亞琛, 德國
Abstract 摘要
This paper discusses the challenges of producing CAR-T cells for cancer treatment and the potential for Artificial Intelligence (AI) for its improvement. CAR-T cell therapy was approved in 2018 as the first Advanced Therapy Medicinal Product (ATMP) for treating acute leukemia and lymphoma. ATMPs are cell- and gene-based therapies that show great promise for treating various cancers and hereditary diseases. While some new ATMPs have been approved, ongoing clinical trials are expected to lead to the approval of many more. However, the production of CAR-T cells presents a significant challenge due to the high costs associated with the manufacturing process, making the therapy very expensive (approx. $400,000). Furthermore, autologous CAR-T therapy is limited to a make-to-order approach, which makes scaling economical production difficult. First attempts are being made to automate this multi-step manufacturing process, which will not only directly reduce the high manufacturing costs but will also enable comprehensive data collection. AI technologies have the ability to analyze this data and convert it into knowledge and insights. In order to exploit these opportunities, this paper analyses the data potential in the automated CAR-T production process and creates a mapping to the capabilities of Al applications. The paper explores the possible use of Al in analyzing the data generated during the automated process and its capabilities to further improve the efficiency and cost-effectiveness of CAR-T cell production. 本文探討生產 CAR-T 細胞以治療癌症的挑戰,以及人工智能(AI)在改善過程中的潛力。2018 年,CAR-T 細胞療法獲批成為首個經高級療法藥品(ATMP)認證用於治療急性白血病和淋巴瘤的療法。ATMP 是基於細胞和基因的療法,在治療各種癌症和遺傳性疾病方面前景廣闊。儘管已有部分新的 ATMP 獲批,但預計正在進行的臨床試驗將導致更多 ATMP 獲批。然而,生產 CAR-T 細胞存在重大挑戰,因為製造過程成本高昂,令療法昂貴(約 40 萬美元)。此外,自體 CAR-T 療法受限於按需製造的方式,這使得實現經濟規模生產困難。目前正在試圖將這一多步驟製造過程自動化,不僅可以直接降低高昂的製造成本,還能實現全面的數據收集。AI 技術有能力分析這些數據,並將其轉換為知識和見解。為了利用這些機會,本文分析了自動化 CAR-T 生產過程中的數據潛力,並將其與 AI 應用的能力進行了對應。本文探討了在自動化過程中生成的數據分析中使用 AI 的可能性,以及其進一步提高 CAR-T 細胞生產效率和降低成本的能力。
KEYWORDS 關鍵詞
CAR-T manufacturing, artificial intelligence, machine learning, cell and gene therapy, immunotherapy, data analytics, ATMP, advanced therapy 汽車免疫細胞療法製造、人工智能、機器學習、細胞與基因療法、免疫療法、數據分析、先進療法產品、先進療法
1 Introduction 1 緒論
The approval of the first chimeric antigen receptor (CAR)-T cell product in the European Union in 2018 marked a significant paradigm shift in the treatment of acute lymphoblastic leukemia (ALL) (EMA/188757/2022 Kymriah, 2022). Since then, the field of advanced therapies has rapidly evolved, with the approval of nine additional Gene Therapy Medicinal Products (GTMP) and a multitude of ongoing clinical trials. Approved GTMPs are for the treatment of multiple myeloma, melanoma and inherited diseases such as hemophilia and retinal dystrophy (Paul-Ehrlich-Institut, 2023). In addition, current clinical trials focus on solid tumors and alternatives for T cells such as NK cells and macrophages (Marofi et al., 2021; Pan et al., 歐洲聯盟於 2018 年批准首款嵌合抗原受體(CAR)-T 細胞產品,這標誌著用於治療急性淋巴細胞白血病(ALL)的治療範式發生重大轉變(EMA/188757/2022 Kymriah, 2022)。自此之後,先進療法領域已迅速發展,先後批准了九種基因療法藥物產品(GTMP),並有大量臨床試驗正在進行。獲批的 GTMP 用於治療多發性骨髓瘤、黑色素瘤以及血友病和視網膜營養不良等遺傳性疾病(Paul-Ehrlich-Institut, 2023)。此外,目前的臨床試驗還關注固體腫瘤以及替代 T 細胞的細胞類型,如 NK 細胞和巨噬細胞(Marofi et al., 2021; Pan et al.,
FIGURE 1 圖 1
CAR-T cell therapy process and its challenges. 嶄新的 CAR-T 細胞免疫療法與其挑戰
2022). However, despite the significant clinical success of these therapies, high costs in manufacturing and supply hinder wide-scale patient access. For cost reduction, the complex manufacturing processes need to be better characterized to ultimately ensure a successful therapy outcome. 儘管這些療法在臨床上取得了顯著成功,但是由於製造和供應成本高昂,使得廣泛的患者無法獲得。為了降低成本,需要更好地描述複雜的製造過程,最終確保療法順利取得成功。
For this reason, the field is moving steadily toward digitization and automation of the entire therapy process (Blache et al., 2022). One project dedicated to this approach is the European Union Horizon 2020 project AIDPATH (European Commision, 2021a) which is an acronym for Artificial Intelligence-driven, Decentralized Production for Advanced Therapies in the Hospital. AIDPATH aims to develop an open platform for the production of CAR-T cells using flexible automation concepts together with digital solutions for data management and the integration of AI (Hort et al., 2022). In particular, the use of AI holds great potential and has the possibility to improve CAR-T cell manufacturing in the future. AI has gained increasing popularity in recent years due to its ability to process everincreasing amounts of data and support its analytical capabilities. 出于此原因，该领域正稳步向着整个疗程的数字化和自动化发展(Blache 等人，2022 年)。致力于这一方法的项目之一是欧洲联盟地平线 2020 项目 AIDPATH(European Commision，2021a)，这是一个缩写词,代表人工智能驱动的医院先进疗法的分散式生产。AIDPATH 旨在开发一个用于 CAR-T 细胞生产的开放平台,结合灵活的自动化概念以及用于数据管理和人工智能集成的数字解决方案(Hort 等人，2022 年)。特别是,人工智能拥有巨大的潜力,并有可能在未来提高 CAR-T 细胞制造的效率。近年来,由于人工智能处理越来越多数据并支持其分析能力的能力,其日益受到欢迎。
The use of AI in CAR-T cell therapy presents both opportunities and challenges. Integrating AI technologies can improve manufacturing efficiency and accuracy, optimize logistics, and reduce costs. AI can also assist in identifying appropriate patients for therapy and help monitor therapy progression and predict treatment responses. However, there are still open issues and challenges to overcome. Privacy, security, and ethical issues play a critical role in implementing AI in CAR-T cell therapy. In addition, the integration of AI systems into existing production workflows and the validation of AI-based decisions still need to be explored. 在 CAR-T 细胞治疗中使用 AI 既有机遇也有挑战。整合 AI 技术可提高生产效率和准确性，优化物流并降低成本。AI 还可协助识别适合接受治疗的患者，并帮助监测治疗进程并预测治疗反应。然而,仍有待解决的问题和挑战。隐私、安全和伦理问题在将 AI 应用于 CAR-T 细胞治疗中发挥关键作用。此外,将 AI 系统整合到现有的生产工作流程中以及验证基于 AI 的决策仍需进一步探索。
Therefore, this paper is dedicated to the topic of AI in CAR-T cell therapy. It highlights the fundamentals and potentials of AI in a manufacturing context and explores why its use in CAR-T cell therapy has been limited to date. Furthermore, this paper discusses the potential uses of AI in the treatment process and identifies existing barriers. In addition, existing AI methods are categorized and listed along the therapy process. Finally, an outlook on the future development of AI in the field of CAR-T cell therapy is provided, highlighting potential trends and opportunities. 因此,本文致力於探討人工智能在 CAR-T 細胞療法中的應用。它強調了人工智能在製造環境中的基本原理和潛力,並探討了到目前為止其在 CAR-T 細胞療法中使用有限的原因。此外,本文討論了人工智能在治療過程中的潛在用途,並確定了現有的障礙。此外,現有的人工智能方法被分類和列出,並與療法過程相對應。最後,本文展望了人工智能在 CAR-T 細胞療法領域未來的發展,突出了潛在的趨勢和機遇。
Overall, the integration of AI into CAR-T cell therapy has the potential to provide significant advances in the production of CART cells and treatment of leukemia and lymphoma. By overcoming challenges and targeting the potential of AI, new therapies can be 整體而言,將人工智慧整合到 CAR-T 細胞療法中,有潛力為白血病和淋巴瘤的 CAR-T 細胞生產和治療帶來重大進展。通過克服挑戰並發揮人工智慧的潛力,可以開發出新的療法。
developed more efficiently and made available to patients more quickly. 開發更有效並更快速地提供給病患。
2 Definition of AI and applications in manufacturing 2 人工智能的定義及其在製造業的應用
The potential of AI in healthcare is enormous, as evidenced by its rapid market growth and significant investments in research and development. By 2027, the AI market is projected to reach a staggering $407\$ 407 billion, with the manufacturing sector poised to experience a financial impact of $3.8\$ 3.8 trillion by 2035 (Maslej et al., 2023). Notably, the healthcare industry has received the highest investment, amounting to $6.1\$ 6.1 billion in 2022. Organizations that have already embraced AI in healthcare have reported remarkable cost reductions and revenue increases (Haan, 2023). 人工智能在醫療保健領域的潛力是巨大的,這從其快速的市場增長和對研發的大量投資中可見一斑。據預測,到 2027 年,人工智能市場規模將達到驚人的 $407\$ 407 億美元,到 2035 年,製造業將受到 $3.8\$ 3.8 萬億美元的經濟影響(Maslej et al., 2023)。值得注意的是,醫療保健行業在 2022 年獲得了 $6.1\$ 6.1 億美元的投資,這是最高的。已經在醫療保健領域採用人工智能的組織報告了顯著的成本降低和收入增加(Haan, 2023)。
In information systems, AI can be described as an agent. Kühl et al. distinguish here between simple reflex agents and learning agents (Kühl et al., 2022). A reflexive agent applies knowledge once acquired from an initial implementation to its environment, while a learning agent continues to learn by interacting with its environment after initial training. Both types of agents are described by their interaction with their environment. This interaction consists of the reception of data from the environment and on an action to be executed in the environment. Internally, acquired knowledge is applied to achieve a given goal by the execution of an action. Now, such an intelligent agent may have acquired this knowledge by training Machine Learning (ML) models, or it may have a non-ML based knowledge representation, such as a rule-based expert system. ML, meanwhile, can be viewed as an implementation of statistical learning. Thus, ML, is a method applied by AI systems (Kühl et al., 2020). 在資訊系統中，人工智慧可被描述為一個代理人。Kühl 等人在此區分了簡單反射代理人和學習代理人(Kühl 等人，2022)。反射性代理人將一開始從實現中獲得的知識應用於其環境，而學習代理人在初始訓練後通過與其環境互動而不斷學習。這兩種代理人都是由其與環境的互動來描述的。這種互動包括從環境接收數據以及在環境中執行的操作。內部上，獲得的知識被應用於通過執行操作來實現給定的目標。現在，這樣一個智能代理人可能已經通過訓練機器學習(ML)模型獲得了這些知識，或者它可能有一個非 ML 基礎的知識表示，例如基於規則的專家系統。同時，ML 可以被視為統計學習的一種實現。因此，ML 是人工智慧系統所採用的一種方法(Kühl 等人，2020)。
Such an intelligent agent can interact with its environment with different degrees of autonomy. A possible categorization of autonomy can be made by the amount of human interaction in the process of data analysis from the data basis to the decision or action. Here, a distinction can be made between descriptive, diagnostic, predictive, and prescriptive tasks with which the agent is entrusted (Sallam et al., 2014; Kühn et al., 2018). A descriptive agent describes what is happening in the environment. The human must figure out why it is happening and what will happen to derive a decision or action that will change the environment in the desired sense. A diagnostic agent now goes one step 如此智慧型代理人可以與其環境以不同程度的自主性進行互動。可根據資料分析過程中人類互動的程度，對自主性進行可能的分類。這裡可以區分描述性、診斷性、預測性和處方性任務，由該代理人負責這些任務(Sallam 等人，2014 年; Kühn 等人，2018 年)。描述性代理人描述環境中正在發生的事情。人類必須弄清楚為什麼會發生這種情況，以及會發生什麼事情，從而得出一個改變環境的決定或行動。診斷性代理人現在進一步分析突如其來的事件。
further and tries to explain relationships in the environment. A predictive agent goes further still and predicts how the environment will change in the future. Finally, a prescriptive agent supports the human in deciding which action to take to achieve a desired result or carries out the action itself. A bioreactor can provide an example of the differentiation of agents in the process of CAR-T cell production explained here: a descriptive agent describes the number of cells in the bioreactor, a diagnostic agent can justify why exactly this number of cells is found in the reactor on the basis of the information supplied. A predictive agent can predict the number of cells for a point in time in the future and a prescriptive agent can determine the optimal time to harvest and propose it to the operator and if all regulatory aspects are covered, trigger the process itself. 在環境中進一步探討並嘗試闡述關係。預測型智能體更進一步預測環境將如何在未來發生變化。最後,規範型智能體協助人類決定要採取哪種行動以實現所需結果,或者自行執行該行動。生物反應器可以提供一個智能體在 CAR-T 細胞生產過程中分化的實例:描述型智能體描述生物反應器中的細胞數量,診斷型智能體可以根據提供的信息解釋為什麼會有這個數量的細胞存在於反應器中。預測型智能體可以預測未來某個時間點的細胞數量,而規範型智能體可以確定最佳收穫時間並提議給操作員,如果所有監管方面都得到覆蓋,它還能自行啟動該過程。
3 CAR-T therapy process and its challenges 3 CAR-T 療法過程及其挑戰
The manufacturing and provision of CAR-T cells pose new challenges for hospitals and treatment centers. Due to the autologous nature of the therapy, T cells are removed from patients in the hospital, shipped to a pharmaceutical company or an academic site for CAR-T cell manufacturing, and then shipped back for administration to the patient. Figure 1 illustrates the treatment process and the challenges involved (Iyer et al., 2018; Enejo, 2019; Braga et al., 2021). 生產和提供 CAR-T 細胞為醫院和治療中心帶來新挑戰。由於療法的自體性質,T 細胞從病人處被取出,運送至製藥公司或學術機構進行 CAR-T 細胞製造,然後再運回給病人使用。圖 1 說明了治療過程及所涉及的挑戰(Iyer 等人,2018 年;Enejo,2019 年;Braga 等人,2021 年)。
First, the patients are registered in the hospital and their eligibility for the therapy is determined (Braga et al., 2021). Blood is then drawn from the patient and the leukocytes are isolated (leukapheresis). At the manufacturing site the leukocytes are preprepared and the desired T cells are selected. Which T cells are selected depends on the chosen product. Which T cells and in which ratio they yield the best quality is the focus of current research. In the subsequent activation step, the cells are stimulated for proliferation and differentiation. Afterward, the CAR is integrated in the genome of the T cells (genetic modification). Different methods can be used for this such as viral transduction or nonviral transfection. The latter was developed more recently for safer and more cost-efficient genetic modification (Harris and Elmer, 2021). Then, the CAR-T cells are expanded to reach the required amount. With 7-107-10 days, the expansion process is by far the longest manufacturing process and thus a major driver for the overall delivery time, besides the final quality and release criteria control. Therefore the trend is to reduce the duration of the expansion time to the minimum amount of time to get a sufficient product and reduce the delivery time. Lastly, the CAR-T cells are cryopreserved and shipped back to the hospital. At the hospital, the patient receives the necessary bridging therapies (e.g., chemotherapy), the manufactured product is checked and administered to the patient. In the post-treatment phase, the patient continues to be monitored and remains in the hospital for up to 10 days. For the following 28 days, it is recommended that the patient stays within a 2-h distance to the hospital (Kymriah, 2018; Iyer et al., 2018; Vormittag et al., 2018; Braga et al., 2021). 首先,患者在医院登记,并确定他们接受治疗的资格(Braga et al., 2021)。然后从患者身上抽取血液,并分离出白细胞(白细胞分离术)。在制造地点,白细胞被预先处理,所需的 T 细胞被选择。选择哪些 T 细胞以及它们以何种比例能产生最佳质量,是当前研究的重点。在随后的激活步骤中,细胞被刺激以促进增殖和分化。之后,CAR 被整合到 T 细胞的基因组中(基因修饰)。可以使用不同的方法来实现,如病毒转导或非病毒转染。后者的发展更加安全和更具成本效益(Harris and Elmer, 2021)。然后,CAR-T 细胞被扩增到所需的数量。扩增过程需要 7-107-10 天,这是制造过程中最长的一个步骤,因此是整体交付时间的主要驱动因素,除了最终质量和放行标准控制。因此,趋势是将扩增时间尽量缩短到获得足够产品所需的最小时间,从而缩短交付时间。最后,CAR-T 细胞被冷冻保存并运送回医院。在医院,患者接受必要的过渡性治疗(如化疗),制造的产品进行检查并给予患者。在治疗后阶段,继续监测患者,患者可能在医院停留长达 10 天。在随后的 28 天内,建议患者留在距医院 2 小时路程以内的地方(Kymriah, 2018; Iyer et al., 2018; Vormittag et al., 2018; Braga et al., 2021)。
Across the treatment process, challenges emerge that currently still hinder equitable and affordable CAR-T cell therapy. Figure 1 summarizes the main challenges. A major barrier to wide access to CAR-T cell therapy is the associated cost. The cost of approved products is $475,000\$ 475,000 for Kymriah^(®)\mathrm{Kymriah}^{\circledR} and $373,000\$ 373,000 for Yescarta ^(®){ }^{\circledR} (Geethakumari et al., 2021). In addition, there are other costs 在治療過程中,仍存在阻礙公平及可負擔 CAR-T 細胞療法的挑戰。圖 1 概述了主要的挑戰。可獲得 CAR-T 細胞療法的主要障礙是相關成本。已核准產品的成本為 $475,000\$ 475,000 美元(Kymriah)和 $373,000\$ 373,000 美元(Yescarta)(Geethakumari 等人,2021 年)。此外,還有其他成本
associated with bridging therapies, follow-up, and possible treatment of side effects (Kamal-Bahl et al., 2022). In the EU, reimbursement practices for CAR-T cell therapies are inconsistent and occur through separate compensation payments. Pricing decisions are mostly made between pharmaceutical companies and regulators. A uniform reimbursement model is proving difficult due to regional and country-specific factors (Haag et al., 2022). A 2020 study highlights the significant administrative and financial challenges faced by hospitals and treatment centers in Germany. Problems with reimbursement and the need to make advance payments are often apparent here (Wörmann, 2020). One solution for uniform and fair reimbursement could be outcome-based reimbursement models (OMS), in which costs are only incurred if the therapy is successful. Challenges arise here, however, in the comparability of clinical studies and an overall lack of understanding of the manufacturing process (Solbach et al., 2020). 與疗桥接疗法、随访和可能的副作用治疗相关(Kamal-Bahl et al., 2022)。在欧盟,CAR-T 细胞疗法的报销做法不一致,通过单独的补偿支付进行。定价决定主要由制药公司和监管者做出。由于地区和国家特定因素,建立一个统一的报销模式很困难(Haag et al., 2022)。2020 年的一项研究强调了德国医院和治疗中心面临的重大行政和财务挑战。报销问题和需要预付款的必要性在此处往往很明显(Wörmann, 2020)。一种可能的解决方案是基于结果的报销模式(OMS),只有在疗法成功的情况下才产生费用。但在这里,临床研究的可比性以及对制造过程整体缺乏理解的挑战也随之而来(Solbach et al., 2020)。
An autologous CAR-T cell product is a complex biological product consisting of the patient’s genetically modified T cells. Accordingly, the quality of the product varies greatly with the patient’s biological material as well as with the manufacturing process. Thus, even small effects in the process can have a large impact on the product. These include, for example, different procedures for T-cell stimulation and the gene delivery process (Stock et al., 2019), as well as the choice of reagents (Egri et al., 2020; Ghassemi et al., 2020). The focus in recent years has also tended to be on optimizing biological parameters to increase response rates rather than improving the overall process chain. More recently, the field has also been shifting to optimizing the production process and thus reducing process times and eliminating manual processes. Technological concepts and devices enable the automation of single process steps (e.g., through liquid handling units or bioreactors) and the entire process chain (e.g., CliniMACS ^(***){ }^{\star}, Lonza Cocoon ^(@){ }^{\circ} ) (Moutsatsou et al., 2019). While the latter drastically reduce human interaction and thus increase standardization and reproducibility, they follow a one-device-per-patient approach, which makes scalability difficult. In the AIDPATH research project, these limitations are being addressed via a modular, vendor-independent platform for parallel, automated manufacturing and quality control (Hort et al., 2022). 自體 CAR-T 細胞產品是一種複雜的生物產品,由患者遺傳修飾的 T 細胞組成。因此,該產品的質量在很大程度上取決於患者的生物材料以及製造過程。因此,即使製程中的小效果也可能對產品產生重大影響。這些包括,例如,T 細胞刺激的不同程序和基因遞送過程(Stock et al., 2019),以及試劑的選擇(Egri et al., 2020; Ghassemi et al., 2020)。近年來,重點也傾向於優化生物參數以提高反應率,而不是改善整個過程鏈。最近,該領域也正在轉向優化生產過程,從而縮短過程時間並消除手動過程。技術概念和設備可以實現單個工藝步驟(如通過液體操作單元或生物反應器)和整個工藝鏈(如 CliniMACS、Lonza Cocoon)的自動化(Moutsatsou et al., 2019)。雖然後者大大減少了人工操作,從而提高了標準化和可重複性,但它們遵循每患者一個設備的方法,這使得擴展性很困難。在 AIDPATH 研究項目中,正在通過一個模塊化的、供應商獨立的平台來解決這些局限性,用於並行自動化製造和質量控制(Hort et al., 2022)。
Another challenge is evident in the side effects and uncertain efficacy of CAR-T cell therapy. The most common side effects are cytokine release syndrome (CRS) and immune effector cellassociated neurotoxicity syndrome (ICANS). In CRS, there is a massive release of cytokines caused by the contact of CAR-T cells with the target antigens of cancer cells. ICANS affects the central nervous system and can cause a variety of symptoms. Other phenomena that affect efficacy include antigen loss, tumor heterogeneity, and lack of persistence (Ayuketang et al., 2022; Rees et al., 2022). 另一個挑戰是 CAR-T 細胞療法的副作用和不確定療效。最常見的副作用是細胞因子釋放綜合症 (CRS) 和免疫效應細胞相關神經毒性綜合症 (ICANS)。在 CRS 中,由於 CAR-T 細胞與癌細胞的目標抗原接觸而引發大量細胞因子的釋放。ICANS 影響中樞神經系統,可引發各種症狀。影響療效的其他現象包括抗原丟失、腫瘤異質性和持久性不足 (Ayuketang et al., 2022; Rees et al., 2022)。
Adequate infrastructure also has a major impact on equitable access to CAR-T cell therapy. While there is sufficient coverage in Germany with 39 CAR-T centers (Novartis, 2023), there are large gaps in coverage in the USA (especially in the Southeast and Midwest) (Kamal-Bahl et al., 2022). This involves not only the buildings, facilities, and cleanrooms, but also adequately trained personnel. A variety of individuals from different disciplines are needed throughout the therapy process, all of whom must be trained and qualified (Beaupierre et al., 2019). 適當的基礎設施也對獲得 CAR-T 細胞療法的公平性產生重大影響。雖然在德國有 39 個 CAR-T 中心(Novartis, 2023)的足夠覆蓋率,但在美國(特別是東南部和中西部)則存在大量的覆蓋缺口(Kamal-Bahl 等人,2022)。這不僅涉及建築物、設施和無塵室,還需要有適當培訓的人員。在整個療程中需要各個不同領域的各種人員,所有這些人都必須接受培訓並獲得資格認證(Beaupierre 等人,2019)。
TABLE 1 Relevant AI research in CAR-T cell manufacturing and therapy (* marks work, that is not yet implemented). 表 1 CAR-T 細胞製造和療法中的相關人工智能研究（*標記的工作尚未實施）。
CAR design 汽車設計
Patient evaluation and selection 患者評估與選擇
T-Cell extraction and preparation 細胞提取及準備
Genetic engineering and expansion 基因工程與擴張
Conditioning therapy and infusion 調理療法與輸注
Post-treatment and recovery 治療後恢復
descriptive 描述性的
Lee et al. (2020) 李等人 (2020)
Naghizadeh et al. (2022) 納吉扎德等人 (2022)
[UC2] [UC2]
[UC2]
diagnostic 診斷
利貝利尼等人（2021）、比克斯等人（2023）
Liberini et al.
(2021), Beekers et al.
(2023)
Liberini et al.
(2021), Beekers et al.
(2023)| Liberini et al. |
| :--- |
| (2021), Beekers et al. |
| (2023) |
predictive 預測性
莫施等(2019)、丹納範斯勒等(2020)、李等(2020)
Mösch et al. (2019),
Dannenfelser et al.
(2020), Lee et al.
(2020)
Mösch et al. (2019),
Dannenfelser et al.
(2020), Lee et al.
(2020)| Mösch et al. (2019), |
| :--- |
| Dannenfelser et al. |
| (2020), Lee et al. |
| (2020) |
Gil and Grajek (2022)^(**)(2022)^{*} 吉爾和格拉傑
O'Reilly et al. (2023) 奧瑞利等人(2023 年)
[UC2] Wu et al. (2018), Reyes et al. (2022) [UC2] 吳等人（2018 年）、雷耶斯等人（2022 年）
Banerjee et al. (2021), Tang et al. (2020), Tedesco and Mohan (2021), Le et al. (2019), Fleuren et al. (2020), Bedoya et al. (2020), Giannini et al. (2019), Beekers et al. (2023) 巴納吉等(2021 年)、湯等(2020 年)、泰德斯科和莫漢(2021 年)、黎等(2019 年)、弗萊倫等(2020 年)、貝多雅等(2020 年)、吉安尼等(2019 年)、比克斯等(2023 年)
prescriptive 規範的
[UC3, 4] Sugimoto (2019) 【UC3, 4】杉本(2019)
[UC1,3,4][\mathrm{UC} 1,3,4]
[UC4]
CAR design Patient evaluation and selection T-Cell extraction and preparation Genetic engineering and expansion Conditioning therapy and infusion Post-treatment and recovery
descriptive Lee et al. (2020) Naghizadeh et al. (2022) [UC2]
diagnostic "Liberini et al.
(2021), Beekers et al.
(2023)"
predictive "Mösch et al. (2019),
Dannenfelser et al.
(2020), Lee et al.
(2020)" Gil and Grajek (2022)^(**) O'Reilly et al. (2023) [UC2] Wu et al. (2018), Reyes et al. (2022) Banerjee et al. (2021), Tang et al. (2020), Tedesco and Mohan (2021), Le et al. (2019), Fleuren et al. (2020), Bedoya et al. (2020), Giannini et al. (2019), Beekers et al. (2023)
prescriptive [UC3, 4] Sugimoto (2019) [UC1,3,4] [UC4] | | CAR design | Patient evaluation and selection | T-Cell extraction and preparation | Genetic engineering and expansion | Conditioning therapy and infusion | Post-treatment and recovery |
| :---: | :---: | :---: | :---: | :---: | :---: | :---: |
| descriptive | Lee et al. (2020) | | Naghizadeh et al. (2022) | [UC2] | | |
| diagnostic | | Liberini et al. <br> (2021), Beekers et al. <br> (2023) | | | | |
| predictive | Mösch et al. (2019), <br> Dannenfelser et al. <br> (2020), Lee et al. <br> (2020) | Gil and Grajek $(2022)^{*}$ | O'Reilly et al. (2023) | [UC2] Wu et al. (2018), Reyes et al. (2022) | | Banerjee et al. (2021), Tang et al. (2020), Tedesco and Mohan (2021), Le et al. (2019), Fleuren et al. (2020), Bedoya et al. (2020), Giannini et al. (2019), Beekers et al. (2023) |
| prescriptive | | | [UC3, 4] Sugimoto (2019) | $[\mathrm{UC} 1,3,4]$ | [UC4] | |
4 Al application scenarios in CAR-T cell therapy 細胞免疫療法中 4 個人工智慧應用場景
In this section the process described in Section 3 is overlaid with AI use cases found in the literature. Table 1 provides an overview of the process steps as well as the stages of development of AI systems. Relevant work is mapped herein to identify focus areas of research and highlight potential gaps. 在本節中,第 3 節中所描述的過程與文獻中發現的人工智能應用案例重疊疊合。表 1 概述了該過程的步驟以及人工智能系統的發展階段。相關工作被放映在此處,以確定研究重點領域並突出潛在差距。
A large focus of current research on AI in CAR-T cell therapy deals with patient follow-up. Here, the emphasis is on predicting the occurrence of side effects like CRS or sepsis after the therapy is administered (Bedoya et al., 2020; Fleuren et al., 2020; G et al., 2019; Le et al., 2019; Tang et al., 2020; Tedesco and Mohan, 2021). To monitor patients more closely, one team is proposing the use of smart devices and wearables to use ML to analyse the data collected there and respond even more quickly (Banerjee et al., 2021). In the field of patient evaluation and selection, biomarker evaluation plays a crucial role to ensure successful therapy in the CAR-T process. In this regard (Gil and Grajek, 2022), suggests a consideration of biomarker-based selection criteria to ensure that therapy is optimally effective (not yet implemented, therefore marked with * in Table 1). Another use case is to select patients in whom the therapy is likely to achieve the best results (Liberini et al., 2021). Another important step in the CAR-T process is the extraction and preparation of the T cells. Here, healthy CD 3 T cells are specifically selected to provide an optimal starting point for the further steps of the process (Sugimoto, 2019). In addition, pre-cell selection data will allow prediction of optimal cell selection timing for patients individually to achieve maximum benefit (O’Reilly et al., 2023). 對現有 CAR-T 細胞治療的 AI 研究而言，患者的後續跟進是一個重點。重點在於預測療程後出現細胞因數釋放綜合徵或敗血症等副作用的發生 (Bedoya 等人, 2020; Fleuren 等人, 2020; G 等人, 2019; Le 等人, 2019; Tang 等人, 2020; Tedesco 和 Mohan, 2021)。為了更密切監測患者,有一個團隊提出使用智能設備和可穿戴設備,利用機器學習分析收集到的數據,以更快速地做出反應 (Banerjee 等人, 2021)。在患者評估和選擇領域,生物標記評估在確保 CAR-T 療程成功方面扮演著關鍵作用。就此而言,(Gil and Grajek, 2022) 建議考慮基於生物標記的選擇標準,以確保治療效果最佳化 (尚未實施,因此在表 1 中用 * 標記)。另一個用例是選擇可能獲得最佳療效的患者 (Liberini 等人, 2021)。CAR-T 療程的另一個重要步驟是 T 細胞的提取和準備。這裡,選擇特定的健康 CD 3 T 細胞,作為後續步驟的最佳起點 (Sugimoto, 2019)。此外,細胞選擇前的數據將允許預測每個患者的最佳細胞選擇時間,以獲得最大效益 (O'Reilly 等人, 2023)。
In the genetic engineering and expansion phase, predictive quality assessment of the cell product is performed to predict the clinical outcome of the therapy (Naghizadeh et al., 2022). Surveys by Wu et al. (Wu et al., 2018) in 2018 and Reyes et al. (Reyes et al., 2022) in 2022 provide insights into the state-of-the-art soft sensors and AI for cell culture control. Wu et al. (Wu et al., 2018) focus on automated cell expansion trends and KPIs such as foaming, cell count, viability, glycosylation, biomass, and morphology, highlighting fluorescence, Raman spectroscopy, chemometrics, and artificial neural networks. Reyes et al. (Reyes et al., 2022) conduct a comprehensive survey covering various modern sensor tools, including artificial neural networks, spectroscopy, optical sensors, free-floating wireless sensors, 在遺傳工程和擴張階段,進行細胞產品的預測性質量評估,以預測療法的臨床結果(Naghizadeh et al., 2022)。 2018 年的 Wu 等人(Wu et al., 2018)和 2022 年的 Reyes 等人(Reyes et al., 2022)的調查提供了先進軟感測器和人工智能用於細胞培養控制的洞見。 Wu 等人(Wu et al., 2018)關注自動細胞擴張趨勢和關鍵績效指標,如起泡、細胞計數、活力、糖基化、生物量和形態,突出螢光、拉曼光譜、化學計量學和人工神經網路。 Reyes 等人(Reyes et al., 2022)進行了全面的調查,涵蓋了各種先進的傳感器工具,包括人工神經網路、光譜學、光學傳感器、自由漂浮的無線傳感器。
and statistical methods for modeling cell density and antibody titers. Another field that is being strongly addressed is the design of the CAR gene and its effect on cells and tumours prior to the manufacturing process. Here, the correlations between different possible markers and their effects on tumour cells are investigated and an attempt is made to predict possible efficacy (Mösch et al., 2019; Dannenfelser et al., 2020; Lee et al., 2020). 用於建模細胞密度和抗體滴度的數學和統計方法。另一個被大力關注的領域是 CAR 基因的設計及其對製造過程前的細胞和腫瘤的影響。在這裡,調查了不同可能標記之間的相關性及其對腫瘤細胞的影響,並嘗試預測可能的療效 (Mösch et al., 2019; Dannenfelser et al., 2020; Lee et al., 2020)。
In addition to the listed use cases from literature, other use cases for AI in CAR-T cell production are being investigated in the AIDPATH research project. Two of those use cases (UC) deal directly with the most time-consuming process step, the expansion of the CAR-T cells in the bioreactor. Use case 1 focuses on the development of a digital twin of the bioreactor by mechanistically modelling its design and control, as well as modelling the CAR-T cells growth via the consumption of key nutrients and production of metabolites. This digital twin will provide a softsensor of cell-concentration in real-time, as well as short term ( 1-21-2 days) forecasts of cell concentration in the future. Such predictions can then be used to inform when the expansion stage should be terminated based on assessment of whether the target dose (i.e., required cell number for treatment) has been reached. In Use case 2 a reactive online process control based on a set of ‘soff’ sensors is developed to complement the existing PID controller for real-time monitoring of key bioreactor parameters [UC2]. These soft sensors process data from 8 selected ‘hard’ sensors and provide consensus alerts to the human operator. Different soft sensor algorithms, including statistically based and artificial intelligence techniques, contribute to the overall confidence in assessing the situation. Future developments aim to include patientspecific adaptations by adjusting sensor set points and algorithm configurations. Furthermore, the modular concept (Section 3) raises the problem of the production scheduling of the manufacturing platform. If, in the future, the capacity of the plant is increased so that the products of multiple patients can be manufactured concurrently, the optimization of the production through scheduling [UC3] becomes inevitable. The uncertainty of the cell-expansion process combined with hard time constraints between consecutive production processes requires new scheduling methodology. Furthermore, the coordination of the patients’ therapies running in parallel [UC4] must be added to the system in order to manage the uncertainties in all steps of the therapies and to ensure that the patient and the product are ready at the same time (Hort et al., 2022). 除了文獻中列出的案例之外,AI 在 CAR-T 細胞生產中的其他用例正在 AIDPATH 研究項目中進行調查。其中兩個用例(UC)直接涉及最耗時的過程步驟,即生物反應器中 CAR-T 細胞的擴增。用例 1 側重於通過機械模擬生物反應器的設計和控制,以及通過對關鍵營養物質的消耗和代謝物的產生來模擬 CAR-T 細胞的生長,來開發生物反應器的數字孿生。這個數字孿生將提供實時的細胞濃度軟感測器,以及未來細胞濃度的短期(< 5 天)預測。這種預測可用於評估擴增階段是否應該終止,因為目標劑量(即治療所需的細胞數量)已經達到。在用例 2 中,基於一組"軟"感測器的反應性在線過程控制被開發,以補充現有的 PID 控制器,對生物反應器的關鍵參數進行實時監測[UC2]。這些軟傳感器處理來自 8 個選定的"硬"傳感器的數據,並向人工操作員提供共識警報。不同的軟傳感器算法,包括基於統計的和人工智能的技術,有助於提高對情況評估的整體信心。未來的發展目標是通過調整傳感器設定點和算法配置來包含患者特定的適應性。此外,模塊化概念(第 3 節)引發了製造平台生產計劃的問題。如果未來工廠的產能提高,使得多個患者的產品可以同時製造,則通過計劃優化生產[UC3]是不可避免的。 細胞擴張過程的不確定性加上連續生產過程之間的嚴格時間限制,需要新的排程方法。此外,平行進行的患者治療計畫的協調[UC4]必須納入系統,以管理治療各步驟的不確定性,確保患者和產品能夠同時就緒(Hort et al., 2022)。
